2,622 results
Search Results
2. Reply: Letter to the editor from Aktas in relation to the paper "Prognostic value of the Geriatric Nutritional Risk Index and other hematological markers on long-term survival in the geriatric population".
- Author
-
da Costa Pereira, Jarson Pedro, da Silva Diniz, Alcides, Chaves de Lemos, Maria Conceição, Sabino Pinho Ramiro, Cláudia Porto, and Coelho Cabral, Poliana
- Subjects
- *
PREDICTIVE tests , *SURGICAL complications , *GERIATRIC nutrition , *BIOMARKERS - Published
- 2024
- Full Text
- View/download PDF
3. Study of Flare Assessment in Systemic Lupus Erythematosus Based on Paper Patients.
- Author
-
Isenberg, D., Sturgess, J., Allen, E., Aranow, C., Askanase, A., Sang-Cheol, B., Bernatsky, S., Bruce, I., Buyon, J., Cervera, R., Clarke, A., Dooley, Mary Anne, Fortin, P., Ginzler, E., Gladman, D., Hanly, J., Inanc, M., Jacobsen, S., Kamen, D., and Khamashta, M.
- Subjects
SYSTEMIC lupus erythematosus diagnosis ,CLINICAL competence ,COMPARATIVE studies ,CONSENSUS (Social sciences) ,DECISION making ,RESEARCH methodology ,MEDICAL cooperation ,MEDICAL records ,RESEARCH ,RESEARCH evaluation ,EVALUATION research ,PREDICTIVE tests ,RESEARCH bias ,SEVERITY of illness index ,DISEASE progression - Abstract
Objective: To determine the level of agreement of disease flare severity (distinguishing severe, moderate, and mild flare and persistent disease activity) in a large paper-patient exercise involving 988 individual cases of systemic lupus erythematosus.Methods: A total of 988 individual lupus case histories were assessed by 3 individual physicians. Complete agreement about the degree of flare (or persistent disease activity) was obtained in 451 cases (46%), and these provided the reference standard for the second part of the study. This component used 3 flare activity instruments (the British Isles Lupus Assessment Group [BILAG] 2004, Safety of Estrogens in Lupus Erythematosus National Assessment [SELENA] flare index [SFI] and the revised SELENA flare index [rSFI]). The 451 patient case histories were distributed to 18 pairs of physicians, carefully randomized in a manner designed to ensure a fair case mix and equal distribution of flare according to severity.Results: The 3-physician assessment of flare matched the level of flare using the 3 indices, with 67% for BILAG 2004, 72% for SFI, and 70% for rSFI. The corresponding weighted kappa coefficients for each instrument were 0.82, 0.59, and 0.74, respectively. We undertook a detailed analysis of the discrepant cases and several factors emerged, including a tendency to score moderate flares as severe and persistent activity as flare, especially when the SFI and rSFI instruments were used. Overscoring was also driven by scoring treatment change as flare, even if there were no new or worsening clinical features.Conclusion: Given the complexity of assessing lupus flare, we were encouraged by the overall results reported. However, the problem of capturing lupus flare accurately is not completely solved. [ABSTRACT FROM AUTHOR]- Published
- 2018
- Full Text
- View/download PDF
4. Testing differences in predictive ability: A tutorial.
- Author
-
Fearn, Tom
- Subjects
- *
PREDICTIVE tests , *PREDICTION models , *FORECASTING , *CLASSIFICATION - Abstract
This paper describes some statistical tests for comparing the predictive performance of two or more prediction rules. It covers the cases of both quantitative and qualitative predictions, that is, both regression and classification problems. Worked examples are included for both cases. This paper describes some statistical tests for comparing the predictive performance of two or more prediction rules. It covers the cases of both quantitative and qualitative predictions, that is, both regression and classification problems. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Development and Validation of the FSIQ-RMS: A New Patient-Reported Questionnaire to Assess Symptoms and Impacts of Fatigue in Relapsing Multiple Sclerosis.
- Author
-
Hudgens, Stacie, Schüler, René, Stokes, Jonathan, Eremenco, Sonya, Hunsche, Elke, and Leist, Thomas P.
- Subjects
- *
FATIGUE (Physiology) , *MULTIPLE sclerosis , *ELECTRONIC paper , *STATISTICAL reliability , *COGNITIVE interviewing , *MEASURING instruments , *MULTIPLE sclerosis diagnosis , *MENTAL health , *COGNITION , *COMPARATIVE studies , *ECONOMIC aspects of diseases , *HEALTH status indicators , *RESEARCH methodology , *MEDICAL cooperation , *PSYCHOMETRICS , *QUESTIONNAIRES , *READABILITY (Literary style) , *RESEARCH , *QUALITATIVE research , *ACTIVITIES of daily living , *EVALUATION research , *PREDICTIVE tests , *CROSS-sectional method ,RESEARCH evaluation - Abstract
Objectives: A new patient-reported outcome (PRO) instrument to measure fatigue symptoms and impacts in relapsing multiple sclerosis (RMS) was developed in a qualitative stage, followed by psychometric validation and migration from paper to an electronic format.Methods: Adult patients with relapsing-remitting multiple sclerosis (RRMS) were interviewed to elicit fatigue-related symptoms and impacts. A draft questionnaire was debriefed in cognitive interviews with further RRMS patients, and revised. Content confirmation interviews were conducted with patients with progressive-relapsing multiple sclerosis (PRMS) and relapsing secondary-progressive multiple sclerosis (RSPMS). Psychometric analyses used data from adult patients with different RMS subtypes and matched non-RMS controls in a multicenter, observational study. After item reduction, the final instrument was migrated to a smartphone (eDiary) and usability was confirmed in interviews with additional adult RMS patients.Results: The qualitative stage included 37 RRMS, 5 PRMS, and 5 RSPMS patients. Saturation of concepts was reached during concept elicitation. Cognitive interviews confirmed that participants understood the instructions, items, and response options of the instrument-named FSIQ-RMS-as intended. Psychometric validation included 164 RMS and 74 control patients. Internal consistency and test-retest reliability were demonstrated. The symptoms domain discriminated along the RMS symptom-severity continuum and between patients and controls. Patients were able to attribute fatigue-related symptoms to RMS. Usability and conceptual equivalence of the eDiary were confirmed (n = 10 participants).Conclusions: With 7 symptom items and 13 impact items (in 3 impacts subdomains: physical, cognitive and emotional, and coping) after item reduction, the FSIQ-RMS is a comprehensive, valid, and reliable measure of fatigue-related symptoms and impacts in RMS patients. [ABSTRACT FROM AUTHOR]- Published
- 2019
- Full Text
- View/download PDF
6. Paper 08: Predicting Clinically Significant Outcomes in Patients Undergoing Hip Arthroscopy for the Treatment of Femoroacetabular Impingement Syndrome: Five-Year Results in 453 Patients.
- Author
-
Knapik, Derrick, Newhouse, Alexander, Alter, Thomas, Chahla, Jorge, Nho, Shane, and Clapp, Ian
- Subjects
HIP surgery ,FEMORACETABULAR impingement ,PREDICTIVE tests ,ARTHROSCOPY ,HEALTH outcome assessment ,CONFERENCES & conventions - Abstract
Objectives: To determine predictors of clinically significant outcome achievement at a minimum of 5-year follow-up in patients undergoing hip arthroscopy for the treatment of femoroacetabular impingement syndrome with routine capsular closure. Methods: Data were collected and analyzed from consecutive patients who underwent primary hip arthroscopy with routine capsular closure for the treatment of FAIS from a single fellowship-trained surgeon between January 2012 and December 2018. Baseline data, preoperative patient reported outcome measures (PROMs) and 5- year PROMs including Hip Outcome Score-Activities of Daily Living, HOS-Sports Subscale, international Hip Outcome Tool 12 questions, modified Harris Hip Score and visual analog scale pain were recorded. The minimal clinically important difference (MCID) was calculated using the distribution method while patient acceptable symptom state (PASS), and substantial clinical benefit (SCB) were determined from literature defined values. Bivariate correlations with any MCID achievement, any PASS achievement, and any SCB achievement as well as a principle components analysis for variable reduction were used to create three separate multivariate binary logistic regressions to identify significant predictors of achieving a clinically significant outcome. Results: 453 patients with an average age of 34.3 ± 12.5 and average BMI of 25.5 ± 4.9 and majority female (69.1%) were included in the final analysis. There was a significant improvement in all 5-year functional outcomes when compared to preoperative scores (p<0.001 for all). At a minimum of 5-year follow-up, 82.8% of patients achieved any MCID, 69.8% achieved any PASS, and 58.9% achieved any SCB. A total of 23 patients (5.1%) of the study population underwent revision hip arthroscopy or total hip arthroplasty within the follow-up period. Female sex (Odds Ratio (OR), 2.56 [95% confidence interval (CI), 1.47 to 4.45) was a positive predictor of achieving any MCID while higher Tönnis angle (OR, 0.92 [95% CI, 0.87 to 0.98]), Tönnis grade =1 (OR, 0.34 [95% CI, 0.14 to 0.83]) were negative predictors of achieving any MCID. Higher preoperative HOS-ADL (OR, 1.03 [95% CI, 1.01 to 1.05]) and female sex (OR, 2.01 [95% CI, 1.14 to 3.55]) were positive predictors of PASS. With regards to SCB, running (OR, 2.02 [95% CI, 1.31 to 3.14]) was a positive predictor of achievement while a history of back pain (OR, 0.49 [95% CI, 0.28 to 0.86]) and preoperative chronic pain for greater than 2 years (OR, 0.62 [95% CI, 0.36 to 0.98]), were negative predictors of achievement. Conclusions: At a minimum of 5-year follow-up, 82.8% of patients undergoing primary hip arthroscopy for the treatment of FAIS achieved any MCID, 69.8% achieved any PASS, 58.9% achieved any SCB. Female sex, higher preoperative PROs, and participation in running were positive predictors of achieving a clinically significant outcome while a higher Tönnis angle, Tönnis grade = 1, preoperative chronic pain, and back pain were negative predictors of achieving a clinically significant outcome. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
7. An AI-based multiphase framework for improving the mechanical ventilation availability in emergency departments during respiratory disease seasons: a case study.
- Author
-
Ortiz-Barrios, Miguel, Petrillo, Antonella, Arias-Fonseca, Sebastián, McClean, Sally, de Felice, Fabio, Nugent, Chris, and Uribe-López, Sheyla-Ariany
- Subjects
TREATMENT of respiratory diseases ,COMPUTER simulation ,RANDOM forest algorithms ,PREDICTIVE tests ,CROSS-sectional method ,RESEARCH funding ,RECEIVER operating characteristic curves ,ARTIFICIAL intelligence ,PROBABILITY theory ,HOSPITAL emergency services ,DECISION making ,ARTIFICIAL respiration ,EPIDEMICS ,QUALITY assurance ,CONFIDENCE intervals ,MECHANICAL ventilators ,SENSITIVITY & specificity (Statistics) - Abstract
Background: Shortages of mechanical ventilation have become a constant problem in Emergency Departments (EDs), thereby affecting the timely deployment of medical interventions that counteract the severe health complications experienced during respiratory disease seasons. It is then necessary to count on agile and robust methodological approaches predicting the expected demand loads to EDs while supporting the timely allocation of ventilators. In this paper, we propose an integration of Artificial Intelligence (AI) and Discrete-event Simulation (DES) to design effective interventions ensuring the high availability of ventilators for patients needing these devices. Methods: First, we applied Random Forest (RF) to estimate the mechanical ventilation probability of respiratory-affected patients entering the emergency wards. Second, we introduced the RF predictions into a DES model to diagnose the response of EDs in terms of mechanical ventilator availability. Lately, we pretested two different interventions suggested by decision-makers to address the scarcity of this resource. A case study in a European hospital group was used to validate the proposed methodology. Results: The number of patients in the training cohort was 734, while the test group comprised 315. The sensitivity of the AI model was 93.08% (95% confidence interval, [88.46 − 96.26%]), whilst the specificity was 85.45% [77.45 − 91.45%]. On the other hand, the positive and negative predictive values were 91.62% (86.75 − 95.13%) and 87.85% (80.12 − 93.36%). Also, the Receiver Operator Characteristic (ROC) curve plot was 95.00% (89.25 − 100%). Finally, the median waiting time for mechanical ventilation was decreased by 17.48% after implementing a new resource capacity strategy. Conclusions: Combining AI and DES helps healthcare decision-makers to elucidate interventions shortening the waiting times for mechanical ventilators in EDs during respiratory disease epidemics and pandemics. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
8. Unravelling the Roots of Emotional Development: Examining the Relationships Between Attachment, Resilience and Coping in Young Adolescents.
