Search

BackgroundSystematically recorded smoking data are not always available in vital statistics records, and even when available it can underestimate true smoking rates.ObjectiveTo develop a prediction model for maternal tobacco smoking in late pregnancy based on birth certificate information using a combination of self- or provider-reported smoking and biomarkers (smoking metabolites) in neonatal blood spots as the alloyed gold standard.MethodsWe designed a case-control study where childhood cancer cases were identified from the California Cancer Registry and controls were from the California birth rolls between 1983 and 2011 who were cancer-free by the age of six. In this analysis, we included 894 control participants and performed high-resolution metabolomics analyses in their neonatal dried blood spots, where we extracted cotinine [mass-to-charge ratio (m/z) = 177.1023] and hydroxycotinine (m/z = 193.0973). Potential predictors of smoking were selected from California birth certificates. Logistic regression with stepwise backward selection was used to build a prediction model. Model performance was evaluated in a training sample, a bootstrapped sample, and an external validation sample.ResultsOut of seven predictor variables entered into the logistic model, five were selected by the stepwise procedure: maternal race/ethnicity, maternal education, child's birth year, parity, and child's birth weight. We calculated an overall discrimination accuracy of 0.72 and an area under the receiver operating characteristic curve (AUC) of 0.81 (95% confidence interval [CI] 0.77, 0.84) in the training set. Similar accuracies were achieved in the internal (AUC 0.81, 95% CI 0.77, 0.84) and external (AUC 0.69, 95% CI 0.64, 0.74) validation sets.ConclusionsThis easy-to-apply model may benefit future birth registry-based studies when there is missing maternal smoking information; however, some smoking status misclassification remains a concern when only variables from the birth certificate are used to predict maternal smoking.

BACKGROUND: The high rate of postoperative hypoproteinemia in patients undergoing hip revision is associated with severe trauma, which affects the rapid recovery of patients. OBJECTIVE: To investigate the risk factors of perioperative hypoproteinemia in patients with hip revision, and to provide guidance for early screening of highrisk patients with postoperative hypoproteinemia. METHODS: According to the inclusion and exclusion criteria, 161 patients who underwent hip revision were divided into hypoproteinemia group (76 cases) and normal group (85 cases). The rate of hypoproteinemia was 47.2%. Data such as age, gender, body mass index, osteoporosis, operation time, preoperative erythrocytes, preoperative hemoglobin, preoperative leukocytes, preoperative platelets, preoperative fibrinogen, preoperative C-reaction protein, preoperative sedimentation rate, preoperative blood calcium, preoperative albumin, postoperative drainage tube placement, American Society of Anesthesiologists score, and postoperative hypoproteinemia were collected. SPSS software was used to analyze the independent risk factors of hypoproteinemia after hip revision using multivariate binary logistic regression analysis. R software was used to construct the nomogram prediction model. Receiver operating characteristic curve and calibration curve and decision curve were drawn to evaluate the model. RESULTS AND CONCLUSION: (1) Univariate analysis results showed that body mass index, preoperative erythrocytes, preoperative hemoglobin, preoperative platelets, preoperative fibrinogen, preoperative C-reaction protein, and operation time were significantly different between the two groups (P < 0.05). (2) Multivariate binary Logistic regression analysis results showed that body mass index (OR=0.859, P=0.021), operation time (OR=1.010, P=0.002), preoperative erythrocytes (OR=0.424, P=0.036), and preoperative C-reaction protein (OR=1.043, P=0.032) levels were independent risk factors for postoperative hypoproteinemia in patients with hip revision. (3) Based on four independent risk factors: body mass index, operation time, preoperative erythrocytes and preoperative C-reaction protein, the nomogram can effectively predict the risk of hypoproteinemia after hip revision. This nomogram prediction model has good differentiation and accuracy, and may lead to better clinical net benefits for patients. [ABSTRACT FROM AUTHOR]

Shot peening is a mechanical surface treatment process that enhances the fatigue performance of metallic components. Numerous studies have demonstrated the significant influence of peening particles' motion on the quality of treatment. However, previous research has not established a connection between particle motion characteristics and nozzle structure. The nozzle structure directly affects both airflow characteristics and shot movement, making it crucial to examine how it influences particle motion to optimize both nozzle design and process parameters. To accurately determine the motion characteristics of particles, this study constructs a high-speed camera system for capturing their movements and uses the Particle Image Velocimetry (PIV) method for analysis. This study thoroughly investigates how factors such as jet pressure, nozzle diameter, and length affect shot motion behavior. The results indicate positive correlations between particle velocity with jet pressure and nozzle length while showing a negative correlation with nozzle diameter. Modifying structural parameters can effectively regulate both the velocity and dispersion angles of particles during peening operations under specified jet pressure conditions. Furthermore, based on experimental findings, a new prediction model for particle velocity considering structural parameters associated with nozzles was proposed. [ABSTRACT FROM AUTHOR]

Background and Purpose Methods Results Conclusions Elevated intracranial pressure (ICP) resulting from severe head injury or stroke poses a risk of secondary brain injury that requires neurosurgical intervention. However, currently available noninvasive monitoring techniques for predicting ICP are not sufficiently advanced. We aimed to develop a minimally invasive ICP prediction model using simple CT images to prevent secondary brain injury caused by elevated ICP.We used the following three methods to determine the presence or absence of elevated ICP using midbrain‐level CT images: (1) a deep learning model created using the Python (PY) programming language; (2) a model based on cistern narrowing and scaling of brainstem deformities and presence of hydrocephalus, analyzed using the statistical tool Prediction One (PO); and (3) identification of ICP by senior residents (SRs). We compared the accuracy of the validation and test data using fivefold cross‐validation and visualized or quantified the areas of interest in the models.The accuracy of the validation data for the PY, PO, and SR methods was 83.68% (83.42%‐85.13%), 85.71% (73.81%‐88.10%), and 66.67% (55.96%‐72.62%), respectively. Significant differences in accuracy were observed between the PY and SR methods. Test data accuracy was 77.27% (70.45%‐77.2%), 84.09% (75.00%‐85.23%), and 61.36% (56.82%‐68.18%), respectively.Overall, the outcomes suggest that these newly developed models may be valuable tools for the rapid and accurate detection of elevated ICP in clinical practice. These models can easily be applied to other sites, as a single CT image at the midbrain level can provide a highly accurate diagnosis. [ABSTRACT FROM AUTHOR]

Objective: Submucosal infiltration of less than 200 μm is considered an indication for endoscopic surgery in cases of superficial esophageal cancer and precancerous lesions. This study aims to identify the risk factors associated with submucosal infiltration exceeding 200 micrometers in early esophageal cancer and precancerous lesions, as well as to establish and validate an accompanying predictive model. Methods: Risk factors were identified through least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression. Various machine learning (ML) classification models were tested to develop and evaluate the most effective predictive model, with Shapley Additive Explanations (SHAP) employed for model visualization. Results: Predictive factors for early esophageal invasion into the submucosa included endoscopic ultrasonography or magnifying endoscopy> SM1(P<0.001,OR = 3.972,95%CI 2.161–7.478), esophageal wall thickening(P<0.001,OR = 12.924,95%CI,5.299–33.96), intake of pickled foods(P=0.04,OR = 1.837,95%CI,1.03–3.307), platelet-lymphocyte ratio(P<0.001,OR = 0.284,95%CI,0.137–0.556), tumor size(P<0.027,OR = 2.369,95%CI,1.128–5.267), the percentage of circumferential mucosal defect(P<0.001,OR = 5.286,95%CI,2.671–10.723), and preoperative pathological type(P<0.001,OR = 4.079,95%CI,2.254–7.476). The logistic regression model constructed from the identified risk factors was found to be the optimal model, demonstrating high efficacy with an area under the curve (AUC) of 0.922 in the training set, 0.899 in the validation set, and 0.850 in the test set. Conclusion: A logistic regression model complemented by SHAP visualizations effectively identifies early esophageal cancer reaching 200 micrometers into the submucosa. [ABSTRACT FROM AUTHOR]

BACKGROUND: It has been hypothesized that PANoptosis may be involved in the pathologic process of osteoporosis, but there have been no studies addressing the mechanisms of PANoptosis genes in osteoporosis. OBJECTIVE: To analyze the biological mechanism of PANoptosis regulators in the occurrence and development of osteoporosis. METHODS: The GSE56815 dataset was obtained from the Gene Expression Omnibus database and PANoptosis genes were extracted for differential analysis. The key genes of PANoptosis were screened by random forest tree model to construct a disease risk prediction model. Consensus clustering algorithm, single sample genome enrichment analysis and immune infiltration analysis were used to explore the differences between different PANoptosis molecular subtypes. Herbal drugs that regulate the key genes of PANoptosis were predicted through Coremine medical database, a medical ontology information retrieval platform. RESULTS AND CONCLUSION: Based on the four PANoptosis key genes (CASP1, CASP10, MEFV, and TNF), the diagnostic markers of osteoporosis were determined, and the risk prediction model was constructed and verified. Osteoporosis was divided into two different PANoptosis subtypes (clusters A, B and gene clusters A, B), and the PANoptosis scores of cluster B and gene cluster B were higher than those of cluster A and gene cluster A, respectively. Traditional Chinese drugs such as ginseng which can regulate the key genes of PANoptosis were predicted by the Coremine medical database. [ABSTRACT FROM AUTHOR]