- Author
-
Godor, Brian P., van der Horst, Frank C. P., and Van der Hallen, Ruth
- Subjects
STRUCTURAL equation modeling ,PREDICTIVE tests ,ATTACHMENT behavior ,SURVEYS ,QUESTIONNAIRES ,EMOTIONS ,PSYCHOLOGICAL adaptation ,PATH analysis (Statistics) ,PSYCHOLOGICAL resilience ,CHILDREN - Abstract
One's attachment style forms early in life and can aid in dealing with future setbacks. Equally, Coping and resilience are two specific psychological mechanisms that form how one deals with problems and recovers from stressful situations. These three concepts are well-known interrelated concepts within psychology but to what extent they overlap is still unclear. The present study investigated attachment, resiliency and coping using structural equation modeling. Participants (N = 390), aged between 9 and 12 y old, completed an paper survey including Experiences in Close Relationship-Revised questionnaire (ECR-RC-12), Resiliency Scales for Children & Adolescents (RSCA), and the Brief-CPE (Coping Orientation to Problems Experienced). Path analysis revealed strong associations between attachment and resiliency as well as strong associations between resiliency and coping. Specifically, the predictive value of anxious attachment on resiliency was seen for all three resiliency sub-scales. However, the predictive value of avoidance attachment on resiliency was only revealed for two of the resiliency sub-scales. The two resiliency protective factors (sense of mastery and sense of relatedness) have a positive predictive value for three coping strategies. Equally, the resiliency risk factor (emotional reactivity) also positively predicted two coping strategies. The current findings demonstrate clear associations between these three concepts. Equally, the theoretical connections are discussed in light of these findings. Equally, stemming from this study, clinical implications are discussed that can inform practice in terms of approaching psychopathologies from different angles (resilience, coping, and attachment) as well as, the development of coping and resilience skills in order to support healthy development. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
9. Reviewing the SmartPLS 4 software: the latest features and enhancements.
- Author
-
Cheah, Jun-Hwa, Magno, Francesca, and Cassia, Fabio
- Subjects
STRUCTURAL equation modeling ,GRAPHICAL user interfaces ,PREDICTIVE tests ,LATENT variables ,MULTIVARIATE analysis - Abstract
Partial least squares structural equation modeling (PLS-SEM) is a highly popular multivariate data analysis method. The SmartPLS 3 software program helped many marketing researchers analyze the complex relationships between latent variables (i.e., mediation, moderation, etc.), which they measured by means of sets of observed variables. This program's intuitive graphical user interface and various features, such as new metrics (e.g., HTMT, model fit indexes), advanced techniques (multigroup analysis, PLS
predict ), and complementary techniques (e.g., confirmatory tetrad analysis, importance-performance map analysis), which impacted many business disciplines. SmartPLS 4 represents a significant leap forward in development with its completely revamped graphical user interface, faster processing speed for data estimation, and new model assessment features (i.e., cross-validated predictive ability test, endogeneity assessment, and a necessary condition analysis). This paper reviews SmartPLS 4 and discusses its various features, thereby providing researchers with concrete guidance that fits their analytical research goals. [ABSTRACT FROM AUTHOR]- Published
- 2024
- Full Text
- View/download PDF
10. Predictive model assessment and selection in composite-based modeling using PLS-SEM: extensions and guidelines for using CVPAT.
- Author
-
Sharma, Pratyush N., Liengaard, Benjamin D., Hair, Joseph F., Sarstedt, Marko, and Ringle, Christian M.
- Subjects
PREDICTION models ,EVIDENCE gaps ,PREDICTIVE tests ,STRUCTURAL equation modeling ,MARKETING models - Abstract
Purpose: Researchers often stress the predictive goals of their partial least squares structural equation modeling (PLS-SEM) analyses. However, the method has long lacked a statistical test to compare different models in terms of their predictive accuracy and to establish whether a proposed model offers a significantly better out-of-sample predictive accuracy than a naïve benchmark. This paper aims to address this methodological research gap in predictive model assessment and selection in composite-based modeling. Design/methodology/approach: Recent research has proposed the cross-validated predictive ability test (CVPAT) to compare theoretically established models. This paper proposes several extensions that broaden the scope of CVPAT and explains the key choices researchers must make when using them. A popular marketing model is used to illustrate the CVPAT extensions' use and to make recommendations for the interpretation and benchmarking of the results. Findings: This research asserts that prediction-oriented model assessments and comparisons are essential for theory development and validation. It recommends that researchers routinely consider the application of CVPAT and its extensions when analyzing their theoretical models. Research limitations/implications: The findings offer several avenues for future research to extend and strengthen prediction-oriented model assessment and comparison in PLS-SEM. Practical implications: Guidelines are provided for applying CVPAT extensions and reporting the results to help researchers substantiate their models' predictive capabilities. Originality/value: This research contributes to strengthening the predictive model validation practice in PLS-SEM, which is essential to derive managerial implications that are typically predictive in nature. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
11. Guest editorial: Current issues in composite-based and covariance-based structural equations modeling: what to do and when to do it.
- Author
-
Voss, Kevin
- Subjects
STRUCTURAL equation modeling ,PHILOSOPHY of science ,SCIENTIFIC method ,PREDICTIVE tests - Published
- 2023
- Full Text
- View/download PDF
12. Classification of Ear Imagery Database using Bayesian Optimization based on CNN-LSTM Architecture.
- Author
-
Mohammed, Kamel K., Hassanien, Aboul Ella, and Afify, Heba M.
- Subjects
DATABASES ,EAR examination ,MEDICAL information storage & retrieval systems ,PREDICTIVE tests ,EAR diseases ,DIAGNOSTIC imaging ,DIAGNOSIS ,CLINICAL medicine ,ARTIFICIAL neural networks ,SENSITIVITY & specificity (Statistics) ,EARWAX impaction ,OTITIS media ,ALGORITHMS - Abstract
The external and middle ear conditions are diagnosed using a digital otoscope. The clinical diagnosis of ear conditions is suffered from restricted accuracy due to the increased dependency on otolaryngologist expertise, patient complaint, blurring of the otoscopic images, and complexity of lesions definition. There is a high requirement for improved diagnosis algorithms based on otoscopic image processing. This paper presented an ear diagnosis approach based on a convolutional neural network (CNN) as feature extraction and long short-term memory (LSTM) as a classifier algorithm. However, the suggested LSTM model accuracy may be decreased by the omission of a hyperparameter tuning process. Therefore, Bayesian optimization is used for selecting the hyperparameters to improve the results of the LSTM network to obtain a good classification. This study is based on an ear imagery database that consists of four categories: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). This study used 880 otoscopic images divided into 792 training images and 88 testing images to evaluate the approach performance. In this paper, the evaluation metrics of ear condition classification are based on a percentage of accuracy, sensitivity, specificity, and positive predictive value (PPV). The findings yielded a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a PPV of 100% for the testing database. Finally, the proposed approach shows how to find the best hyperparameters concerning the Bayesian optimization for reliable diagnosis of ear conditions under the consideration of LSTM architecture. This approach demonstrates that CNN-LSTM has higher performance and lower training time than CNN, which has not been used in previous studies for classifying ear diseases. Consequently, the usefulness and reliability of the proposed approach will create an automatic tool for improving the classification and prediction of various ear pathologies. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
13. Integrated Diagnostics of Thyroid Nodules.
- Author
-
Giovanella, Luca, Campennì, Alfredo, Tuncel, Murat, and Petranović Ovčariček, Petra
- Subjects
THYROID gland radiography ,THYROTROPIN ,MOLECULAR diagnosis ,PREDICTIVE tests ,THYROID gland tumors ,INTEGRATIVE medicine ,UNNECESSARY surgery ,ARTIFICIAL intelligence ,DIAGNOSTIC imaging ,BIOINFORMATICS ,RADIONUCLIDE imaging ,CYTOLOGY ,RISK management in business ,NUCLEAR medicine ,THYROID gland ,NEEDLE biopsy ,IODINE - Abstract
Simple Summary: Thyroid nodules are commonly detected in daily clinical practice, and their diagnosis and therapy usually involve different specialists and various diagnostic and therapeutic methods. Thyroid nodule management requires the integration of laboratory, imaging, and pathology examinations to achieve a proper diagnosis. It enables the elimination of unnecessary therapeutic procedures in many individuals and the timely identification of patients who require specific therapies. Furthermore, bioinformatics may change the current management of clinical data, enabling more personalized diagnostic approaches for patients with thyroid nodules. The clinical impact of artificial intelligence needs to be determined in further large-sample studies, especially in indeterminate cytology findings, that require "diagnostic surgery" to provide a definitive diagnosis. Thyroid nodules are common findings, particularly in iodine-deficient regions. Our paper aims to revise different diagnostic tools available in clinical thyroidology and propose their rational integration. We will elaborate on the pros and cons of thyroid ultrasound (US) and its scoring systems, thyroid scintigraphy, fine-needle aspiration cytology (FNAC), molecular imaging, and artificial intelligence (AI). Ultrasonographic scoring systems can help differentiate between benign and malignant nodules. Depending on the constellation or number of suspicious ultrasound features, a FNAC is recommended. However, hyperfunctioning thyroid nodules are presumed to exclude malignancy with a very high negative predictive value (NPV). Particularly in regions where iodine supply is low, most hyperfunctioning thyroid nodules are seen in patients with normal thyroid-stimulating hormone (TSH) levels. Thyroid scintigraphy is essential for the detection of these nodules. Among non-toxic thyroid nodules, a careful application of US risk stratification systems is pivotal to exclude inappropriate FNAC and guide the procedure on suspicious ones. However, almost one-third of cytology examinations are rendered as indeterminate, requiring "diagnostic surgery" to provide a definitive diagnosis.
99m Tc-methoxy-isobutyl-isonitrile ([99m Tc]Tc-MIBI) and [18 F]fluoro-deoxy-glucose ([18 F]FDG) molecular imaging can spare those patients from unnecessary surgeries. The clinical value of AI in the evaluation of thyroid nodules needs to be determined. [ABSTRACT FROM AUTHOR]- Published
- 2024
- Full Text
- View/download PDF
14. Osteo-NeT: An Automated System for Predicting Knee Osteoarthritis from X-ray Images Using Transfer-Learning-Based Neural Networks Approach.