Background: This study aims to develop an artificial neural network (ANN) prediction model incorporating random forest (RF) screening ability for predicting the risk of depression in adolescents and identifies key risk factors to provide a new approach for primary care screening of depression among adolescents. Methods: The data were from a large cross‐sectional study conducted in China from July to September 2021, enrolling 8635 adolescents aged 10–17 with their parents. We used the Patient health questionnaire (PHQ‐9) to rate adolescent depression symptoms, using scales and single‐item questions to collect demographic information and other variables. Initial model variables screening used the RF importance assessment, followed by building prediction model using the screened variables through the ANN. Results: The rate of depression symptoms in adolescents was 24.6%, and the depression risk prediction model was built based on 70% of the training set and 30% of the test set. Ten variables were included in the final prediction model with a model accuracy of 85.03%, AUC of 0.892, specificity of 89.79%, and sensitivity of 70.81%. The top 10 significant factors of depression risk were adolescent rumination, adolescent self‐esteem, adolescent mobile phone addiction, peer victimization, care in parenting styles, overprotection in parenting styles, academic pressure, conflict in parent–child relationship, parental rumination, and relationship between parents. Conclusions: The ANN model based on the RF effectively identifies depression risk in adolescents and provides a methodological reference for large‐scale primary screening. Cross‐sectional studies and single‐item scales limit further improvements in model accuracy. [ABSTRACT FROM AUTHOR]

Background: Migraine is a debilitating neurological disorder that presents significant management challenges, resulting in underdiagnosis and inappropriate treatments, leaving patients at risk of medication overuse (MO). MO contributes to disease progression and the development of medication overuse headache (MOH). Predicting which migraine patients are at risk of MO/MOH is crucial for effective management. Thus, this systematic review aims to review and critique available prediction models for MO/MOH in migraine patients. Methods: A systematic search was conducted using Embase, Scopus, Medline/PubMed, ACM Digital Library, and IEEE databases from inception to April 22, 2024. The risk of bias was assessed using the prediction model risk of bias assessment tool. Results: Out of 1,579 articles, six studies with nine models met the inclusion criteria. Three studies developed new prediction models, while the remaining validated existing scores. Most studies utilized cross-sectional and prospective data collection in specific headache settings and migraine types. The models included up to 53 predictors, with sample sizes from 17 to 1,419 participants. Traditional statistical models (logistic regression and least absolute shrinkage and selection operator regression) were used in two studies, while one utilized a machine learning (ML) technique (support vector machines). Receiver operating characteristic analysis was employed to validate existing scores. The area under the receiver operating characteristic (AUROC) for the ML model (0.83) outperformed the traditional statistical model (0.62) in internal validation. The AUROCs ranged from 0.84 to 0.85 for the validation of existing scores. Common predictors included age and gender; genetic data and questionnaire evaluations were also included. All studies demonstrated a high risk of bias in model construction and high concerns regarding applicability to participants. Conclusion: This review identified promising results for MO/MOH prediction models in migraine patients, although the field remains limited. Future research should incorporate important risk factors, assess discrimination and calibration, and perform external validation. Further studies with robust designs, appropriate settings, high-quality and quantity data, and rigorous methodologies are necessary to advance this field. [ABSTRACT FROM AUTHOR]

STUDY QUESTION Could the risk of subsequent pregnancy loss be predicted based on the risk factors of recurrent pregnancy loss (RPL) patients? SUMMARY ANSWER A nomogram, constructed from independent risk factors identified through multivariate logistic regression, serves as a reliable tool for predicting the likelihood of subsequent pregnancy loss in RPL patients. WHAT IS KNOWN ALREADY Approximately 1–3% of fertile couples experience RPL, with over half lacking a clear etiological factor. Assessing the subsequent pregnancy loss rate in RPL patients and identifying high-risk groups for early intervention is essential for pregnancy counseling. Previous prediction models have mainly focused on unexplained RPL, incorporating baseline characteristics such as age and the number of previous pregnancy losses, with limited inclusion of laboratory and ultrasound indicators. STUDY DESIGN, SIZE, DURATION The retrospective study involved 3387 RPL patients who initially sought treatment at the Reproductive Immunology Clinic of Renji Hospital, Shanghai Jiao Tong University School of Medicine, between 1 January 2020 and 31 December 2022. Of these, 1153 RPL patients met the inclusion criteria and were included in the analysis. PARTICIPANTS/MATERIALS, SETTING, METHODS RPL was defined as two or more pregnancy losses (including biochemical pregnancy loss) with the same partner before 28 weeks of gestation. Data encompassing basic demographics, laboratory indicators (autoantibodies, peripheral immunity coagulation, and endocrine factors), uterine and endometrial ultrasound results, and subsequent pregnancy outcomes were collected from enrolled patients through initial questionnaires, post-pregnancy visits fortnightly, medical data retrieval, and telephone follow-up for lost patients. R software was utilized for data cleaning, dividing the data into a training cohort (n = 808) and a validation cohort (n = 345) in a 7:3 ratio according to pregnancy success and pregnancy loss. Independent predictors were identified through multivariate logistic regression. A nomogram was developed, evaluated by 10-fold cross-validation, and compared with the model incorporating solely age and the number of previous pregnancy losses. The constructed nomogram was evaluated using the AUC, calibration curve, decision curve analysis (DCA), and clinical impact curve analysis (CICA). Patients were then categorized into low- and high-risk subgroups. MAIN RESULTS AND THE ROLE OF CHANCE We included age, number of previous pregnancy losses, lupus anticoagulant, anticardiolipin IgM, anti-phosphatidylserine/prothrombin complex IgM, anti-double-stranded DNA antibody, arachidonic acid-induced platelet aggregation, thrombin time and the sum of bilateral uterine artery systolic/diastolic ratios in the nomogram. The AUCs of the nomogram were 0.808 (95% CI: 0.770–0.846) in the training cohort and 0.731 (95% CI: 0.660–0.802) in the validation cohort, respectively. The 10-fold cross-validated AUC ranged from 0.714 to 0.925, with a mean AUC of 0.795 (95% CI: 0.750–0.839). The AUC of the nomogram was superior compared to the model incorporating solely age and the number of previous pregnancy losses. Calibration curves, DCAs, and CICAs showed good concordance and clinical applicability. Significant differences in pregnancy loss rates were observed between the low- and high-risk groups (P  <   0.001). LIMITATIONS, REASONS FOR CAUTION This study was retrospective and focused on patients from a single reproductive immunology clinic, lacking external validation data. The potential impact of embryonic chromosomal abnormalities on pregnancy loss could not be excluded, and the administration of medication to all cases impacted the investigation of risk factors for pregnancy loss and the model's predictive efficacy. WIDER IMPLICATIONS OF THE FINDINGS This study signifies a pioneering effort in developing and validating a risk prediction nomogram for subsequent pregnancy loss in RPL patients to effectively stratify their risk. We have integrated the nomogram into an online web tool for clinical applications. STUDY FUNDING/COMPETING INTEREST(S) This study was supported by the National Natural Science Foundation of China (82071725). All authors have no competing interests to declare. TRIAL REGISTRATION NUMBER N/A. [ABSTRACT FROM AUTHOR]

Objectives PsA is the most prevalent coexisting condition associated with psoriasis. Early-stage PsA patients always present unspecific and subtle clinical manifestations causing delayed diagnosis and leading to unfavourable health outcomes. The application of US enables precise identification of inflammatory changes in musculoskeletal structures. Hence, we constructed US models to aid early diagnosis of PsA. Methods This was a cross-sectional study carried out in the Department of Dermatology at West China Hospital (October 2018–April 2021). All participants underwent thorough US examinations. Participants were classified into the under 45 group (18 ≤ age ≤ 45 years) and over 45 (age >45 years) group and then randomly grouped into derivation and test cohort (7:3). Univariable logistic regression, least absolute shrinkage and selection operator, and multivariable logistic regression visualized by nomogram were conducted in order. Receiver operating characteristic (ROC), calibration curve, decision curve analysis (DCA) and clinical impact curve analysis (CICA) were performed for model verification. Results A total of 1256 participants were included, with 767 participants in the under 45 group and 489 in the over 45 group. Eleven and 16 independent ultrasonic variables were finally selected to construct the under 45 and over 45 model with the area under the ROC of 0.83 (95% CI 0.78–0.87) and 0.83 (95% CI 0.78–0.88) in derivation cohort, respectively. The DCA and CICA analyses showed good clinical utility of the two models. Conclusion The implementation of the US models could streamline the diagnostic process for PsA in psoriasis patients, leading to expedited evaluations while maintaining diagnostic accuracy. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) demonstrates considerable heterogeneity in the manifestation of clinical symptoms and disease progression. Recently, six clinical milestones have been proposed to evaluate disease severity in PD. However, the identification of PD progression subtypes based on these milestone events has not yet been performed. Methods: Latent class analysis (LCA) was employed to identify subtypes of PD progression based on the timing of the first occurrence of six milestones within a 6-year follow-up period in Parkinson's Progression Markers Initiative (PPMI) database. Results: The study cohort consisted of 354 early PD patients, of whom 42.9% experienced at least one milestone within six years. LCA identified two distinct subtypes of PD progression: slow progression (83%) and rapid progression (17%). The total number of milestones over six years was significantly higher in the rapid progression subtype compared to the slow progression subtype (median: 3.00 vs. 0.00, p < 0.001). At baseline, the rapid progression subtype, compared to the slow progression subtype, was characterized by an older age at onset and more severe motor and non-motor symptoms. On biomarkers, the rapid progression subtype demonstrated elevated CSF p-tau and serum NFL, but decreased mean striatal DAT uptake. Five clinical variables (age, SDMT score, MDS-UPDRS I score, MDS-UPDRS II + III scores, and RBD) were selected to construct the predictive model. The original predictive model achieved an AUC of 0.82. In internal validation using bootstrap resampling, the model achieved an AUC of 0.82, with a 95%CI ranging from 0.76 to 0.87. The model's performance was acceptable regarding both calibration and clinical utility. Conclusion: Approximately 17% of early PD patients exhibited the rapid progression subtype, characterized by the occurrence of more and earlier-onset milestones. The nomogram predictive model, incorporating five baseline clinical variables (age, SDMT score, MDS-UPDRS I score, MDS-UPDRS II + III scores, RBD), serves as a valuable tool for prognostic counseling and patient selection in PD clinical trials. [ABSTRACT FROM AUTHOR]