- Author
-
Alshamrani, Hassan A., Rashid, Mamoon, Alshamrani, Sultan S., and Alshehri, Ali H. D.
- Subjects
KNEE osteoarthritis ,X-rays ,PREDICTIVE tests ,RADIOGRAPHY ,MACHINE learning ,LEARNING strategies ,AUTOMATION ,TRANSFER of training ,RESEARCH funding ,ARTIFICIAL neural networks - Abstract
Knee osteoarthritis is a challenging problem affecting many adults around the world. There are currently no medications that cure knee osteoarthritis. The only way to control the progression of knee osteoarthritis is early detection. Currently, X-ray imaging is a central technique used for the prediction of osteoarthritis. However, the manual X-ray technique is prone to errors due to the lack of expertise of radiologists. Recent studies have described the use of automated systems based on machine learning for the effective prediction of osteoarthritis from X-ray images. However, most of these techniques still need to achieve higher predictive accuracy to detect osteoarthritis at an early stage. This paper suggests a method with higher predictive accuracy that can be employed in the real world for the early detection of knee osteoarthritis. In this paper, we suggest the use of transfer learning models based on sequential convolutional neural networks (CNNs), Visual Geometry Group 16 (VGG-16), and Residual Neural Network 50 (ResNet-50) for the early detection of osteoarthritis from knee X-ray images. In our analysis, we found that all the suggested models achieved a higher level of predictive accuracy, greater than 90%, in detecting osteoarthritis. However, the best-performing model was the pretrained VGG-16 model, which achieved a training accuracy of 99% and a testing accuracy of 92%. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
15. Hyperthermia Treatment Monitoring via Deep Learning Enhanced Microwave Imaging: A Numerical Assessment.
- Author
-
Yago Ruiz, Álvaro, Cavagnaro, Marta, and Crocco, Lorenzo
- Subjects
HEAD & neck cancer treatment ,MEDICAL thermometry ,DEEP learning ,THERMOTHERAPY ,PREDICTIVE tests ,RESEARCH evaluation ,MICROWAVES ,PATIENT monitoring ,RESEARCH funding ,MEDICAL thermography - Abstract
Simple Summary: Non-invasive temperature monitoring during hyperthermia cancer treatment is of paramount importance. It allows physicians to verify the therapeutic temperature is reached in the treated area. Currently, only superficial or invasive thermometry is performed on a clinical level. Magnetic resonance thermometry has been proposed as a a non-invasive alternative but its applicability is limited. Conversely, microwave imaging based thermometry is a potential low cost candidate for non-invasive temperature monitoring. This works presents a computational study in which the use of deep learning is proposed to face the challenges related to the use of microwave imaging in hyperthermia monitoring. The paper deals with the problem of monitoring temperature during hyperthermia treatments in the whole domain of interest. In particular, a physics-assisted deep learning computational framework is proposed to provide an objective assessment of the temperature in the target tissue to be treated and in the healthy one to be preserved, based on the measurements performed by a microwave imaging device. The proposed concept is assessed in-silico for the case of neck tumors achieving an accuracy above 90%. The paper results show the potential of the proposed approach and support further studies aimed at its experimental validation. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
16. Old ideas, new directions: re-examining the predictive utility of the hemodynamic profile of the stress response in healthy populations.
- Author
-
Howard, Siobhán
- Subjects
HYPERTENSION ,PHYSIOLOGICAL stress ,DISEASE progression ,PREDICTIVE tests ,CARDIOVASCULAR system physiology ,PSYCHOSOMATIC disorders ,RISK assessment ,POPULATION health ,HEMODYNAMICS ,ACADEMIC dissertations ,PSYCHOLOGICAL stress - Abstract
The 'reactivity hypothesis' has a long and fruitful history in health psychology and behavioural medicine, with elements of its thesis taken as core and others lost in the plethora of research on its utility as a theory of psychosomatic disease. One such thesis is that the underlying hemodynamic profile of the stress response may be particularly revealing when detailing the impact of psychological stress on the development of cardiovascular disease. This paper re-examines old ideas surrounding the hemodynamic profile of the stress response, asking why its health-predictive properties were never fully explored. Further, this paper reviews the evidence that a vascular profile of stress responding may be especially predictive of disease development, particularly in the case of hypertension. In addition, measurement of hemodynamic profile, as well as its known psychosocial moderators, is reviewed including how examination of patterns of cardiovascular stress response adaptation may extend the field. This paper highlights that the extension of the reactivity hypothesis to include both hemodynamic profile and patterns of cardiovascular stress response adaptation may hold much explanatory power in detailing the impact of how stress responding and stress tolerance promotes disease development. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
17. Deep Learning Classification Method to Detect and Diagnose the Cancer Regions in Oral MRI Images.
- Author
-
Kirubabai, M. Praveena and Arumugam, G.
- Subjects
DIGITAL image processing ,DEEP learning ,MOUTH tumors ,RESEARCH evaluation ,PREDICTIVE tests ,MAGNETIC resonance imaging ,TUMOR classification ,ALGORITHMS - Abstract
The paper proposes deep learning algorithm used to classify the oral images into either normal or abnormal images. The cancer regions are segmented using morphological operations. The segmented cancer regions are further diagnosed into 'Mild' or 'Severe' using deep learning algorithm. The main advantage of the deep learning algorithm is that it requires minimum number of oral images for both classification and diagnosis stages of the proposed work. In this paper, the total number of cancers affected oral images used is about 160 and the proposed oral cancer detection system using CNN classification approach classifies 159 cancer affected oral images correctly and achieves 99.3% of detection rate. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
18. Concurrent and Predictive Validity of a Cycloid Loops Copy Task to Assess Handwriting Disorders in Children.
- Author
-
Lopez, Clémence and Vaivre-Douret, Laurence
- Subjects
PREDICTIVE tests ,RESEARCH methodology evaluation ,HANDWRITING ,DRAWING ,RESEARCH funding ,SPATIAL behavior ,LOGISTIC regression analysis ,RECEIVER operating characteristic curves ,SENSITIVITY & specificity (Statistics) ,VIDEO recording ,KINEMATICS - Abstract
Handwriting disorders (HDs) are mainly assessed using script or cursive handwriting tasks. The most common is the scale for children's handwriting, with a French adaptation (BHK). The present study aims to assess the concurrent validity of a pre-scriptural task (copying a line of cycloid loops) with the BHK for the diagnosis of HDs. Thirty-five primary school children (7 females, 28 males) with HD aged 6–11 years were recruited and compared to 331 typically developing children (TDC). Spatial/temporal/kinematic measures were collected using a digital pen on a paper. Posture and inter-segmental writing arm coordination were video recorded. A logistic regression statistical method, including a receiver-operating characteristic curve, was used to assess the ability of the task to predict HD. Gestural patterns were significantly less mature in HDs than in TDC (p < 0.05), and associated with poorer quality, less fluid, and slower drawing (p < 0.001). Moreover, good correlations between temporal and kinematic measures and the BHK scale were found. Number of strokes, total drawing time, in-air pauses times, and number of velocity peaks showed very good sensitivity (88%) and specificity (74%) to diagnose HDs. Consequently, the cycloid loops task is an easy, robust, and predictive tool for clinicians to identify HDs before the alphabet is mastered. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
19. Machine Learning Techniques Outperform Conventional Statistical Methods in the Prediction of High Risk QTc Prolongation Related to a Drug-Drug Interaction.
- Author
-
Van Laere, Sven, Muylle, Katoo M., Dupont, Alain G., and Cornu, Pieter
- Subjects
C-reactive protein ,DECISION trees ,PREDICTIVE tests ,RESEARCH evaluation ,KIDNEY function tests ,AGE distribution ,LONG QT syndrome ,MACHINE learning ,POTASSIUM ,ATRIAL fibrillation ,RETROSPECTIVE studies ,RISK assessment ,DRUG interactions ,HEART beat ,ELECTROCARDIOGRAPHY ,DESCRIPTIVE statistics ,RESEARCH funding ,PREDICTION models ,STATISTICAL models ,SENSITIVITY & specificity (Statistics) ,CALCIUM ,LOGISTIC regression analysis ,DATA analysis software ,LONGITUDINAL method ,DISEASE risk factors ,EVALUATION - Abstract
In clinical practice, many drug therapies are associated with prolongation of the QT interval. In literature, estimation of the risk of prescribing drug-induced QT prolongation is mainly executed by means of logistic regression; only one paper reported the use of machine learning techniques. In this paper, we compare the performance of both techniques on the same dataset. High risk for QT prolongation was defined as having a corrected QT interval (QTc) ≥ 450 ms or ≥ 470 ms for respectively male and female patients. Both conventional statistical methods (CSM) and machine learning techniques (MLT) were used. All algorithms were validated internally and with a hold-out dataset of respectively 512 and 102 drug-drug interactions with possible drug-induced QTc prolongation. MLT outperformed the best CSM in both internal and hold-out validation. Random forest and Adaboost classification performed best in the hold-out set with an equal harmonic mean of sensitivity and specificity (HMSS) of 81.2% and an equal accuracy of 82.4% in a hold-out dataset. Sensitivity and specificity were both high (respectively 75.6% and 87.7%). The most important features were baseline QTc value, C-reactive protein level, heart rate at baseline, age, calcium level, renal function, serum potassium level and the atrial fibrillation status. All CSM performed similarly with HMSS varying between 60.3% and 66.3%. The overall performance of logistic regression was 62.0%. MLT (bagging and boosting) outperform CSM in predicting drug-induced QTc prolongation. Additionally, 19.2% was gained in terms of performance by random forest and Adaboost classification compared to logistic regression (the most used technique in literature in estimating the risk for QTc prolongation). Future research should focus on testing the classification on fully external data, further exploring potential of other (new) machine and deep learning models and on generating data pipelines to automatically feed the data to the classifier used. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
20. Attack based on data: a novel perspective to attack sensitive points directly.
- Author
-
Ge, Yuyao, Yang, Zhongguo, Chen, Lizhe, Wang, Yiming, and Li, Chengyang
- Subjects
PREDICTION models ,RATE setting ,POINT set theory ,STATISTICS ,LOCATION-based services ,PREDICTIVE tests ,CLASSIFICATION - Abstract
Adversarial attack for time-series classification model is widely explored and many attack methods are proposed. But there is not a method of attack based on the data itself. In this paper, we innovatively proposed a black-box sparse attack method based on data location. Our method directly attack the sensitive points in the time-series data according to statistical features extract from the dataset. At first, we have validated the transferability of sensitive points among DNNs with different structures. Secondly, we use the statistical features extract from the dataset and the sensitive rate of each point as the training set to train the predictive model. Then, predicting the sensitive rate of test set by predictive model. Finally, perturbing according to the sensitive rate. The attack is limited by constraining the L0 norm to achieve one-point attack. We conduct experiments on several datasets to validate the effectiveness of this method. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
21. Sector-level equity returns predictability with machine learning and market contagion measure.
- Author
-
Peng, Weijia and Yao, Chun
- Subjects
MACHINE learning ,RANDOM walks ,RANDOM forest algorithms ,PREDICTIVE tests - Abstract
In this paper, we develop new latent risk measures that are designed as a prior synthesis of key forecasting information associated with financial market contagion. These measures are based on the decomposition (using high-frequency financial data) of the quadratic covariation between two assets into continuous and jump components. We also examine the usefulness of a large variety of machine learning methods for forecasting equity returns at market and sector levels. In addition to constructing predictions using standard machine learning methods, we also investigate the predictive performance of a group of hybrid machine learning methods that combine least absolute shrinkage operator and neural network methods. We demonstrate that the novel latent measures significantly reduce the MSFE when added into candidate machine learning models and are dominant predictive signals based on variable importance analysis, suggesting that the latent measures constructed using high-frequency financial data are useful for predicting returns. Overall, at the monthly frequency, we find that machine learning methods significantly improve forecasting performance relative to the random walk and linear benchmark alternatives, when comparing mean square forecast error (MSFE), and when implementing Diebold-Mariano (DM) predictive accuracy test. The "best" method is the random forest method, which "wins" in almost all permutations, across all of the "target" variables that we predict. It is also worth noting that our hybrid machine learning methods often outperform individual methods. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
22. Connectivity modelling in conservation science: a comparative evaluation.
- Author
-
Unnithan Kumar, Siddharth and Cushman, Samuel A.
- Subjects
PREDICTIVE tests ,SPATIAL ecology ,APPLIED ecology ,SCIENTIFIC models ,SIMULATION methods & models - Abstract
Landscape connectivity, the extent to which a landscape facilitates the flow of ecological processes such as organism movement, has grown to become a central focus of applied ecology and conservation science. Several computational algorithms have been developed to understand and map connectivity, and many studies have validated their predictions using empirical data. Yet at present, there is no published comparative analysis which uses a comprehensive simulation framework to measure the accuracy and performance of the dominant methods in connectivity modelling. Given the widespread usage of such models in spatial ecology and conservation science, a thorough evaluation of their predictive abilities using simulation techniques is essential for guiding their appropriate and effective application across different contexts. In this paper, we address this by using the individual-based movement model Pathwalker to simulate different connectivity scenarios generated from a wide range of possible movement behaviours and spatial complexities. With this simulated data, we test the predictive abilities of three major connectivity models: factorial least-cost paths, resistant kernels, and Circuitscape. Our study shows the latter two of these three models to consistently perform most accurately in nearly all cases, with their abilities varying substantially in different contexts. For the majority of conservation applications, we infer resistant kernels to be the most appropriate model, except for when the movement is strongly directed towards a known location. We conclude this paper with a review and interdisciplinary discussion of the current limitations and possible future developments of connectivity modelling. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
23. Detecting autism from picture book narratives using deep neural utterance embeddings.
- Author
-
Wawer, Aleksander and Chojnicka, Izabela
- Subjects
DIAGNOSIS of autism ,DEEP learning ,PREDICTIVE tests ,COMMUNICATIVE competence ,SPEECH evaluation ,TASK performance ,DATABASE management ,QUESTIONNAIRES ,BOOKS ,ARTIFICIAL neural networks ,SENSITIVITY & specificity (Statistics) ,ALGORITHMS - Abstract
Background: Deficits in the ability to use language in social contexts, including storytelling skills, are observed across the autism spectrum. Development in machine‐learning approaches may contribute to clinical psychology and psychiatry, given its potential to support decisions concerning the diagnosis and treatment of psychiatric conditions and disorders. Aims: To evaluate the usefulness of deep neural networks for detecting autism spectrum disorder (ASD) from textual utterances, specifically from narrations produced by individuals with ASD. Methods & Procedures: We examined two text encoders: Embeddings from Language Models (ELMo) and Universal Sentence Encoder (USE), and three classification algorithms: XGBoost, support vector machines, and dense neural network layer. We aimed to classify 25 participants with ASD and 25 participants with typical development (TD) based on their narrations produced during the Autism Diagnostic Observation Schedule, Second Edition (ADOS‐2) picture book task. The results of computational approaches were compared with the results of standardized testing and classifications made by two psychiatrists (raters). The raters were asked to read utterances produced by a participant (without an examiner's statements and additional information) and assign a participant to one of the two groups: ASD or with typical development (TD). Outcomes & Results: The computer‐based models had higher sensitivity, specificity, positive predictive values and negative predictive values than the raters, and lower than the two standardized instruments: ADOS‐2 and Social Communication Questionnaire (SCQ). Conclusions & Implications: Our findings lay the groundwork for future studies involving deep neural network‐based text representation models as tools for augmenting the ASD diagnosis or screening. Both ELMo and USE text encoders provided promising specificities, sensitivities, positive predictive values and negative predictive values. Our results indicate the usefulness of page‐level embeddings for utterance representation in ADOS‐2 picture book task. WHAT THIS PAPER ADDS: What is already known on this subject: Deficits in the use of language in social contexts, and narrative ability in particular, are observed across the autism spectrum. Most research on narrative skills has applied hand‐coding methods. Hitherto, machine‐learning methods were used mostly for image recognition problems and data from screening questionnaires for ASD classification. Detection of mental and developmental disorders from textual input is an emerging field for machine and deep‐learning methods. What this paper adds to existing knowledge: This study explored the ability of several types of deep neural network‐based text representation models to detect ASD. Both ELMo and USE provided the most promising values of specificity, sensitivity, positive predictive values and negative predictive values. What are the potential or actual clinical implications of this work?: Competitive accuracy, repeatability, speed and ease of operation are all advantages of computerized methods. They allow for objective and quantitative assessment of narrative ability and complex language skills. Deep neural network‐based text representation models could in the future support clinicians and augment the decision‐making process related to ASD diagnosis, screening and intervention planning. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
24. Development and validation of a composite score to predict severe forms of ischemic colitis.
- Author
-
Fillias, Quentin, Millet, Ingrid, Guiu, Boris, Orliac, Celine, Curros Doyon, Fernanda, Gamon, Lucie, Molinari, Nicolas, and Taourel, Patrice
- Subjects
PREDICTIVE tests ,RISK assessment ,RETROSPECTIVE studies ,ISCHEMIC colitis ,PROGNOSIS - Abstract
Objective: To develop a simple scoring system in order to predict the risk of severe (death and/or surgery) ischemic colitis METHODS: In this retrospective study, 205 patients diagnosed with ischemic colitis in a tertiary hospital were consecutively included over a 6-year period. The study sample was sequentially divided into a training cohort (n = 103) and a validation cohort (n = 102). In the training cohort, multivariable analysis was used to identify clinical, biological, and CT variables associated with poor outcome and to build a risk scoring system. The discriminative ability of the score (sensitivity, specificity, positive predictive value, negative predictive value) was estimated in the two cohorts to externally validate the score, and a receiver operating characteristic curve was established to estimate the area under the curve of the score. Bootstrapping was used to validate the score internally.Results: In the training cohort, four independent variables were associated with unfavorable outcome: hemodynamic instability (2 pts), involvement of the small bowel (1 pt), paper-thin wall pattern (3 pts), no stratified enhancement pattern (1 pt). The score was used to categorize patients into low risk (score: 0, 1), high risk (score: 2-3), and very high risk (score: 4-7) groups with sensitivity and specificity of 97% and 67%, respectively, and a good discriminating capability, with a C-statistic of 0.94. Internal and external validation showed good discrimination capability (C-statistics of 0.9 and 0.84, respectively).Conclusion: A simple risk score can stratify patients into three distinct prognosis groups, which can optimize patient management.Clinical Trial Number: NCT04662268 KEY POINTS: • Simple scoring system predicting the risk of severe ischemic colitis • First study to include CT findings to the clinical and biological data used to determine a severity score. [ABSTRACT FROM AUTHOR]- Published
- 2022
- Full Text
- View/download PDF
25. Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning.
- Author
-
Liu, Yiman, Huang, Qiming, Han, Xiaoxiang, Liang, Tongtong, Zhang, Zhifang, Lu, Xiuli, Dong, Bin, Yuan, Jiajun, Wang, Yan, Hu, Menghan, Wang, Jinfeng, Stefanidis, Angelos, Su, Jionglong, Chen, Jiangang, Li, Qingli, and Zhang, Yuqi
- Subjects
PREDICTIVE tests ,RESEARCH funding ,BLIND experiment ,ATRIAL septal defects ,PEDIATRICS ,DEEP learning ,VIDEO recording ,ECHOCARDIOGRAPHY ,SENSITIVITY & specificity (Statistics) - Abstract
Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. We chose four standard views in pediatric cardiac ultrasound to identify atrial septal defects; the four standard views were as follows: subcostal sagittal view of the atrium septum (subSAS), apical four-chamber view (A4C), the low parasternal four-chamber view (LPS4C), and parasternal short-axis view of large artery (PSAX). We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). In our model, we present a block random selection, maximal agreement decision, and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. We validate our model using our private dataset by five cross-validation. For ASD detection, we achieve 89.33 ± 3.13 AUC, 84.95 ± 3.88 accuracy, 85.70 ± 4.91 sensitivity, 81.51 ± 8.15 specificity, and 81.99 ± 5.30 F1 score. The proposed model is a multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
26. Modelling the Effect of Grassland Fuel Bed Structure on the Headfire Rate of Spread.
- Author
-
Brou, Akahoua David V. and Adou, Kablan Jérôme
- Subjects
GRASSLAND fires ,GRASSLANDS ,WILDFIRES ,PREDICTIVE tests ,PREDICTION models - Abstract
The dry weight of biomass to be consumed by fire in the wildland – urban interface (WUI) plays an important role in the spread of fire inside the WUI. In this paper, we present a model of grassland fire spread based on fuel load. The herbaceous stratum is represented by a heterogeneous fuel layer, with characteristics close to the real one. Fire propagation is simulated by using a two-phase model. Thirteen fire experiments in eastern Australia were used to test the predictive capacity of the model. The rates of spread are on the whole relatively well predicted. Using the fuel layer model to simulate fire spread, we tested how fuel load affects fire behavior. The results show that the fire spread rate does not systematically decrease with the increasing of fuel load. However, there may be a critical fuel load for rapid rate of spread, below or above which the rate of spread decreases. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
27. Detection of Glaucoma from Fundus Images Using Novel Evolutionary-Based Deep Neural Network.
- Author
-
Madhumalini, M. and Devi, T. Meera
- Subjects
GLAUCOMA diagnosis ,EXPERIMENTAL design ,COMPUTERS in medicine ,RETINA ,PREDICTIVE tests ,DIAGNOSTIC imaging ,EYE ,OPTIC nerve ,OPTICAL coherence tomography ,ARTIFICIAL neural networks ,SENSITIVITY & specificity (Statistics) ,STATISTICAL models ,EYE examination - Abstract
Glaucoma is an asymptotic condition that damages the optic nerves of a human eye. Glaucoma is frequently caused due to abnormally high pressure in an eye that leads to permanent blindness. Detecting glaucoma at an initial phase has the possibility of curing this disease, but diagnosing accurately is considered as a challenging task. Therefore, this paper proposes a novel method known as a glaucoma detection system that performs the diagnosis of glaucoma by exploiting the prescribed characteristics. The significant intention of this paper involves diagnosing the glaucoma disease present at the top optical nerve of a human eye. The proposed glaucoma detection has used four different phases namely data preprocessing or enhancement phase, segmentation phase, feature extraction phase, and classification phase. Here, a novel classifier named fractional gravitational search-based hybrid deep neural network (FGSA-HDNN) is developed for the effective classification of glaucoma-infected images from the normal image. Finally, the experimental analysis for the proposed approach and various other techniques are performed, and the accuracy rate while diagnosing glaucoma achieved is 98.75%. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