Background: Hypertension resolution following adrenalectomy in patients with primary aldosteronism (PA) remains a critical clinical challenge. Identifying preoperatively which patients will become normotensive is both a priority and a point of contention. In this narrative review, we explore the controversies and unresolved issues surrounding the prediction of hypertension resolution after adrenalectomy in PA. Methods: A comprehensive literature review was conducted, focusing on studies published between 1954 and 2024 that evaluated all studies that discussed predictive models for hypertension resolution post-adrenalectomy in PA patients. Databases searched included MEDLINE®, Ovid Embase, and Web of Science databases. Results: The review identified several predictors and predictive models of hypertension resolution, including female sex, duration of hypertension, antihypertensive medication, and BMI. However, inconsistencies in study designs and patient populations led to varied conclusions. Conclusions: Although certain predictors and predictive models of hypertension resolution post-adrenalectomy in PA patients are supported by evidence, significant controversies and unresolved issues remain. While the current predictive models provide valuable insights, there is a clear need for further research in this area. Future studies should focus on validating and refining these models. [ABSTRACT FROM AUTHOR]

Contamination in domestic and drinking water during the conveyance process is one of the biggest health risks of all time. This is a very common hazard that is expected in the areas where water, sewer, and drainage pipes are laid in trenches near each other. The extent of the contamination spread in the case of intrusion through a pipe leak for water distribution networks (WDNs) laid on sloping terrain is not known. This article deals with the simulation and hydraulic analysis of organic contaminant intrusion in WDNs with significant consideration of the slope of the laid pipes. The source of organic contamination is considered to be the nearby leaking sewer water. The effects of sloping terrain on contaminant spread in the pipe network are studied in detail by injecting contaminant concentrations at eight different critical locations in the network. The results of contamination spread after a particular time at all nodes are compiled, and by using statistical techniques, a relation between the contaminant spread and pipe slope is proposed. The presented model is validated by comparing the actual values of the contaminant in water samples obtained at the site with the calculated ones, and it shows that the values deviate within the range of ±2% only, which is considered a good match. The research proves to be beneficial for the management of water distribution through pipe networks against contaminants to maintaining water quality and public health. [ABSTRACT FROM AUTHOR]

Hydrogen will play critical pole in industrial field, heating field and transportation field, which can achieve mutual conversion of different energies. Hydrogen load prediction demand is important for establishing unified energy system, a novel prediction model is established based on particle swarm algorithm (PSA) and grey Ridgelet neural network (GRNN) to improve medium and long term hydrogen load demand prediction accuracy. Firstly hydrogen load demand prediction model in unified energy system is established, which concludes hydrogen load demand prediction models in industrial field, heating field and transportation field, and then total hydrogen demand model is deduced. Secondly, model of GRNN is constructed based on grey system theory and Ridgelet neural network, analysis procedure of GRNN is established. Structure of GRNN is confirmed, and mathematical model is constructed. To enhance prediction effectiveness of GRNN, PSA is used to optimize parameters of GRNN. Finally hydrogen load demand data in a province is selected to carry out prediction simulation, results show that prediction error of proposed PSA-GRNN ranges from 1.88% to 3.02%, which is less than that of other three prediction models, and fit goodness of proposed PSA-GRNN ranges from 0.958 to 0.985, which is also less than that of other three prediction models. Therefore proposed PSA-GRNN has better prediction precision and efficiency, which can obtain better precision effect and applicability. Hydrogen load demand prediction results in heating field based on PSAGRNN are closer to real value than that based on other three prediction models, results show that proposed PSA-GRNN has better prediction accuracy that other three prediction models. [ABSTRACT FROM AUTHOR]

This article focuses on the influences of austenitizing temperature and holding time on the grain sizes of 1800 MPa ultrahigh strength steel (UHS‐1800). When the austenitizing temperature increases from 900 to 990 °C and the holding time is 5 min, the austenite grain size increases from 12.60 to 20.88 μm. When the austenitizing temperature is 930 °C and the holding time increases from 3 to 9 min, the grain size increases from 13.52 to 17.22 μm. When the austenitizing temperature increases from 900 to 990 °C and the holding time is 5 min, the radiuses of the second‐phase particles increase from 15.23 to 25.36 nm. When the austenitizing temperature is 930 °C and the holding time increases from 3 to 9 min, the radius of the second‐phase particle increases from 15.72 to 20.50 nm. On this basis, a prediction model for austenite grain growth suitable for UHS‐1800 hot stamping process is proposed. The growth model of the austenite grain can accurately predict the grain growth behavior during the hot stamping process, with a maximum error of 5.35% compared to experiments. [ABSTRACT FROM AUTHOR]

Summary: This is the first study to employ multilevel modeling analysis to develop a predictive tool for falls in individuals who have participated in community group exercise over a year. The tool may benefit healthcare workers in screening community-dwelling older adults with various levels of risks for falls. Purpose: The aim of this study was to develop a calculation tool to predict the risk of falls 1 year in the future and to find the cutoff value for detecting a high risk based on a database of individuals who participated in a community-based group exercise. Methods: We retrospectively reviewed a total of 7726 physical test and Kihon Checklist data from 2381 participants who participated in community-based physical exercise groups. We performed multilevel logistic regression analysis to estimate the odds ratio of falls for each risk factor and used the variance inflation factor to assess collinearity. We determined a cutoff value that effectively distinguishes individuals who are likely to fall within a year based on both sensitivity and specificity. Results: The final model included variables such as age, sex, weight, balance, standing up from a chair without any aid, history of a fall in the previous year, choking, cognitive status, subjective health, and long-term participation. The sensitivity, specificity, and best cutoff value of our tool were 68.4%, 53.8%, and 22%, respectively. Conclusion: Using our tool, an individual's risk of falls over the course of a year could be predicted with acceptable sensitivity and specificity. We recommend a cutoff value of 22% for use in identifying high-risk populations. The tool may benefit healthcare workers in screening community-dwelling older adults with various levels of risk for falls and support physicians in planning preventative and follow-up care. [ABSTRACT FROM AUTHOR]

Objectives: This study was performed to construct and validate a risk prediction model for non-invasive ventilation (NIV) failure after birth in premature infants with gestational age < 32 weeks. Methods: The data were derived from the multicenter retrospective study program – Jiangsu Provincial Neonatal Respiratory Failure Collaboration Network from Jan 2019 to Dec 2021. The subjects finally included were preterm infants using NIV after birth with gestational age less than 32 weeks and admission age within 72 h. After screening by inclusion and exclusion criteria, 1436 babies were subsequently recruited in the study, including 1235 infants in the successful NIV group and 201 infants in the failed NIV group. Results: (1) Gestational age, 5 min Apgar, Max FiO2 during NIV, and FiO2 fluctuation value during NIV were selected by univariate and multivariate analysis. (2) The area under the curve of the prediction model was 0.807 (95% CI: 0.767–0.847) in the training set and 0.825 (95% CI: 0.766–0.883) in the test set. The calibration curve showed good agreement between the predicted probability and the actual observed probability (Mean absolute error = 0.008 for the training set; Mean absolute error = 0.012 for the test set). Decision curve analysis showed good clinical validity of the risk model in the training and test cohorts. Conclusion: This model performed well on dimensions of discrimination, calibration, and clinical validity. This model can serve as a useful tool for neonatologists to predict whether premature infants will experience NIV failure after birth. [ABSTRACT FROM AUTHOR]