28. Towards an Accurate MRI Acute Ischemic Stroke Lesion Segmentation Based on Bioheat Equation and U-Net Model.
- Author
-
Bousselham, Abdelmajid, Bouattane, Omar, Youssfi, Mohamed, and Raihani, Abdelhadi
- Subjects
BRAIN physiology ,STROKE diagnosis ,DIGITAL image processing ,GRAPHIC arts ,PREDICTIVE tests ,BODY temperature ,MAGNETIC resonance imaging ,CEREBRAL ischemia - Abstract
Acute ischemic stroke represents a cerebrovascular disease, for which it is practical, albeit challenging to segment and differentiate infarct core from salvageable penumbra brain tissue. Ischemic stroke causes the variation of cerebral blood flow and heat generation due to metabolism. Therefore, the temperature is modified in the ischemic stroke region. In this paper, we incorporate acute ischemic stroke temperature profile to reinforce segmentation accuracy in MRI. Pennes bioheat equation was used to generate brain thermal images that may provide rich information regarding the temperature change in acute ischemic stroke lesions. The thermal images were generated by calculating the temperature of the brain with acute ischemic stroke. Then, U-Net was used in this paper for the segmentation of acute ischemic stroke. A dataset of 3192 images was created to train U-Net using k -fold crossvalidation. The training time was about 10 hours and 35 minutes in NVIDIA GPU. Next, the obtained trained model was compared with recent methods to analyze the effect of the ischemic stroke temperature profile in segmentation. The obtained results show that significant parts of acute ischemic stroke and background areas are segmented only in thermal images, which proves the importance of using thermal information to improve the segmentation outcomes in MRI diagnosis. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
29. Planning CT Identifies Patients at Risk of High Prostate Intrafraction Motion.
- Author
-
Ballhausen, Hendrik, Li, Minglun, Lombardo, Elia, Landry, Guillaume, and Belka, Claus
- Subjects
PREDICTIVE tests ,PROSTATE ,PUBIC symphysis ,T-test (Statistics) ,BODY movement ,COMPUTED tomography ,RECEIVER operating characteristic curves ,SENSITIVITY & specificity (Statistics) - Abstract
Simple Summary: Motion of the prostate may adversely affect the outcome of radiotherapy. Online tracking of the prostate during irradiation is technologically feasible but only available at select institutions. It would be beneficial to be able to identify patients at risk of particularly high prostate intrafraction motion with simpler technology. In this paper, we present a larger inner diameter of the lesser pelvis as an anatomical predictor for high prostate intrafraction motion. It can be measured with a single planning CT, which should always be available. Risk patients identified in this way could then be selected for more rigorous online motion management or benefit from increased safety margins. Prostate motion (standard deviation, range of motion, and diffusion coefficient) was calculated from 4D ultrasound data of 1791 fractions of radiation therapy in N = 100 patients. The inner diameter of the lesser pelvis was obtained from transversal slices through the pubic symphysis in planning CTs. On the lateral and craniocaudal axes, motility increases significantly (t-test, p < 0.005) with the inner diameter of the lesser pelvis. A diameter of >106 mm (ca. 6th decile) is a good predictor for high prostate intrafraction motion (ca. 9th decile). The corresponding area under the receiver operator curve (AUROC) is 80% in the lateral direction, 68% to 80% in the craniocaudal direction, and 62% to 70% in the vertical direction. On the lateral x-axis, the proposed test is 100% sensitive and has a 100% negative predictive value for all three characteristics (standard deviation, range of motion, and diffusion coefficient). On the craniocaudal z-axis, the proposed test is 79% to 100% sensitive and reaches 95% to 100% negative predictive value. On the vertical axis, the proposed test still delivers 98% negative predictive value but is not particularly sensitive. Overall, the proposed predictor is able to help identify patients at risk of high prostate motion based on a single planning CT. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
30. Antecedents and mediators of experiential retailing consumer behavior.
- Author
-
Meng, Hu, Sun, Yangyang, Liu, Xinxin, Li, Yujia, and Yang, Yingjie
- Subjects
CONSUMER behavior ,RELATIONSHIP quality ,PREDICTIVE tests ,CONSUMERS ,BRAND identification ,RELATIONSHIP marketing - Abstract
Purpose: An experiential retailing strategy is considered cardiotonic for consumers and brands. When such a stimulus is used, what cognition and behaviors are generated is an issue worthy of study. Therefore, the purpose of this study is to explore the factors and mechanisms that affect consumer response and relationship quality through empirical research. Design/methodology/approach: Based on theoretical deduction, this paper proposes a conceptual model that includes four antecedents: experiential scene atmosphere (ESA), highlight design, interaction approach and value fit. These affect consumer–brand relationship quality (CRQ) through consumer identification (CI), brand identity (BI) and experiential immersion degree. In two rounds of predictive tests, 624 and 481 valid data were collected, respectively, and the feasibility of the scale was verified scrupulously. Furthermore, 427 participants reported the participants' tendencies in a formal empirical study. Findings: The results show that the direct effects of antecedents, mediators and dependent variables are significant. Although the mediating effect of BI in experiential highlighting design on CRQ is not supported, other consumer response variables have a full or partial mediating effect. Originality/value: This study not only functions as an innovation of research perspective enriching the theoretical framework of the influence mechanism of experiential retailing, but also strengthens the discussion on the role of value fit, especially emotional value fit, in experiential retailing. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
31. The Significance of the Biopsychopolitical Model of Mental Health and Illnesses: Exploring Trends, Predictors and Statistical Challenges.
- Author
-
sebahutu, Evariste erwin
- Subjects
HEALTH policy ,BIOPSYCHOSOCIAL model ,PREDICTIVE tests ,CONFIDENCE intervals ,SOCIAL determinants of health ,EQUALITY ,PRACTICAL politics ,POPULATION geography ,DESCRIPTIVE statistics ,QUESTIONNAIRES ,MENTAL illness - Abstract
The current concerns regarding the ever-increasing global burden of non-communicable diseases where mental disorders and related somatic diseases make a significant contribution triggered my interest in the review of social determinants of mental health. Sufficient evidence led to the link of political systems to mental ill-health of citizens and taking into account the drawbacks of the biopsychosocial model based interventions led me to the formulation of the biopsychopolitical model that may guide the curative and preventive interventions for mental and related somatic diseases that I collectively call Social Distress Coping Disorders (SDCDs). The present paper aimed to find the predictor that may guide epidemiological studies. While ironically the Human Development Index (HDI) and Social Development Index (SDI) positively correlate with the global prevalence of disorders like depression and anxiety; an attempt was made to find a predictor that may negatively correlate with the prevalence of SDCDs on a global scale with no success due to reasons elucidated. On a local scale, the income inequality measures weakly negatively correlated with hypertension at 95% CI (R= -0.307, β = -0.449, p= 0.030) while no correlation was found for depression (R= -0.106, β = -0.014, p= 0.47) in 50 African countries with available data, and possible reasons for this were mentioned. The link between political systems and social determinants of mental health is certain, while waiting for a suitable model and predictor due to biased data as shown, the validity of the biopsychopolitical model is assured [ABSTRACT FROM AUTHOR]
- Published
- 2023
32. "Impaired Resilience (00210)" in patients under fertility treatment: Clinical validation study.
- Author
-
Romeiro, Joana, Caldeira, Sílvia, and Venicios Lopes, Marcos
- Subjects
INFERTILITY treatment ,STATISTICS ,NOSOLOGY ,PREDICTIVE tests ,JUDGMENT (Psychology) ,SCIENTIFIC observation ,RESEARCH evaluation ,CONFIDENCE intervals ,RESEARCH methodology ,CROSS-sectional method ,SELF-perception ,MEDICAL care ,WOMEN ,HEALTH status indicators ,INFERTILITY ,SOCIAL isolation ,NURSING practice ,FERTILITY ,QUESTIONNAIRES ,MENTAL depression ,FACTOR analysis ,DESCRIPTIVE statistics ,RESEARCH funding ,SENSITIVITY & specificity (Statistics) ,DATA analysis ,PSYCHOLOGICAL adaptation ,SHAME ,STATISTICAL sampling ,DATA analysis software ,PSYCHOLOGICAL resilience ,NURSING diagnosis ,PSYCHOLOGICAL distress ,MEDICAL logic - Abstract
Copyright of International Journal of Nursing Knowledge is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
33. Deep Learning- and Expert Knowledge-Based Feature Extraction and Performance Evaluation in Breast Histopathology Images.
- Author
-
Kode, Hepseeba and Barkana, Buket D.
- Subjects
BREAST tumor diagnosis ,DEEP learning ,DECISION trees ,SUPPORT vector machines ,PREDICTIVE tests ,PROFESSIONS ,RANDOM forest algorithms ,HISTOLOGICAL techniques ,COMPUTER-aided diagnosis ,ARTIFICIAL neural networks ,STATISTICAL models - Abstract
Simple Summary: Breast cancer is one of the leading causes of cancer death among women. Developing machine learning-based diagnosis models receives great attention from researchers and scientists using histopathology images. Deep learning (DL) algorithms automatically extract features from raw data through convolutional operations. The generalization of the DL models' results relies on large datasets, although they eliminate the expert knowledge in the feature extraction stage. This work aimed to compare the performance of the features extracted via deep learning and a knowledge-based approach in breast cancer detection from histopathology images. Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
34. What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification.
- Author
-
Schröder, Maresa, Zamanian, Alireza, and Ahmidi, Narges
- Subjects
IMAGE processing ,TIME series analysis ,DEEP learning ,UNIVARIATE analysis ,PREDICTIVE tests - Abstract
Saliency methods are designed to provide explainability for deep image processing models by assigning feature-wise importance scores and thus detecting informative regions in the input images. Recently, these methods have been widely adapted to the time series domain, aiming to identify important temporal regions in a time series. This paper extends our former work on identifying the systematic failure of such methods in the time series domain to produce relevant results when informative patterns are based on underlying latent information rather than temporal regions. First, we both visually and quantitatively assess the quality of explanations provided by multiple state-of-the-art saliency methods, including Integrated Gradients, Deep-Lift, Kernel SHAP, and Lime using univariate simulated time series data with temporal or latent patterns. In addition, to emphasize the severity of the latent feature saliency detection problem, we also run experiments on a real-world predictive maintenance dataset with known latent patterns. We identify Integrated Gradients, Deep-Lift, and the input-cell attention mechanism as potential candidates for refinement to yield latent saliency scores. Finally, we provide recommendations on using saliency methods for time series classification and suggest a guideline for developing latent saliency methods for time series. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
35. Predicting Chronic Homelessness: The Importance of Comparing Algorithms using Client Histories.
- Author
-
Messier, Geoffrey, John, Caleb, and Malik, Ayush
- Subjects
PREDICTIVE tests ,MACHINE learning ,DECISION making ,DESCRIPTIVE statistics ,HOMELESSNESS ,HOUSING ,INFORMATION storage & retrieval systems ,LOGISTIC regression analysis ,ARTIFICIAL neural networks ,PREDICTION models ,ALGORITHMS ,SECONDARY analysis - Abstract
This paper investigates how to best compare algorithms for predicting chronic homelessness for the purpose of identifying good candidates for housing programs. Predictive methods can rapidly refer potentially chronic shelter users to housing but also sometimes incorrectly identify individuals who will not become chronic (false positives). We use shelter access histories to demonstrate that these false positives are often still good candidates for housing. Using this approach, we compare a simple threshold method for predicting chronic homelessness to the more complex logistic regression and neural network algorithms. While traditional binary classification performance metrics show that the machine learning algorithms perform better than the threshold technique, an examination of the shelter access histories of the cohorts identified by the three algorithms show that they select groups with very similar characteristics. This has important implications for resource constrained not-for-profit organizations since the threshold technique can be implemented using much simpler information technology infrastructure than the machine learning algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