The pressure-time relation in the shock flow field of a near-earth air blast is complex. The triple point (TP) path is the physical boundary between the free and non-free shock flow fields. Accurately predicting the TP path is the basis for studying the evolution law of the reflection flow field and the guarantee of effectively assessing the damage power of the warhead. Based on the assumption that the Mach stem center is on the projection point of the blast center on the ground, the TP path calculation method was constructed by the geometric relationship. The unknown coefficients were solved using the existing TP data and the least square method. The TP prediction model proposed was compared with the existing ones on the calibration, new numerical simulation TP, and the measured real blast datasets. The error of the new numerical simulation TP data is within ±15% of the real value. The results show that the TP path prediction model proposed performs better. Most of its prediction results are within ±20% of three datasets compared to other models for the working conditions with the scaled height of burst from 0.397 to 2.777 m/kg1/3 and the horizontal scaled distance within 10 m/kg1/3 in the conventional cylindrical TNT explosion with the length-diameter of 1 in the air. The reliability of the prediction model is verified. [ABSTRACT FROM AUTHOR]

• Found the high-risk factors of PAS patients successfully. • Found the independent risk factors for the occurrence of PAS. • Construct a prediction model of PAS which had great clinical prediction value. To investigate the risk factors affecting patients with placenta previa (PP) and to construct an effective prediction model for the severity of PAS in PP. A total of 240 pregnant women with PP were enrolled in this study. An MRI+Ultrasound-based model was developed to classify patients into placental implantation and non-placental implantation groups. Multivariate nomograms were created based on imaging features. The model was evaluated using Receiver Operating Characteristic (ROC) curve analysis. The predictive accuracy of the nomogram was assessed through calibration plots and decision curve analysis. The MRI+Ultrasound-based prediction model demonstrated favorable discrimination between the placental implantation and non-placental implantation groups. The calibration curve exhibited agreement between the estimated and actual probability of placental implantation. Additionally, decision curve analysis indicated a high clinical benefit across a wide range of probability thresholds. The Area under the ROC curve (AUC) was 0.911 (95 % CI: 0.76–0.947), with a sensitivity of 88.40 % and specificity of 88.10 %. The MRI+Ultrasound-based prediction model could be a valuable tool for preoperative prediction of the percentage of implantation. Our study enables obstetricians to conduct more adequate preoperative evaluations. [ABSTRACT FROM AUTHOR]

This article explores the use of artificial intelligence (AI) in peri-operative prediction model research. It discusses various AI methodologies, including supervised and unsupervised learning, as well as deep learning. The article highlights the importance of methodological considerations when interpreting prediction models, such as sample size, class imbalance, internal and external validation, and evaluation of discrimination and calibration. It also addresses the comparison between traditional statistical methods and machine learning, emphasizing the need for improved reporting and reduction of bias in prediction model research. The article concludes by providing a list of considerations for interpreting prediction model research that utilizes AI. [Extracted from the article]

Although the vehicle dynamics effects of variable anti-roll moment distribution actuated through active suspension systems are widely discussed in the literature, their model-based control has only been recently analysed, given the highly nonlinear nature of the involved dynamics. Moreover, the available studies do not discuss the trade-off between internal model complexity and controller performance, nor analyse the opportunities offered by vehicle connectivity, which enables the prediction of the steering angle and reference yaw rate profiles ahead. To address the gap, this paper introduces and assesses three optimal controllers for an electric vehicle with active suspensions, multiple powertrains, and a brake-by-wire system. The formulations are: (a) a gain scheduled output feedback linear quadratic regulator (OFLQR); (b) a nonlinear model predictive controller using a three-degree-of-freedom prediction model, without and with preview of the steering angle and reference yaw rate ahead, respectively referred to as NMPC-3 and NMPC-3-Pre; and (c) a nonlinear model predictive controller based on an eight-degree-of-freedom prediction model, referred to as NMPC-8 and NMPC-8-Pre depending on the absence or presence of preview. The results on an experimentally validated model show that: (i) NMPC-8 provides evident yaw rate tracking benefits with respect to (w.r.t) OFLQR and NMPC-3; and (ii) NMPC-8-Pre can bring ∼20% yaw rate tracking improvement w.r.t. an optimally tuned NMPC-8 configuration. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of the study was to design a simple, handy prediction for the effect of spherical and cylindrical refractive error on the visual acuity degradation at different distances and validate this model on a clinical dataset. Methods: This study examined 70 eyes from 35 patients' post-cataract surgery with aberration-free intraocular lenses. Biometric and corneal data were analysed, and subjective refraction and visual acuity were evaluated by two experienced optometrists. The study computed the spherical equivalent (SEQ), and defocus equivalent via vector addition (DEQ vec), as the sum of absolute values (DEQ abs). Predictive models were developed using univariate regression, with confidence intervals (BCa 95%) calculated through non-parametric bootstrapping (10,000 cycles). Results: Various calculated equivalents included −0.44 D for spherical equivalent (SEQ), 0.70 D for defocus equivalent based on vector calculation (DEQ vec), and 0.89 D for defocus equivalent based on absolute values (DEQ abs). Uncorrected and corrected visual acuity averaged 0.07 logMAR and −0.04 logMAR, respectively. The absolute defocus equivalent (DEQ abs) exhibited the smallest confidence interval (BCa 95%) at 0.07. Conclusion: The defocus equivalent based on the addition of absolute values (DEQ abs) emerged as the most practical predictor for the described applications. Notably, it offers the advantage of easy calculability through a simple equation: VA loss = DEQ abs ⋅ 0.23. In 95% of cases, this predicted loss would have an accuracy of ±0.03 lines. [ABSTRACT FROM AUTHOR]

Rock abrasiveness is a vital parameter affecting cutter wear, tunneling efficiency, and cost budgeting during mechanical excavation. The Cerchar abrasivity index (CAI), a suggested standard parameter to characterize the rock abrasiveness, can be obtained through the laboratory test. Understanding the correlations between the CAI and physical, mechanical, and mineralogical properties helps to precisely evaluate the cutter wear and improve the excavation efficiency. In this paper, correlations between CAI and 17 commonly used rock parameters were established for 27 groups of rock samples collected from China using simple and multiple regression methods. Based on the Pearson correlation coefficient (PCC) results, the possibility of linear relationships between CAI and physical, mechanical, and mineralogical parameters of rock samples was analyzed for determining the appropriate model. Subsequently, simple linear regression and Boltzmann models were developed based on physical and mechanical parameters. The model based on porosity showed excellent forecasting performance over other models. Through the analysis on the coefficient of determination (R2) value, a better multiregression model (R2 = 0.92) based on the mechanical parameters was obtained. However, a more feasible model (R2 = 0.91) based on the thermal conductivity, diffusion coefficient, elastic modulus, and Rock Abrasivity Index (RAI) was also suggested, considering the simplicity and period of parameter measurement. After the classification of rock types, the linear correlations strengthened significantly, especially for the mineralogical properties. The CAI showed a linear correlation with equivalent quartz content (EQC) and RAI for the granite and sandstone, while the quartz content (Q) still showed no relation with CAI. The results can provide a reference for evaluating the abrasive properties of rock during the mechanical excavation process. [ABSTRACT FROM AUTHOR]

To develop and validate a prediction model utilizing clinical and ultrasound (US) data for preoperative assessment of efficacy following US-guided thermal ablation (TA) in patients with benign thyroid nodules (BTNs) ≥ 2 cm. We retrospectively assessed 962 patients with 1011 BTNs who underwent TA at four tertiary centers between May 2018 and July 2022. Ablation efficacy was categorized into therapeutic success (volume reduction rate [VRR] > 50%) and non-therapeutic success (VRR ≤ 50%). We identified independent factors influencing the ablation efficacy of BTNs ≥ 2 cm in the training set using multivariate logistic regression. On this basis, a prediction model was established. The performance of model was further evaluated by discrimination (area under the curve [AUC]) in the validation set. Of the 1011 nodules included, 952 (94.2%) achieved therapeutic success at the 12-month follow-up after TA. Independent factors influencing VRR > 50% included sex, nodular composition, calcification, volume, and largest diameter (all p < 0.05). The prediction equation was established as follows: p = 1/1 + Exp∑[8.113 −2.720 × (if predominantly solid) −2.790 × (if solid) −1.275 × (if 10 mL < volume ≤ 30mL) −1.743 × (if volume > 30 mL) −1.268 × (if with calcification) −2.859 × (if largest diameter > 3 cm) +1.143 × (if female)]. This model showed great discrimination, with AUC of 0.908 (95% confidence interval [CI]: 0.868–0.947) and 0.850 (95% CI: 0.748–0.952) in the training and validation sets, respectively. A clinical prediction model was successfully developed to preoperatively predict the therapeutic success of BTNs larger than 2 cm in size following US-guided TA. This model aids physicians in evaluating treatment efficacy and devising personalized prognostic plans. [ABSTRACT FROM AUTHOR]