36. Predictors of COVID‐19 preventive behaviours in a sample of the Turkish population.
- Author
-
Savci, Cemile and Cil Akinci, Ayse
- Subjects
RESEARCH ,PILOT projects ,COVID-19 ,PREDICTIVE tests ,ANALYSIS of variance ,RESEARCH methodology ,MULTIPLE regression analysis ,HEALTH literacy ,SOCIOECONOMIC factors ,PEARSON correlation (Statistics) ,HEALTH behavior ,DESCRIPTIVE statistics ,QUESTIONNAIRES ,STATISTICAL correlation ,DATA analysis software ,EDUCATIONAL attainment ,HEALTH promotion - Abstract
Aim: This research aimed to determine predictors of COVID‐19 preventive behaviours in a sample of the Turkish population. Methods: The study was conducted with 575 individuals. COVID‐19 preventive behaviours were evaluated with a 19‐item scale scored from 19 to 95. Knowledge on COVID‐19 was evaluated with a 22‐item scale scored from 0 to 22. General health literacy was evaluated with the Turkey Health Literacy Scale (THLS), which was scored from 0 to 50. Results: The average COVID‐19 preventive behaviours score was moderately high in this sample of the Turkish population. Being female, having a higher level of education, better economic status, being a non‐smoker, having a higher level of COVID‐19 knowledge and better general health literacy score were significant predictors of COVID‐19 preventive behaviours (P < 0.05). Conclusion: Sociodemographic characteristics, knowledge of COVID‐19 and general health literacy are crucial in preventing COVID‐19 infections in a sample of the Turkish population. Summary statement: What is already known about the topic? To reduce the risk of transmission and prevent the spread of the COVID‐19, it is necessary to comply with COVID‐19 preventive behaviours.Sociodemographic characteristics, knowledge of COVID‐19 and general health literacy are crucial in preventing the COVID‐19 disease. What does this paper add? COVID‐19 preventive behaviours scored moderately high among a sample of the Turkish population.Being female, having higher level of education, better economic status, being a non‐smoker, having higher level of knowledge about COVID‐19 and better general health literacy are significant predictors of COVID‐19 preventive behaviours in a sample of the Turkish population, accounting for 22.4% of the variance in COVID‐19 preventive behaviours. The implications of this paper: Attempts should be made to increase the COVID‐19 knowledge and health literacy to increase COVID‐19 preventive behaviours among the Turkish population.In particular, attempts should be made to increase the COVID‐19 preventive behaviours for men, individuals with low education and poor economic conditions, and smokers. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
37. First Trimester Potential Biochemical Predictive Tests for Gestational Diabetes Mellitus: A Systematic Review.
- Author
-
Darvish, Soodabeh, Fakari, Farzaneh Rashidi, and Haghdoost, Simin
- Subjects
GESTATIONAL diabetes ,PREDICTIVE tests ,FIRST trimester of pregnancy ,PREGNANCY complications ,PREGNANT women - Abstract
Objective: Gestational diabetes mellitus (GDM) is the most common metabolic complication during pregnancy. So, a large number of studies have evaluated the usefulness of different screening tests. The aim of this study was focused on the potential of only first-trimester screening used in the prediction of GDM. Materials and Methods: In this systematic review, we searched PubMed, EMBASE, and Scopus (between 2010 and 2020) and also searched the reference lists of the relevant articles manually. After performing a thorough evaluation of the 242 potentially eligible papers, only 60 papers were selected in terms of the inclusion criteria. Search key terms were combining 'Gestational diabetes' or 'GD' "gestational diabetes mellitus" or" GDM" or pregnancy- induced diabetes' with at least one of the following terms: "screening test", "first-trimester", "prediction", "marker predictor", "serum marker". Results: A total of 161954 pregnant women were evaluated in these reviewed studies. Moreover, many tests were assessed in the first trimester of pregnancy to predict GDM. This review showed that hs-CRP, FPG, TG, and LDL-C along with maternal BMI in the first trimester were related to the increased risk of developing GDM. Other tests were used in only one or two studies. Conclusion: This review showed that hs-CRP, FPG, TG, and LDL-C along with maternal BMI in the first trimester were linked to an increased risk of developing GDM. It is recommended that further well-designed studies by considering the cost-effective advantages of these predictive tests, should be performed. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
38. New insights into biochar ammoniacal nitrogen adsorption and its correlation to aerobic degradation ammonia emissions.
- Author
-
Vieira Firmino, Matheus, Trémier, Anne, Couvert, Annabelle, and Szymczyk, Anthony
- Subjects
- *
BIOCHAR , *POTASSIUM hydroxide , *ADSORPTION capacity , *SURFACE charges , *ADSORPTION (Chemistry) , *PREDICTIVE tests - Abstract
• Biochar ammoniacal nitrogen adsorption capacity was measured. • Nitric acid increased biochar capacity to reduce aerobic degradation ammonia losses. • Biochar ammoniacal nitrogen adsorption explains its capacity to reduce ammonia losses. • Biochar adsorption properties is related to its surface electrical charge. One of the technical barriers to the wider use of biochar in the composting practices is the lack of accurate quantification linking biochar properties to application outcomes. To address this issue, this paper investigates the use of ammonia nitrogen adsorption capacity by biochar as a predictor of ammonia emission during composting in the presence of biochar. With this in mind, this work investigated the use of ammonia nitrogen adsorption capacity of biochar when mixed with solid digestate, and the reduction in ammonia emissions resulting from the addition of biochar during aerobic degradation of solid digestate. A biochar synthesized at 900 °C, another synthesized at 450 °C, and two derivatives of the latter biochar, one chemically modified with nitric acid and the other with potassium hydroxide, were tested. This study concluded that the chemical characteristics of the biochar, including pH and oxygen/carbon atomic ratio, had a greater influence on the adsorption of ammonia nitrogen than physical attributes such as specific surface area. In this regard, nitric acid modification had superior performance compared to hydroxide potassium modification to increase biochar chemical attributes and reduce ammonia emissions when applied to aerobic degradation. Finally, a significant linear correlation (p-value < 0.05, r2 = 0.79) was found between biochar ammonia nitrogen adsorption capacity and ammonia emissions along composting, showing the potential of this variable as a predictive parameter. This study provides insights for future explorations aiming to develop predictive tests for biochar performance. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
39. MRI-Based Machine Learning Fusion Models to Distinguish Encephalitis and Gliomas.
- Author
-
Zheng, Fei, Yin, Ping, Yang, Li, Wang, Yujian, Hao, Wenhan, Hao, Qi, Chen, Xuzhu, and Hong, Nan
- Subjects
ENCEPHALITIS diagnosis ,PREDICTIVE tests ,GLIOMAS ,DIAGNOSTIC imaging ,RECEIVER operating characteristic curves ,PREDICTION models ,RESEARCH funding ,RADIOMICS ,MAGNETIC resonance imaging ,DECISION making in clinical medicine ,SUPPORT vector machines ,DEEP learning ,MATHEMATICAL models ,COMPUTER-aided diagnosis ,ARTIFICIAL neural networks ,MACHINE learning ,THEORY ,DATA analysis software ,SENSITIVITY & specificity (Statistics) - Abstract
This paper aims to compare the performance of the classical machine learning (CML) model and the deep learning (DL) model, and to assess the effectiveness of utilizing fusion radiomics from both CML and DL in distinguishing encephalitis from glioma in atypical cases. We analysed the axial FLAIR images of preoperative MRI in 116 patients pathologically confirmed as gliomas and clinically diagnosed with encephalitis. The 3 CML models (logistic regression (LR), support vector machine (SVM) and multi-layer perceptron (MLP)), 3 DL models (DenseNet 121, ResNet 50 and ResNet 18) and a deep learning radiomic (DLR) model were established, respectively. The area under the receiver operating curve (AUC) and sensitivity, specificity, accuracy, negative predictive value (NPV) and positive predictive value (PPV) were calculated for the training and validation sets. In addition, a deep learning radiomic nomogram (DLRN) and a web calculator were designed as a tool to aid clinical decision-making. The best DL model (ResNet50) consistently outperformed the best CML model (LR). The DLR model had the best predictive performance, with AUC, sensitivity, specificity, accuracy, NPV and PPV of 0.879, 0.929, 0.800, 0.875, 0.867 and 0.889 in the validation sets, respectively. Calibration curve of DLR model shows good agreement between prediction and observation, and the decision curve analysis (DCA) indicated that the DLR model had higher overall net benefit than the other two models (ResNet50 and LR). Meanwhile, the DLRN and web calculator can provide dynamic assessments. Machine learning (ML) models have the potential to non-invasively differentiate between encephalitis and glioma in atypical cases. Furthermore, combining DL and CML techniques could enhance the performance of the ML models. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
40. Challenges and Opportunities for Twenty First Century Bayesian Econometricians: A Personal View.
- Author
-
van Dijk, Herman K.
- Subjects
TWENTY-first century ,MACHINE learning ,CONDITIONAL probability ,BAYESIAN field theory ,ECONOMIC shock ,TWENTIETH century ,ECONOMICS education ,PREDICTIVE tests - Abstract
This essay is about Bayesian econometrics with a purpose. Specifically, six societal challenges and research opportunities that confront twenty first century Bayesian econometricians are discussed using an important feature of modern Bayesian econometrics: conditional probabilities of a wide range of economic events of interest can be evaluated by using simulation-based Bayesian inference. The enormous advances in hardware and software have made this Bayesian computational approach a very attractive vehicle of research in many subfields in economics where novel data patterns and substantial model complexity are predominant. In this essay the following challenges and opportunities are briefly discussed, including the scientific results obtained in the twentieth century leading up to these challenges: Posterior and predictive analysis of everything: connecting micro-economic causality with macro-economic issues; the need for speed: model complexity and the golden age of algorithms; learning about models, forecasts and policies including their uncertainty; temporal distributional change due to polarisation, imbalances and shocks; climate change and the macroeconomy; finally and most importantly, widespread, accessible, advanced high-level training. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
41. Advanced marketing analytics using partial least squares structural equation modeling (PLS-SEM).
- Author
-
Sarstedt, Marko and Liu, Yide
- Subjects
CORPORATE image ,STRUCTURAL equation modeling ,MARKETING ,MANAGEMENT information systems ,PREDICTIVE tests ,ENTERPRISE resource planning - Abstract
The article discusses the use of partial least squares structural equation modeling (PLS-SEM) in various disciplines, including management information systems, marketing, and psychology. PLS-SEM allows researchers to analyze complex interrelationships between latent variables and their indicators, providing a better understanding of attitudinal and behavioral theories. The article highlights several studies published in the Journal of Marketing Analytics that have used PLS-SEM to assess the effects of COVID-19 on online shopping behavior, the influence of storytelling on the consumer-brand relationship, and the drivers of consumer trust in live streaming platforms. The article also discusses the use of necessary condition analysis (NCA) and artificial neural networks (ANN) in conjunction with PLS-SEM for more robust analysis and model validation. The special issue concludes with review articles on the latest version of SmartPLS software and a book on advanced issues in PLS-SEM. The authors suggest further research in conceptual distinctions between composite models and factor models, the development of necessity logic in PLS-SEM, and the extension of model assessment techniques for PLS path models. The article acknowledges the reviewers and editors for their contributions to the special issue. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF
42. Development and external validation of automated detection, classification, and localization of ankle fractures: inside the black box of a convolutional neural network (CNN).
- Author
-
Prijs, Jasper, Liao, Zhibin, To, Minh-Son, Verjans, Johan, Jutte, Paul C., Stirler, Vincent, Olczak, Jakub, Gordon, Max, Guss, Daniel, DiGiovanni, Christopher W., Jaarsma, Ruurd L., IJpma, Frank F. A., Doornberg, Job N., Aksakal, Kaan, Barvelink, Britt, Beuker, Benn, Bultra, Anne Eva, Oliviera, Luisa e Carmo, Colaris, Joost, and de Klerk, Huub
- Subjects
X-rays ,PREDICTIVE tests ,RESEARCH evaluation ,ANKLE fractures ,AUTOMATION ,ARTIFICIAL neural networks ,RECEIVER operating characteristic curves ,SENSITIVITY & specificity (Statistics) - Abstract
Purpose: Convolutional neural networks (CNNs) are increasingly being developed for automated fracture detection in orthopaedic trauma surgery. Studies to date, however, are limited to providing classification based on the entire image—and only produce heatmaps for approximate fracture localization instead of delineating exact fracture morphology. Therefore, we aimed to answer (1) what is the performance of a CNN that detects, classifies, localizes, and segments an ankle fracture, and (2) would this be externally valid? Methods: The training set included 326 isolated fibula fractures and 423 non-fracture radiographs. The Detectron2 implementation of the Mask R-CNN was trained with labelled and annotated radiographs. The internal validation (or 'test set') and external validation sets consisted of 300 and 334 radiographs, respectively. Consensus agreement between three experienced fellowship-trained trauma surgeons was defined as the ground truth label. Diagnostic accuracy and area under the receiver operator characteristic curve (AUC) were used to assess classification performance. The Intersection over Union (IoU) was used to quantify accuracy of the segmentation predictions by the CNN, where a value of 0.5 is generally considered an adequate segmentation. Results: The final CNN was able to classify fibula fractures according to four classes (Danis-Weber A, B, C and No Fracture) with AUC values ranging from 0.93 to 0.99. Diagnostic accuracy was 89% on the test set with average sensitivity of 89% and specificity of 96%. External validity was 89–90% accurate on a set of radiographs from a different hospital. Accuracies/AUCs observed were 100/0.99 for the 'No Fracture' class, 92/0.99 for 'Weber B', 88/0.93 for 'Weber C', and 76/0.97 for 'Weber A'. For the fracture bounding box prediction by the CNN, a mean IoU of 0.65 (SD ± 0.16) was observed. The fracture segmentation predictions by the CNN resulted in a mean IoU of 0.47 (SD ± 0.17). Conclusions: This study presents a look into the 'black box' of CNNs and represents the first automated delineation (segmentation) of fracture lines on (ankle) radiographs. The AUC values presented in this paper indicate good discriminatory capability of the CNN and substantiate further study of CNNs in detecting and classifying ankle fractures. Level of evidence: II, Diagnostic imaging study. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
43. Systemic Inflammation and Lung Cancer: Is It a Real Paradigm? Prognostic Value of Inflammatory Indexes in Patients with Resected Non-Small-Cell Lung Cancer.
- Author
-
Mazzella, Antonio, Maiolino, Elena, Maisonneuve, Patrick, Loi, Mauro, and Alifano, Marco
- Subjects
LUNG cancer prognosis ,LUNG cancer ,C-reactive protein ,PREDICTIVE tests ,SCIENTIFIC observation ,HEMOGLOBINS ,PLATELET lymphocyte ratio ,INFLAMMATION ,PREOPERATIVE period ,BLOOD platelets ,LOG-rank test ,MULTIVARIATE analysis ,PARADIGMS (Social sciences) ,CANCER patients ,SERUM albumin ,NEUTROPHILS ,LYMPHOCYTES ,NEUTROPHIL lymphocyte ratio ,SURVIVAL rate ,COMPARATIVE studies ,KAPLAN-Meier estimator ,DESCRIPTIVE statistics ,RESEARCH funding ,LUNG surgery ,LONGITUDINAL method ,OVERALL survival ,PROPORTIONAL hazards models - Abstract
Simple Summary: Systemic inflammation and changes in the inflammatory status are frequent features of lung cancer. There is a close interconnection between cancer development and the clinical, general, and inflammatory status of patients. In this paper, we evaluate a large panel of inflammatory indexes in patients who underwent lung resection for NSCLC lung cancer; we show that pre-operative inflammatory status strongly influences long-term prognosis in patients affected by NSCLC and undergoing surgery. Background (1): Our goal was to investigate if and how pre-operative inflammatory status can influence the long-term prognosis of patients undergoing lung surgery for cancer. Materials and Methods (2): This prospective observational study includes the agreement of all operable patients to the study, who were referred to our department between 1 January 2017 and 30 December 2018. The inflammatory pre-operative status of the patients was investigated by calculating albumin, CPR (c-protein reactive), complete blood count (neutrophils, lymphocytes, platelets, hemoglobin), and some other indexes referring to inflammatory status, namely the HALP amalgamated index, platelet-to-lymphocyte ratio (PLR), neutrophil-to-lymphocytes ratio (NLR), systemic immune-inflammation index (SII), and advanced lung cancer inflammation Index (ALI). The follow-up ended in November 2021. Patient overall survival was assessed using the Kaplan–Meier method. The log-rank test was used to compare survival rates. Variables significantly associated with survival at univariate analysis were entered int Cox multivariate analysis (stepwise mode) to assess their independent character. Hazard ratios and their 95% confidence intervals were calculated. Variables associated with p < 0.05 were considered significative. Results (3): We enrolled 257 patients in our study. The overall survival of the cohort was as follows: 1 year, 96.1%; 3 year, 81.3%; and 4 year, 74.2%. Univariate analysis showed risk factors for overall survival as follows: Thoracoscore ≥ 2 (p = 0.002); histology (p = 0.002); HALP < 32.2 (p = 0.0002); SII ≥ 808.9 (p = 0.0004); ALI < 34.86 (p = 0.0005); NLr ≥ 2.29 (p = 0.01); hemoglobin < 13 g/dl (p = 0.01); PLR ≥ 196.1 (p = 0.005); pN+ (p < 0.0001); pleural invasion (p = 0.0002); and presence of vascular or lymphatic tumor emboli (p = 0.0002). Multivariate Cox analysis (stepwise model) identified Thoracoscore ≥ 2 (p = 0.02); histology, HALP < 32.2 (p = 0.004), and pN (p < 0.0001) as independent predictors of death. Conclusion (4): Pre-operative inflammatory status strongly influences long-term prognosis in patients affected by NSCLC and undergoing surgery. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
44. CA-125 Early Dynamics to Predict Overall Survival in Women with Newly Diagnosed Advanced Ovarian Cancer Based on Meta-Analysis Data.
- Author
-
Karamouza, Eleni, Glasspool, Rosalind M., Kelly, Caroline, Lewsley, Liz-Anne, Carty, Karen, Kristensen, Gunnar B., Ethier, Josee-Lyne, Kagimura, Tatsuo, Yanaihara, Nozomu, Cecere, Sabrina Chiara, You, Benoit, Boere, Ingrid A., Pujade-Lauraine, Eric, Ray-Coquard, Isabelle, Proust-Lima, Cécile, and Paoletti, Xavier
- Subjects
THERAPEUTIC use of antineoplastic agents ,OVARIAN tumors ,PREDICTIVE tests ,META-analysis ,CONFIDENCE intervals ,SYSTEMATIC reviews ,CANCER chemotherapy ,EARLY detection of cancer ,COMPARATIVE studies ,RESEARCH funding ,TUMOR antigens ,TUMOR markers ,PREDICTION models ,RECEIVER operating characteristic curves ,WOMEN'S health ,OVERALL survival - Abstract
Simple Summary: Cancer antigen 125 (CA-125) is a protein found at a high concentration in the blood of patients with specific types of cancer, mainly ovarian cancer. In 2004, the Gynecologic Cancer Intergroup (GCIG) proposed criteria defining response to treatment, as well as disease progression, based on the CA-125 concentration. Ever since, for the follow-up of ovarian cancer patients, the CA-125 concentration and/or CT-scans are used. This paper aims to compare different summaries of CA-125 evolution in the 3 to 6 months following treatment initiation in newly diagnosed advanced ovarian cancer and explore their prognostic capacity to predict overall survival. Based on individual patient data from the GCIG meta-analysis, we propose the most appropriate timeframe between follow-up and the prediction horizon in order to obtain robust, dynamic, individual predictions. (1) Background: Cancer antigen 125 (CA-125) is a protein produced by ovarian cancer cells that is used for patients' monitoring. However, the best ways to analyze its decline and prognostic role are poorly quantified. (2) Methods: We leveraged individual patient data from the Gynecologic Cancer Intergroup (GCIG) meta-analysis (N = 5573) to compare different approaches summarizing the early trajectory of CA-125 before the prediction time (called the landmark time) at 3 or 6 months after treatment initiation in order to predict overall survival. These summaries included observed and estimated measures obtained by a linear mixed model (LMM). Their performances were evaluated by 10-fold cross-validation with the Brier score and the area under the ROC (AUC). (3) Results: The estimated value and the last observed value at 3 months were the best measures used to predict overall survival, with an AUC of 0.75 CI 95% [0.70; 0.80] at 24 and 36 months and 0.74 [0.69; 0.80] and 0.75 [0.69; 0.80] at 48 months, respectively, considering that CA-125 over 6 months did not improve the AUC, with 0.74 [0.68; 0.78] at 24 months and 0.71 [0.65; 0.76] at 36 and 48 months. (4) Conclusions: A 3-month surveillance provided reliable individual information on overall survival until 48 months for patients receiving first-line chemotherapy. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
45. ParAlg: A Paraphasia Algorithm for Multinomial Classification of Picture Naming Errors.
- Author
-
Casilio, Marianne, Fergadiotis, Gerasimos, Salem, Alexandra C., Gale, Robert C., McKinney-Bock, Katy, and Bedrick, Steven
- Subjects
DECISION trees ,SEMANTICS ,STATISTICS ,VOWELS ,PHONOLOGICAL awareness ,PREDICTIVE tests ,COGNITION ,DOCUMENTATION ,DATABASE management ,BENCHMARKING (Management) ,INTER-observer reliability ,ANOMIA ,RESEARCH funding ,PHONETICS ,CONSONANTS ,SENSITIVITY & specificity (Statistics) ,ALGORITHMS ,MEDICAL coding - Abstract
Purpose: A preliminary version of a paraphasia classification algorithm (henceforth called ParAlg) has previously been shown to be a viable method for coding picture naming errors. The purpose of this study is to present an updated version of ParAlg, which uses multinomial classification, and comprehensively evaluate its performance when using two different forms of transcribed input. Method: A subset of 11,999 archival responses produced on the Philadelphia Naming Test were classified into six cardinal paraphasia types using ParAlg under two transcription configurations: (a) using phonemic transcriptions for responses exclusively (phonemic-only) and (b) using phonemic transcriptions for nonlexical responses and orthographic transcriptions for lexical responses (orthographic-lexical). Agreement was quantified by comparing ParAlg-generated paraphasia codes between configurations and relative to human-annotated codes using four metrics (positive predictive value, sensitivity, specificity, and F1 score). An item-level qualitative analysis of misclassifications under the best performing configuration was also completed to identify the source and nature of coding discrepancies. Results: Agreement between ParAlg-generated and human-annotated codes was high, although the orthographic-lexical configuration outperformed phonemic-only (weighted-average F1 scores of .78 and .87, respectively). A qualitative analysis of the orthographic-lexical configuration revealed a mix of human- and ParAlg-related misclassifications, the former of which were related primarily to phonological similarity judgments whereas the latter were due to semantic similarity assignment. Conclusions: ParAlg is an accurate and efficient alternative to manual scoring of paraphasias, particularly when lexical responses are orthographically transcribed. With further development, it has the potential to be a useful software application for anomia assessment. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
46. Prediction of successful labor induction in persons with a low Bishop score using machine learning: Secondary analysis of two randomized controlled trials.