Invasive lumbar puncture is the conventional method for diagnosing neurosyphilis (NS). We investigated a non-invasive alternative method to detect serum Treponema pallidum -specific antibodies against highly immunogenic antigens TP0171 (TP15), TP0435 (TP17), and TP0574 (TP47) by using luciferase immunosorbent assay. A total of 816 HIV-negative patients suspected of NS from the Beijing and Guangzhou cohorts were retrospectively selected and tested for serum anti-TP15, TP17, and TP47 IgG antibodies. Two diagnostic prediction models were developed using stepwise logistic regression in the Beijing cohort, and evaluated in the Guangzhou cohort for external validation. Serum antibodies against TP15, TP17, and TP47 showed moderate capability for NS diagnosis in the Beijing cohort and the corresponding area under the receiver operating characteristic curves (AUCs) were 0.722 [95% confidence interval (CI): 0.680–0.762)], 0.780 (95% CI: 0.741–0.817), and 0.774 (95% CI: 0.734–0.811), respectively. An expanded NS prediction model integrated with anti-TP17 and anti-TP47 antibodies showed better performance than the base NS diagnostic model without anti-TP17 and anti-TP47 antibodies with the AUC of 0.874 (95% CI: 0.841–0.906) vs. 0.845 (95% CI: 0.809–0.881) (p = 0.007) in the development cohort, and 0.934 (95% CI: 0.909–0.960) vs. 0.877 (95% CI: 0.840–0.914) (p < 0.001) in validation cohort, respectively. Decision curve analysis revealed that the net benefit of the expanded model exceeded that of the base model when the threshold probability was between 0.10 and 0.95 in both the development and external validation cohorts. Serum antibodies against TP17 and TP47 exhibited promising diagnostic capability for NS and significantly enhanced the predictive accuracy of model for NS diagnosis. Our study highlights the potential of serum treponemal antibody detection as a non-invasive method for NS diagnosis to substitute invasive lumbar puncture in NS diagnosis. [ABSTRACT FROM AUTHOR]

Objective: The present study aimed to measure fecal and urinary phosphorus (P) excretion from pigs and to develop prediction models for P excretion of pigs. Methods: A total of 96 values for P excretions were obtained from pigs of 15 to 93 kg body weight (BW) fed 12 diets in four experiments and were used to develop the prediction models. All experimental diets contained exogenous phytase at 500 phytase units per kg. Body weight of pigs and dietary P concentrations were used as independent variables in the prediction models. Results: The BW, feed intake, and P intake were positively correlated with total (fecal plus urinary) P excretions (r = 0.80, 0.91, and 0.94, respectively; p<0.001). The models for estimating P excretion were: fecal P excretion (g/d) = –0.654–0.000618×BW2 +0.273×BW ×dietary P concentration (R2 = 0.83; p<0.001); urinary P excretion (g/d) = 0.045+ 0.00781×BW×dietary P concentration (R2 = 0.15; p<0.001); total P excretion (g/d) = –0.598–0.000613×BW2 +0.280×BW×dietary P concentration (R2 = 0.86; p<0.001) where the BW of pigs and dietary P concentration are expressed as kg and % (as-fed basis), respectively. Based on the developed prediction models, the estimated annual fecal, urinary, and total P excretion for a market pig was 1.24, 0.09, and 1.33 kg/yr, respectively. Conclusion: The P excretions in market pigs can be estimated using BW of pigs and dietary P concentration. In the present model, a market pig excretes 1.24 kg of fecal P and 0.09 kg of urinary P per year. [ABSTRACT FROM AUTHOR]

Background: Children with IgA Vasculitis (IgAV) may develop renal complications, which can impact their long-term prognosis. This study aimed to build a machine learning model to predict renal damage in children with IgAV and analyze risk factors for IgA Vasculitis with Nephritis (IgAVN). Methods: 50 clinical indicators were collected from 217 inpatients at our hospital. Six machine learning algorithms—Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbor, Support Vector Machine, Decision Trees, and Random Forest—were utilized to select the model with the highest predictive performance. A simplified model was developed through feature importance ranking and validated by an additional cohort with 46 patients. Results: The random forest model had the highest accuracy, precision, recall, F1 score, and area under the curve, with values of 0.91, 0.98, 0.70, 0.79 and 0.94, respectively. The top 11 features according to the importance ranking were anti-streptolysin O, corticosteroids therapy, antihistamine therapy, absolute eosinophil count, immunoglobulin E, anticoagulant therapy, C-reactive protein, prothrombin time, age at onset, D-dimer, recurrence of rash ≥ 3 times. A simplified model using these features demonstrated optimal performance with an accuracy of 84.2%, a sensitivity of 89.4%, and a specificity of 82.5% in external validation. Finally, we provided a web tool based on the simplified model, whose code was published on https://github.com/mulanruo/IgAVN%5fPrediction. Conclusion: The model based on the random forest algorithm demonstrates good performance in predicting renal damage in children with IgAV, providing a basis for early clinical diagnosis and decision-making. [ABSTRACT FROM AUTHOR]

To analyze influencing factors and establish a prediction model for delayed behavior of early ambulation after surgery for varicose veins of the lower extremity (VVLE). A prospective case-control study. Patients with VVLE were recruited from 2 local hospitals. In total, 498 patients with VVLE were selected using convenience sampling and divided into a training set and a test set. Not applicable. We collected information from the selected participants before surgery and followed up until the day after surgery, then divided them into a normal and delayed ambulation group. Propensity score matching was applied to all participants by type of surgery and anesthesia. All the characteristics in the 2 groups were compared using logistic regression, back propagation neural network (BPNN), and decision tree models. The accuracy, sensitivity, specificity, and area under the curve (AUC) values of the 3 models were compared to determine the optimal model. A total of 406 participants were included after propensity score matching. The AUC values for the training sets of logistic regression, BPNN, and decision tree models were 0.850, 0.932, and 0.757, respectively. The AUC values for the test sets were 0.928, 0.984, and 0.776, respectively. A BPNN was the optimal model. Social Support Rating Scale score, preoperative 30-second sit-stand test score, Clinical-Etiology-Anatomy-Pathophysiology (CEAP) grade, Medical Coping Modes Questionnaire score, and whether you know the need for early ambulation, in descending order of the result of a BPNN model. A probability value greater than 0.56 indicated delayed behavior of early ambulation. Clinicians should pay more attention to those with lower Social Support Rating Scale scores, poor lower limb strength, a higher CEAP grade, and poor medical coping ability, and make patients aware of the necessity and importance of early ambulation, thereby assisting decision-making regarding postoperative rehabilitation. Further research is needed to improve the method, add more variables, and transform the model into a scale to screen and intervene in the delayed behavior of early ambulation of VVLE in advance. [ABSTRACT FROM AUTHOR]

The petroleum refining business consumes approximately 0.2 MMBTU/BBL of energy annually. This consumption is mitigated using heat integration techniques. However, a significant challenge in this process is fouling in the preheat train network of heat exchangers. Fouling necessitates regular cleaning, leading to substantial operational inefficiencies and costs, with annual losses estimated at nearly $16.5 billion. To address this issue, implementing a predictive maintenance model is crucial for performing maintenance at optimal periods, thereby reducing these losses. The study proposes an artificial neural network (ANN) developed using MATLAB's nntool, trained on industrial heat exchanger samples that were preprocessed in Microsoft Excel. This ANN model is designed to forecast fouling patterns in shell and tube heat exchangers. The model's accuracy and effectiveness were validated using R2 (coefficient of determination) and RMSE (root mean square error) measures. The results indicated that the EA-307 Feed-Forward Back-Propagation Neural Network (FFBPNN) model delivered satisfactory performance, with an R2 value of 0.9961. This high level of accuracy underscores the significant impact of the number of neurons on the model's predictive output. Furthermore, the model's testing on a new dataset yielded impressive results, achieving an R2 value of 0.966. This demonstrates the model's robustness and reliability in predicting fouling patterns, facilitating improved maintenance schedules, and minimizing the financial losses associated with fouling. The study highlights the potential of advanced neural network models to significantly enhance the operational efficiency of petroleum refineries by enabling more precise and timely maintenance interventions. [ABSTRACT FROM AUTHOR]

Purpose: Papillary thyroid carcinoma (PTC) frequently coexists with Hashimoto's thyroiditis (HT), which poses challenges in detecting central lymph node metastasis (CLNM) and determining optimal surgical management. Our study aimed to identify the independent predictors for CLNM in PTC patients with HT and develop a comprehensive prediction model for individualized clinical decision-making. Patients and methods: In this retrospective study, a total of 242 consecutive PTC patients who underwent thyroid surgery and central lymph node dissection between February 2019 and December 2021 were included. 129 patients with HT were enrolled as the case group and 113 patients without HT as control. The results of patients' general information, laboratory examination, ultrasound features, pathological evaluation, and BRAF mutation were collected. Multivariate logistic regression analysis was used to identify independent predictors, and the prediction model and nomogram were developed for PTC patients with HT. The performance of the model was assessed using the receiver operating characteristic curve, calibration curve, decision curve analysis, and clinical impact curve. In addition, the impact of the factor BRAF mutation was further evaluated. Results: Multivariate analysis revealed that gender (OR = 8.341, P = 0.013, 95% CI: 1.572, 44.266), maximum diameter (OR = 0.316, P = 0.029, 95% CI: 0.113, 0.888), multifocality (OR = 3.238, P = 0.010, 95% CI: 1.319, 7.948), margin (OR = 2.750, P = 0.046, 95% CI: 1.020, 7.416), and thyrotropin receptor antibody (TR-Ab) (OR = 0.054, P = 0.003, 95% CI: 0.008, 0.374) were identified as independent predictors for CLNM in PTC patients with HT. The area under the curve of the model was 0.82, with accuracy, sensitivity, and specificity of 77.5%, 80.3% and 75.0%, respectively. Meanwhile, the model showed satisfactory performance in the internal validation. Moreover, the results revealed that BRAF mutation cannot further improve the efficacy of the prediction model. Conclusion: Male, maximum diameter > 10mm, multifocal tumors, irregular margin, and lower TR-Ab level have significant predictive value for CLNM in PTC patients with HT. Meanwhile, BRAF mutation may not have a valuable predictive role for CLNM in these cases. The nomogram constructed offers a convenient and valuable tool for clinicians to determine surgical decision and prognostication for patients. [ABSTRACT FROM AUTHOR]