- Author
-
D'Souza, Rohan, Doyle, Orla, Miller, Hugh, Pillai, Natasha, Angehrn, Zuzanna, Li, Philip, and Ispas‐Jouron, Simona
- Subjects
INDUCED labor (Obstetrics) ,PREDICTIVE tests ,DINOPROSTONE ,MULTIVARIATE analysis ,MACHINE learning ,TREATMENT effectiveness ,INTRAVAGINAL administration ,DESCRIPTIVE statistics ,RESEARCH funding ,RECEIVER operating characteristic curves ,BODY mass index ,SECONDARY analysis - Abstract
Background: The objective of this paper was to identify predictors of a vaginal birth in individuals with singleton pregnancies and a Bishop Score <4, following Induction of Labor (IoL) using dinoprostone vaginal insert (DVI). Secondarily, we sought to understand the association between oxytocin use for labor augmentation and IoL outcomes. Methods: We developed and internally validated a multivariate prediction model using machine learning (ML) applied to data from two Phase‐III randomized controlled double‐blind trials (NCT01127581, NCT00308711). The model was internally validated using 10‐fold cross‐validation. Results: This study included 1107 participants. Despite unfavorable cervical status and inclusion of high‐risk pregnancies, 72% of participants had vaginal births. The model's area under receiver operating characteristic curve was 0.73. The following factors increased the chance of vaginal birth: being parous; being between 37 and 41 weeks of gestation; having a lower Body Mass Index; having a lower maternal age; having fewer maternal comorbidities; and having a higher Bishop score. Parity alone correctly predicted the outcome in ~50% of cases, at a ~10% false‐negative rate. Participants whose labors progressed without requiring oxytocin had a higher probability of vaginal birth than those requiring oxytocin for either induction or augmentation (81% vs 70% vs 77%, respectively). Discussion: Even in high‐risk pregnancies and with low Bishop scores, the use of DVI results in a high chance of vaginal birth. Parity is a critical predictor of success. The judicious use of oxytocin for labor induction or augmentation can increase the chance of vaginal birth. Our study validates the use of ML and predictive modeling for treatment response prediction when considering IoL. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
47. Diagnostic Value of Intraoperative Frozen Section in Breast-Conserving Surgery: A Systematic Review and Meta-analysis.
- Author
-
Godazandeh, Gholamali, Alizadeh-Navaei, Reza, Shamshirian, Amir, Heydari, Keyvan, and Shojaee, Leyla
- Subjects
ONLINE information services ,PREDICTIVE tests ,META-analysis ,MEDICAL information storage & retrieval systems ,INFORMATION storage & retrieval systems ,MEDICAL databases ,RESEARCH evaluation ,SYSTEMATIC reviews ,FROZEN tissue sections ,REOPERATION ,LUMPECTOMY ,MEDLINE - Abstract
Context: According to previous studies, using the frozen section procedure during breast surgery reduces the rate of error and the need for re-surgery. We aimed at performing a comprehensive systematic review and meta-analysis to provide reliable evidence on the diagnostic value of frozen section procedures in breast-conserving surgery (BCS). Data Sources: A thorough search was performed in PubMed, Embase, Cochrane Library, and Web of Science databases for human diagnostic studies that used the frozen section in BCS. Meta-analyses were done to find the sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (PLR), and negative likelihood ratio (NLR). Study Selection: Human diagnostic studies used the frozen section in breast-conserving surgery and studies that reported the sensitivity and specificity of the frozen section in BCS or contained data that could be calculated the desired parameters were selected for this meta-analysis. Data Extraction: Assessment of studies quality was done and data was extracted from included papers. Then, the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess the quality of included papers. Results: Thirty-five papers were entered into our study. The meta-analysis indicated the high sensitivity (83.47, 95%CI 79.61 - 87.32) and specificity (99.29, 95%CI 98.89 - 99.68) for the frozen section in BCS, which resulted in an accuracy of 93.77 (95%CI 92.45 - 95.10). We also found a significant PPV (93.26, 95%CI 91.25 - 95.27), NPV (92.17, 95%CI 90.22 - 94.11), PLR (7.99, 95%CI 6.01 - 9.96), and NLR (0.18, 95%CI 0.14 - 0.23). Conclusions: The findings showed that intraoperative frozen section analysis has high sensitivity and specificity for evaluating lumpectomy margins in patients with early-stage breast cancer and significantly reduces the need for re-operation. Accordingly, re-operation costs are not imposed on the patient and reduce the anxiety of the patients. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
48. Clustering of Brain Tumor Based on Analysis of MRI Images Using Robust Principal Component Analysis (ROBPCA) Algorithm.
- Author
-
Hamzenejad, Ali, Ghoushchi, Saeid Jafarzadeh, and Baradaran, Vahid
- Subjects
BRAIN anatomy ,ALZHEIMER'S disease diagnosis ,BRAIN tumor diagnosis ,DIGITAL image processing ,PREDICTIVE tests ,MAGNETIC resonance imaging ,GLIOMAS ,PICK'S disease of the brain ,DIAGNOSTIC imaging ,MENINGIOMA ,HUNTINGTON disease ,RECEIVER operating characteristic curves ,ALGORITHMS - Abstract
Automated detection of brain tumor location is essential for both medical and analytical uses. In this paper, we clustered brain MRI images to detect tumor location. To obtain perfect results, we presented an unsupervised robust PCA algorithm to clustered images. The proposed method clusters brain MR image pixels to four leverages. The algorithm is implemented for five brain diseases such as glioma, Huntington, meningioma, Pick, and Alzheimer's. We used ten images of each disease to validate the optimal identification rate. According to the results obtained, 2% of the data in the bad leverage part of the image were determined, which acceptably discerned the tumor. Results show that this method has the potential to detect tumor location for brain disease with high sensitivity. Moreover, results show that the method for the Glioma images has approximately better results than others. However, according to the ROC curve for all selected diseases, the present method can find lesion location. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
49. ROLE OF THE SONOSALPINGOGRAPHY FOR THE ASSESSMENT OF TUBAL PATENCY.
- Author
-
Chakravarti, Vijay Kishor, Kumar, Adesh, Meena, Bijendar Kumar, and Rani, Shubhanshi
- Subjects
ULTRASONIC imaging of fallopian tubes ,PREDICTIVE tests ,PHYSIOLOGIC salines ,INTERPROFESSIONAL relations ,INFERTILITY ,PRIMARY health care ,DESCRIPTIVE statistics ,FALLOPIAN tube patency tests ,WOMEN'S health ,FALLOPIAN tubes ,SENSITIVITY & specificity (Statistics) ,OBESITY - Abstract
Infertility is the most common health problem in the world. Variuous methods and good infertility procedure are available. Aim and Objectives- The aim of our study is to determine the role of Sonosalpingography in the assessment of tubal patency in cases of primary and secondary infertility (Infertility women). Methods -In our study of 50 fruitless women complaining of infertility, suspected tubal pathologies underwent various radiological modalities. Sonosalpingography and Normal Saline wsa performed in all cases. Result- Sonosalpingography has 87.18% Sensitivity and 75.67% Specificity. Analysis of the row data gave positive predictive value of 80.19% and negative predictive value of 79.9% near perfect agreement was seen between the result of the one method. Majority of the cases belong from 26 to 30 years of age and have been suffering from obesity. 90% of the cases had primary type of infertility and only 10% of the cases at secondary type of infertility. Conclusion - Sonosalpingography has a high sensitivity for tubal patency and is less Expensive diagnostic procedure in the management of the infertility in the Females.easely availability and accessibility of the ultrasound in all primary health care centres definitely can prove superior to conventional method of diagnosis of tubal patency in the infertility patients. [ABSTRACT FROM AUTHOR]
- Published
- 2024
50. The value of a new cardiac magnetic resonance imaging protocol in Myocardial Infarction with Non-obstructive Coronary Arteries (MINOCA) - a case-control study using historical controls from a previous study with similar inclusion criteria.
- Author
-
Tornvall, Per, Brolin, E. B., Caidahl, K., Cederlund, K., Collste, O., Daniel, M., Ekenbäck, C., Jensen, J., Y.-Hassan, S., Henareh, L., Hofman-Bang, C., Lyngå, P., Maret, E., Sarkar, N., Spaak, J., Sundqvist, M., Sörensson, P., Ugander, M., and Agewall, S.
- Subjects
CARDIAC magnetic resonance imaging ,MYOCARDIAL infarction diagnosis ,CORONARY disease ,ETIOLOGY of diseases ,CORONARY angiography ,RESEARCH ,PREDICTIVE tests ,RESEARCH methodology ,MAGNETIC resonance imaging ,CASE-control method ,EVALUATION research ,MEDICAL cooperation ,MEDICAL protocols ,COMPARATIVE studies ,QUALITY of life ,QUESTIONNAIRES ,CONTROL groups - Abstract
Background: Myocardial Infarction with Non-Obstructive Coronary Arteries (MINOCA) is common with a prevalence of 6% of all patients fulfilling the diagnosis of myocardial infarction. MINOCA should be considered a working diagnosis. Cardiac Magnetic Resonance (CMR) imaging has recently been suggested to be of great value to determine the cause behind MINOCA. The objectives of this paper are to describe the rationale behind the second Stockholm Myocardial Infarction with Normal Coronaries (SMINC-2) study and to discuss the protocol for investigation of MINOCA patients in the light of the recently published position paper from the European Society of Cardiology.Methods: The SMINC-2 study is an open non-randomised study using historical controls for comparison. The primary aim is to prove that MINOCA patients investigated with the latest CMR imaging technique can achieve a diagnosis in 70% of all cases entirely by imaging. By including 150 patients we will have >80% chance to prove that the diagnostic accuracy can be improved by 20 absolute % with a p-value of less than 0.05 when compared with CMR imaging in the SMINC-1 study. Furthermore, in addition to invasive coronary angiography, coronary arteries are evaluated by computed tomography angiography to investigate coronary causes and questionnaires are used to describe Quality-of-Life (QoL). By January 1st 2017, 75 patients have been included.Discussion: Whether CMR imaging can provide a diagnosis to an adequate proportion of MINOCA patients is unknown. Well-defined inclusion and exclusion criteria will be used to compare a MINOCA cohort from the population with an appropriate control group. Positive results are likely to influence future guidelines of the management of MINOCA. Furthermore, the study will give mechanistic insights into MINOCA in particular in patients with "true" myocardial infarction and describe QoL in this vulnerable group of patients.Trial Registration: Clinical Trials NCT02318498 . [ABSTRACT FROM AUTHOR]- Published
- 2017
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.