Importance Firearm injuries constitute a public health crisis. At the healthcare encounter level, they are, however, rare events. Objective To develop a predictive model to identify healthcare encounters of adult patients at increased risk of firearm injury to target screening and prevention efforts. Materials and Methods Electronic health records data from Kaiser Permanente Southern California (KPSC) were used to identify healthcare encounters of patients with fatal and non-fatal firearm injuries, as well as healthcare visits of a sample of matched controls during 2010-2018. More than 170 predictors, including diagnoses, healthcare utilization, and neighborhood characteristics were identified. Extreme gradient boosting (XGBoost) and a split sample design were used to train and test a model that predicted risk of firearm injury within the next 3 years at the encounter level. Results A total of 3879 firearm injuries were identified among 5 288 529 KPSC adult members. Prevalence at the healthcare encounter level was 0.01%. The 15 most important predictors included demographics, healthcare utilization, and neighborhood-level socio-economic factors. The sensitivity and specificity of the final model were 0.83 and 0.56, respectively. A very high-risk group (top 1% of predicted risk) yielded a positive predictive value of 0.14% and sensitivity of 13%. This high-risk group potentially reduces screening burden by a factor of 11.7, compared to universal screening. Results for alternative probability cutoffs are presented. Discussion Our model can support more targeted screening in healthcare settings, resulting in improved efficiency of firearm injury risk assessment and prevention efforts. [ABSTRACT FROM AUTHOR]

Central retinal artery occlusion (CRAO) is a kind of ophthalmic emergency which may cause loss of functional visual acuity. However, the limited treatment options emphasize the significance of early disease prevention. Metabolomics has the potential to be a powerful tool for early identification of individuals at risk of CRAO. The aim of the study was to identify potential biomarkers for CRAO through a comprehensive analysis. We employed metabolomics analysis to compare venous blood samples from CRAO patients with cataract patients for the venous difference, as well as arterial and venous blood from CRAO patients for the arteriovenous difference. The analysis of metabolites showed that PC(P-18:0/22:6(4Z,7Z,10Z,13Z,16Z,19Z)), PC(P-18:0/20:4(5Z,8Z,11Z,14Z)) and octanoylcarnitine were strongly correlated with CRAO. We also used univariate logistic regression, random forest (RF), and support vector machine (SVM) to screen clinical parameters of patients and found that HDL-C and ApoA1 showed significant predictive efficacy in CRAO patients. We compared the predictive performance of the clinical parameter model with combined model. The prediction efficiency of the combined model was significantly better with area under the receiver operating characteristic curve (AUROC) of 0.815. Decision curve analysis (DCA) also exhibited a notably higher net benefit rate. These results underscored the potency of these three substances as robust predictors of CRAO occurrence. [ABSTRACT FROM AUTHOR]

Aims: Patients with heart valvular regurgitation is increasing; early screening of potential patients developing heart failure (HF) is crucial. Methods: From 1 November 2019 to 31 October 2023, a total of 509 patients with heart valvular regurgitation hospitalized in the Department of Cardiovascular Disease of the First Affiliated Hospital of Guangzhou University of Traditional Medicine were enrolled. Three hundred fifty‐six cases were selected as the training set for modelling, and 153 cases were selected as the validation set for the internal validation of the model. Results: A predictive model of heart failure with the following nine risk factors was developed: atrial fibrillation (AF), pulmonary infection (PI), coronary artery disease (CAD), creatinine (CREA), low‐density lipoprotein cholesterol (LDL‐C), d‐dimer (DDi), left ventricular end‐diastolic diameter (LVEDd), mitral regurgitation (MR) and aortic regurgitation (AR). The model was evaluated by the C‐index [the training set: area under curve (AUC) 0.937, 95% confidence interval (CI) 0.911–0.963; the validation set: AUC 0.928, 95% CI 0.890–0.967]. Hosmer–Lemeshow test (the training set: χ2 10.908, P = 0.207; the validation set: χ2 4.896, P = 0.769) revealed that both the training and validation sets performed well in terms of model differentiation and calibration. Decision curve analysis showed that both the training and validation sets have higher net benefits, indicating that the model has good utility. Ten‐fold cross‐validation showed that the training set has high similarities with the validation set, which means that the model has good stability. Conclusions: The occurrence of heart failure in patients with valvular regurgitation has a significant correlation with AF, PI, CAD, CREA, LDL‐C, DDi, LVEDd, MR and AR. Based on these risk factors, a prediction model for heart failure was developed and validated, which showed good differentiation and utility, high accuracy and stability, providing a method for predicting heart failure. [ABSTRACT FROM AUTHOR]

Objective To construct a risk prediction model for pulmonary infection in stroke patients and verify its clinical predictive performance. Methods Using convenience sampling, 750 stroke patients hospitalized in a tertiary hospital in Guizhou Province from January 2021 to January 2023 were selected as study subjects. They were divided into a pulmonary infection group (n=267) and a non-pulmonary infection group (n=483) based on whether pulmonary infection occurred. Comparative analysis of relevant data between the two groups was conducted. Logistic regression analysis was applied to establish a risk prediction model. The goodness-of-fit of the model was tested using the Hosmer-Lemeshow (H-L) test, and the predictive performance of the model was evaluated by the area under the receiver operating characteristic curve (ROC curve). Another 145 eligible patients from February to August 2023 were selected to validate the predictive performance of the model. Results Univariate and multivariate analyses revealed that dysphagia [odds ratio (OR) =10.462], coexisting pulmonary diseases (OR=6.046), hypokalemia (OR=2.266), hyponatremia (OR=3.807), low hemoglobin (OR=4.036), National Institutes of Health Stroke Scale (NIHSS) score at admission (OR=38.135), Activities of Daily Living (ADL) score at admission (OR=12. 942), and length of hospital stay (OR=8.992) were independent risk factors for pulmonary infection in stroke patients (P＜0.05). The risk prediction model formula was: Logit (P) =-4.761+2. 348× (dysphagia score) +1.799× (coexisting pulmonary diseases score) +0.818× (hypokalemia score) +1. 337× (hyponatremia score) +1.395× (low hemoglobin score) +3. 641× (NIHSS score) +2.560× (ADL score) +2.196× (length of hospital stay score). The area under the ROC curve of the modeling group was 0.953 [95% confidence interval (95%CI) 0.940-0. 967, P＜0.001], with a Youden index of 0.762, a sensitivity of 0.880, a specificity of 0. 882, and a P value of 0. 553 in the H-L test. The validation results showed that the area under the ROC curve of the validation group was 0. 946 (95%CI: 0. 927-0. 987, P＜0.001), with a sensitivity of 0. 898, a specificity of 0. 875, an accuracy of 88. 3%, and a P value of 0. 510 in the H-L test. Conclusion The established risk prediction model for pulmonary infection in stroke patients has good predictive performance, providing a reference for clinical healthcare professionals to early identify high-risk groups for stroke induced pulmonary infection and facilitating the timely adoption of preventive management measures. [ABSTRACT FROM AUTHOR]

This study aimed to investigate the advantages and applications of machine learning models in predicting the risk of allergic rhinitis (AR) in children aged 2–8, compared to traditional logistic regression. The study analyzed questionnaire data from 7131 children aged 2–8, which was randomly divided into training, validation, and testing sets in a ratio of 55:15:30, repeated 100 times. Predictor variables included parental allergy, medical history during the child’s first year (cfy), and early life environmental factors. The time of first onset of AR was restricted to after the age of 1 year to establish a clear temporal relationship between the predictor variables and the outcome. Feature engineering utilized the chi-square test and the Boruta algorithm, refining the dataset for analysis. The construction utilized Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting Tree (XGBoost) as the models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC), and the optimal decision threshold was determined by weighing multiple metrics on the validation sets and reporting results on the testing set. Additionally, the strengths and limitations of the different models were comprehensively analyzed by stratifying gender, mode of birth, and age subgroups, as well as by varying the number of predictor variables. Furthermore, methods such as Shapley additive explanations (SHAP) and purity of node partition in Random Forest were employed to assess feature importance, along with exploring model stability through alterations in the number of features. In this study, 7131 children aged 2–8 were analyzed, with 524 (7.35%) diagnosed with AR, with an onset age ranging from 2 to 8 years. Optimal parameters were refined using the validation set, and a rigorous process of 100 random divisions and repeated training ensured robust evaluation of the models on the testing set. The model construction involved incorporating fourteen variables, including the history of allergy-related diseases during the child’s first year, familial genetic factors, and early-life indoor environmental factors. The performance of LR, SVM, RF, and XGBoost on the unstratified data test set was 0.715 (standard deviation = 0.023), 0.723 (0.022), 0.747 (0.015), and 0.733 (0.019), respectively; the performance of each model was stable on the stratified data, and the RF performance was significantly better than that of LR (paired samples t-test: p < 0.001). Different techniques for evaluating the importance of features showed that the top5 variables were father or mother with AR, having older siblings, history of food allergy and father’s educational level. Utilizing strategies like stratification and adjusting the number of features, this study constructed a random forest model that outperforms traditional logistic regression. Specifically designed to detect the occurrence of allergic rhinitis (AR) in children aged 2–8, the model incorporates parental allergic history and early life environmental factors. The selection of the optimal cut-off value was determined through a comprehensive evaluation strategy. Additionally, we identified the top 5 crucial features that greatly influence the model’s performance. This study serves as a valuable reference for implementing machine learning-based AR prediction in pediatric populations. [ABSTRACT FROM AUTHOR]

The prognosis of extensive-stage small cell lung cancer is usually poor. In this study, a combined model based on pre-treatment CT radiomics and clinical features was constructed to predict the OS of extensive-stage small cell lung cancer after chemotherapy with immunotherapy.Clinical data of 111 patients with extensive stage small-cell lung cancer who received first-line immunotherapy combined with chemotherapy in our hospital from December 2019 to December 2021 were retrospectively collected. Finally, 93 patients were selected for inclusion in the study, and CT images were obtained through PACS system before treatment. All patients were randomly divided into a training set (n = 66) and a validation set (n = 27). Images were imported into ITK-SNAP to outline areas of interest, and Python software was used to extract radiomics features. A total of 1781 radiomics features were extracted from each patient’s images. The feature dimensions were reduced by MRMR and LASSO methods, and the radiomics features with the greatest predictive value were screened. The weight coefficient of radiomics features was calculated, and the linear combination of the feature parameters and the weight coefficient was used to calculate Radscore. Univariate cox regression analysis was used to screen out the factors significantly associated with prognosis from the radiomics and clinical features, and multivariate cox regression analysis was performed to establish the prognosis prediction model of extensive stage small cell lung cancer. The degree of metastases was selected as a significant clinical prognostic factor by univariate cox regression analysis. Seven radiomics features with significance were selected by LASSO-COX regression analysis, and the Radscore was calculated according to the coefficient of the radiomics features. An alignment diagram survival prediction model was constructed by combining Radscore with the number of metastatic lesions. The study population was stratified into those who survived less than 11 months, and those with a greater than 11 month survival. The C-index was 0.722 (se = 0.044) and 0.68(se = 0.074) in the training and the validation sets, respectively. The Log_rank test results of the combination model were as follows: training set: p < 0.0001, validation set: p = 0.00042. In this study, a combined model based on radiomics and clinical features could predict OS in patients with extensive stage small cell lung cancer after chemotherapy with immunotherapy, which could help guide clinical treatment strategies. [ABSTRACT FROM AUTHOR]

Background: Medical dispute is a global public health issue, which has been garnering increasing attention. In this study, we used machine learning (ML) method to establish a dispute prediction model and explored the clinical-application efficiency of this model in effectively reducing the occurrence of medical disputes. Methods: Retrospective study of All disputes filed by Gansu Medical Mediation Committee from 2019 to 2021 and patients with the same hospital level as that of the dispute group and hospitalization year were randomly selected as the control group in 1:1 ratio. SPSS software was used for univariate feature selection of the 14 factors that may cause disputes, and factors with statistical differences were selected. The data were divided into training and test sets in a 7:3 ratio. Six ML models were selected, and Python was used to establish a dispute prediction model. The area under the curve (AUC) of the receiver operating characteristic curve (ROC), sensitivity, specificity, accuracy, precision, average precision (AP), and F1 score were used to characterize the fitting and accuracy of the models, while decision curve analysis (DCA) was used to evaluate their clinical utility. Results: A total of 1189 patients in the dispute and control groups were extracted. Following 11 influencing factors were selected: the inpatient department, doctor title, patient age, patient gender, patient occupation, payment method, hospitalization days, hospitalization times, discharge method, blood transfusion volume, and hospitalization espenses. Compared to other models, the AUC (0.945, 95% CI 0.913–0.981), Sensitivity (0.887), Accuracy (0.887), AP (0.834), and F1 score (0.880) of the random forest model were higher than those of other models, while the DCA curve indicated its high clinical benefits. Conclusions: Inpatient department, hospitalization expenses, and discharge type are the primary influencing factors of dispute. Random forest exhibited high dispute prediction and clinical-application value and is expected to be promoted for offline dispute prediction. [ABSTRACT FROM AUTHOR]

Chronic lumbopelvic pain (CLPP) and its associated disabilities significantly affect women's social, professional, and personal lives. However, the specific factors contributing to CLPP in women remain unclear. To address this gap, this prospective cross-sectional study aims to identify the risk factors predicting CLPP in women and develop a prediction model that can predict CLPP in women. The study was conducted across Delhi, India, where free health camps were held, and 2400 women were assessed. Among the assessed individuals, the study revealed a high prevalence rate of CLPP among Indian women, standing at 70.4%. Seven risk factors namely, hamstring muscle tightness (> 20° on passive knee extension test), increased lumbar lordosis (> 11.5 cm of the lumbar lordotic index), reduced hip flexibility (> 15 cm on bent knee fallout test), altered foot posture (≥ 20 on foot posture index score), increased perception of psychological stress (> 25 on cohen's perceived stress scale-10 score), reduced physical activity level (< 475 metabolic/minute on international physical activity questionnaire) and reduced performance of transversus abdominis muscle (≤ 5 on deep muscle contraction scale score) strongly predict the risks of CLPP in women. Identifying these risk factors is crucial for effectively preventing and managing CLPP symptoms, especially considering its high prevalence among Indian women. Health professionals should prioritize raising awareness about CLPP and its causative factors, as well as implementing strategies for early detection and intervention. [ABSTRACT FROM AUTHOR]

To develop prediction models for intrapartum caesarean section in vaginal breech birth.This single-center cohort-study included 262 nulliparous and 230 multiparous women attempting vaginal breech birth. For both groups, we developed and (internally) validated three models for the prediction of intrapartum cesarean section.The prediction model for nulliparous women (AUC: 0.67) included epidural analgesia (aOR 2.14; p=0.01), maternal height (aOR 0.64 per 10 cm; p=0.08), birthweight ≥3.8 kg (aOR 2.45; p=0.03) and an interaction term describing the effect of OC if birthweight is ≥3.8 kg (aOR 0.24; p=0.04). An alternative model for nulliparous women which, instead of birthweight, included fetal abdominal circumference with a cut-off at 34 cm (aOR 1.93; p=0.04), showed similar performance (AUC: 0.68). The prediction model for multiparous women (AUC: 0.77) included prelabor rupture of membranes (aOR 0.31; p=0.03), epidural analgesia (aOR 2.42; p=0.07), maternal BMI (aOR 2.92 per 10 kg/m2; p=0.01) and maternal age (aOR 3.17 per decade; p=0.06).Our prediction models show the most relevant risk factors associated with intrapartum cesarean section in vaginal breech birth for both nulliparous and multiparous women. Importantly, this study clarifies the role of the OC by showing that this parameter is only associated with intrapartum cesarean section if birthweight is above 3.8 kg (or abdominal circumference is above 34 cm). Conversely, knowing the OC when the birthweight is less than 3.8 kg (or abdominal circumference is less than 34 cm) did not improve prediction of this surgical outcome. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop and apply a nomogram with good accuracy to predict the risk of CRAB infections in neuro-critically ill patients. In addition, the difficulties and expectations of application such a tool in clinical practice was investigated. Methods: A mixed methods sequential explanatory study design was utilized. We first conducted a retrospective study to identify the risk factors for the development of CRAB infections in neuro-critically ill patients; and further develop and validate a nomogram predictive model. Then, based on the developed predictive tool, medical staff in the neuro-ICU were received an in-depth interview to investigate their opinions and barriers in using the prediction tool during clinical practice. The model development and validation is carried out by R. The transcripts of the interviews were analyzed by Maxqda. Results: In our cohort, the occurrence of CRAB infections was 8.63% (47/544). Multivariate regression analysis showed that the length of neuro-ICU stay, male, diabetes, low red blood cell (RBC) count, high levels of procalcitonin (PCT), and number of antibiotics ≥ 2 were independent risk factors for CRAB infections in neuro-ICU patients. Our nomogram model demonstrated a good calibration and discrimination in both training and validation sets, with AUC values of 0.816 and 0.875. Additionally, the model demonstrated good clinical utility. The significant barriers identified in the interview include "skepticism about the accuracy of the model", "delay in early prediction by the indicator of length of neuro-ICU stay", and "lack of a proper protocol for clinical application". Conclusions: We established and validated a nomogram incorporating six easily accessed indicators during clinical practice (the length of neuro-ICU stay, male, diabetes, RBC, PCT level, and the number of antibiotics used) to predict the risk of CRAB infections in neuro-ICU patients. Medical staff are generally interested in using the tool to predict the risk of CRAB, however delivering clinical prediction tools in routine clinical practice remains challenging. [ABSTRACT FROM AUTHOR]

Background: Stress urinary incontinence (SUI), the prevalent form of urinary incontinence, significantly impairs women's quality of life. This study aims to create a visual nomogram to estimate the risk of SUI within one year postpartum for early intervention in high-risk Chinese women. Methods: We recruited 1,531 postpartum women who gave birth at two hospitals in Kunshan City from 2021 to 2022. Delivery details were meticulously extracted from the hospitals' medical records system, while one-year postpartum follow-ups were conducted via phone surveys specifically designed to ascertain SUI status. Utilizing data from one hospital as the training set, logistic regression analysis was performed to pinpoint significant factors and subsequently construct the nomogram. To ensure robustness, an independent dataset sourced from the second hospital served as the external validation cohort. The model's performance was rigorously evaluated using calibration plots, ROC curves, AUC values, and DCA curves. Results: The study population was 1,125 women. The SUI incidence within one year postpartum was 26% (293/1125). According to the regression analysis, height, pre-pregnancy BMI, method of induction, mode of delivery, perineal condition, neonatal weight, SUI during pregnancy, and SUI during the first pregnancy were incorporated into the nomogram. The AUC of the nomogram was 0.829 (95% CI 0.790–0.867), and the external validation set was 0.746 (95% CI 0.689–0.804). Subgroup analysis based on parity showed good discrimination. The calibration curve indicated concordance. The DCA curve showed a significant net benefit. Conclusion: Drawing from real-world data, we have successfully developed an SUI predictive model tailored for postpartum Chinese women. Upon successful external validation, this model holds immense potential as an effective screening tool for SUI, enabling timely interventions and ultimately may improve women's quality of life. [ABSTRACT FROM AUTHOR]

Objective Methods Results Conclusion To evaluate clinical factors prior to methotrexate (MTX) treatment for tubal ectopic pregnancy and to apply the data to a prediction model for treatment success.A retrospective cohort study was conducted during 2014–2022. Of the 808 patients with a tubal ectopic pregnancy, 372 with a β‐hCG level less than 5000 IU/L were treated with a single dose of MTX and were included in this study. Pretreatment factors, including patient characteristics, initial β‐hCG level, and sonographic parameters, were compared between those who achieved complete resolution and those who needed additional MTX or surgical intervention. A logistic regression model and multivariable analysis were used to predict success. A graphic nomogram was generated to represent the model.Complete resolution of the ectopic pregnancy was achieved in 290 (77.9%) patients after a single dose of MTX. A second dose or surgical intervention was required for 82 (22.0%): 49 (13.2%) received a second dose of MTX and 33 (8.9%) underwent laparoscopic salpingectomy. In the MTX Success group compared to the MTX Failure group, the median β‐hCG levels were lower (746 vs 1347 IU/L, P < 0.001) and the presence of a yolk sac and a fetal pole were less frequent. The predictive model, based on significant variables, includes initial β‐hCG concentration and the visibility of a yolk sac or fetal pole. Analysis with cross‐validation techniques revealed that the model was both accurate and discriminative.A predictive nomogram was developed to predict the success of single‐dose MTX treatment for tubal ectopic pregnancy. [ABSTRACT FROM AUTHOR]

Background: The Nottingham prognostic index (NPI) has been shown to negatively impact survival in breast cancer (BC). However, its ability to predict the locoregional recurrence (LRR) of BC remains still unclear. This study aims to determine whether a higher NPI serves as a significant predictor of LRR in BC. Methods: In total, 238 patients with BC were included in this analysis, and relevant clinicopathological features were collected. Correlation analysis was performed between NPI scores and clinicopathological characteristics. The optimal nomogram model was determined by Akaike information criterion. The accuracy of the model's predictions was evaluated using receiver operating characteristic curves (ROC curves), calibration curves and goodness of fit tests. The clinical application value was assessed through decision curve analysis. Results: Six significant variables were identified, including age, body mass index (BMI), TNM stage, NPI, vascular invasion, perineural invasion (P<0.05). Two prediction models, namely a TNM-stage-based model and an NPI-based model, were constructed. The area under the curve (AUC) for the TNM-stageand NPI-based models were 0.843 (0.785,0.901) and 0.830 (0.766,0.893) in training set and 0.649 (0.520,0.778) and 0.728 (0.610,0.846) in validation set, respectively. Both models exhibited good calibration and goodness of fit. The Fmeasures were 0.761vs 0.756 and 0.556 vs 0.696, respectively. Clinical decision curve analysis showed that both models provided clinical benefits in evaluating risk judgments based on the nomogram model. Conclusions: a higher NPI is an independent risk factor for predicting LRR in BC. The nomogram model based on NPI demonstrates good discrimination and calibration, offering potential clinical benefits. Therefore, it merits widespread adoption and application. [ABSTRACT FROM AUTHOR]

Background: Cervical lymph node metastasis (CLNM) significantly impacts the prognosis of papillary thyroid carcinoma (PTC) patients. Accurate CLNM prediction is crucial for surgical planning and patient outcomes. This study aimed to develop and validate a nomogram-based risk stratification system to predict CLNM in PTC patients. Methods: This retrospective study included 1069 patients from Zhongshan Hospital and 253 from the Qingpu Branch of Zhongshan Hospital. Preoperative ultrasound (US) data and various nodule characteristics were documented. Patients underwent lobectomy with central lymph node dissection and lateral dissection if suspicious. Multivariate logistic regression, least absolute shrinkage and selection operator (LASSO) regression, and the random forest algorithm were used to identify CLNM risk factors. A nomogram was constructed and validated internally and externally. Model performance was assessed via receiver operating characteristic (ROC) curves, calibration plots, DeLong's test, decision curve analysis (DCA), and the clinical impact curve (CIC). Results: Six independent CLNM risk factors were identified: age, sex, tumor size, calcification, internal vascularity, and US-reported CLNM status. The model's area under the curve (AUC) was 0.77 for both the training and the external validation sets. Calibration plots and Hosmer‒Lemeshow (HL) tests showed good calibration. The optimal cutoff value was 0.57, with a sensitivity of 58.02% and a specificity of 83.43%. Risk stratification on the basis of the nomogram categorized patients into low-, intermediate-, and high-risk groups, effectively differentiating the likelihood of CLNM, and an online calculator was created for clinical use. Conclusion: The nomogram accurately predicts CLNM risk in PTC patients, aiding personalized surgical decisions and improving patient management. [ABSTRACT FROM AUTHOR]

AbstractThe impact of transverse load results in the loosening of bolted joints. The loosening condition is determined based on the transverse load and relevant parameters of the bolted joint. To efficiently forecast the loosening state of bolts under various transverse loads and relevant parameters, this study proposes a predictive model for the loosening state of bolted joints. Initially, the relationship between the loosening criteria and relevant parameters is established according to the bolt’s force conditions. Through elementary effect analysis, the high-dimensional representation model is improved, breaking down the loosening criteria function with high-dimensional parameter inputs into a series of low-dimensional functions. Subsequently, the prediction of the loosening state is achieved by training artificial neural networks to approximate multiple low-dimensional functions. The improved predictive model is utilized to determine the critical load for bolted joint loosening. Validation indicates the accuracy of the proposed model. Notably, the influence of the bearing friction coefficient and preload on the critical transverse load is more pronounced compared to the thread friction coefficient. [ABSTRACT FROM AUTHOR]

A combined model was developed using contrast-enhanced CT-based radiomics features and clinical characteristics to predict liver fibrosis stages in patients with chronic liver disease (CLD). We retrospectively analyzed multiphase CT scans and biopsy-confirmed liver fibrosis. 160 CLD patients were randomly divided into 7:3 training/validation ratio. Clinical laboratory indicators associated with liver fibrosis were identified using Spearman's correlation and multivariate logistic regression correlation. Radiomic features were extracted after segmenting the entire liver from multiphase CT images. Feature dimensionality reduction was performed using RF-RFE, LASSO, and mRMR methods. Six radiomics-based models were developed in the training cohort of 112 patients. Internal validation was conducted on 48 randomly assigned patients. Receptor Operating Characteristic (ROC) curves and confusion matrices were constructed to evaluate model performance. The radiomics model exhibited robust performance, with AUC values of 0.810 to 1.000 for significant fibrosis, advanced fibrosis, and cirrhosis. The integrated clinical-radiomics model had superior diagnostic efficacy in the validation cohort, with AUC values of 0.836 to 0.997. Moreover, these models outperformed established biomarkers such as the aspartate aminotransferase to platelet ratio index (APRI) and the fibrosis 4 score (FIB-4), as well as the gamma glutamyl transpeptidase to platelet ratio (GPR), in predicting the fibrotic stages. The clinical-radiomics model holds considerable promise as a non-invasive diagnostic tool for the assessment and staging of liver fibrosis in the patients with CLD, potentially leading to better patient management and outcomes. [ABSTRACT FROM AUTHOR]