Search

Aspirin is widely used for both primary and secondary prevention of panvascular diseases, such as stroke and coronary heart disease (CHD). The optimal balance between reducing panvascular disease events and the potential increase in bleeding risk remains unclear. This study aimed to develop a predictive model specifically designed to assess bleeding risk in individuals using aspirin. A total of 58,415 individuals treated with aspirin were included in this study. Detailed data regarding patient demographics, clinical characteristics, comorbidities, medical history, and laboratory test results were collected from the Affiliated Dongyang Hospital of Wenzhou Medical University. The patients were randomly divided into two groups at a ratio of 7:3. The larger group was used for model development, while the smaller group was used for internal validation. To develop the prediction model, we employed least absolute shrinkage and selection operator (LASSO) regression followed by multivariate logistic regression. The performance of the model was assessed through metrics such as the area under the receiver operating characteristic (ROC) curve (AUC), calibration curves, and decision curve analysis (DCA). The LASSO-derived model employed in this study incorporated six variables, namely, sex, operation, previous bleeding, hemoglobin, platelet count, and cerebral infarction. It demonstrated excellent performance at predicting bleeding risk among aspirin users, with a high AUC of 0.866 (95% CI 0.857–0.874) in the training dataset and 0.861 (95% CI 0.848–0.875) in the test dataset. At a cutoff value of 0.047, the model achieved moderate sensitivity (83.0%) and specificity (73.9%). The calibration curve analysis revealed that the nomogram closely approximated the ideal curve, indicating good calibration. The DCA curve demonstrated a favorable clinical net benefit associated with the nomogram model. Our developed LASSO-derived predictive model has potential as an alternative tool for predicting bleeding in clinical settings. [ABSTRACT FROM AUTHOR]

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or F β -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction—an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality. [ABSTRACT FROM AUTHOR]

Systemic inflammation and reciprocal organ interactions are associated with the pathophysiology of heart failure with preserved ejection fraction (HFpEF). However, the clinical value, especially the diagnositc prediction power of inflammation and extra-cardiac organ dysfunction for HfpEF is not explored. In this cross-sectional study, 1808 hospitalized patients from January 2014 to June 2022 in ChiHFpEF cohort were totally enrolled according to inclusion and exclusion criteria. A diagnostic model with markers from routine blood test as well as liver and renal dysfunction for HFpEF was developed using data from ChiHFpEF-cohort by logistic regression and assessed by receiver operating characteristic curve (ROC) and Brier score. Then, the model was validated by the tenfold cross-validation and presented as nomogram and a web-based online risk calculator as well. Multivariate and LASSO regression analysis revealed that age, hemoglobin, neutrophil to lymphocyte ratio, AST/ALT ratio, creatinine, uric acid, atrial fibrillation, and pulmonary hypertension were associated with HFpEF. The predictive model exhibited reasonably accurate discrimination (ROC, 0.753, 95% CI 0.732–0.772) and calibration (Brier score was 0.200). Subsequent internal validation showed good discrimination and calibration (AUC = 0.750, Brier score was 0.202). In additoin to participating in pathophysiology of HFpEF, inflammation and multi-organ interactions have diagnostic prediction value for HFpEF. Screening and optimizing biomarkers of inflammation and multi-organ interactions stand for a new field to improve noninvasive diagnostic tool for HFpEF. [ABSTRACT FROM AUTHOR]

Preterm birth is one of the most common obstetric complications in low- and middle-income countries, where access to advanced diagnostic tests and imaging is limited. Therefore, we developed and validated a simplified risk prediction tool to predict preterm birth based on easily applicable and routinely collected characteristics of pregnant women in the primary care setting. We used a logistic regression model to develop a model based on the data collected from 481 pregnant women. Model accuracy was evaluated through discrimination (measured by the area under the Receiver Operating Characteristic curve; AUC) and calibration (via calibration graphs and the Hosmer–Lemeshow goodness of fit test). Internal validation was performed using a bootstrapping technique. A simplified risk score was developed, and the cut-off point was determined using the "Youden index" to classify pregnant women into high or low risk for preterm birth. The incidence of preterm birth was 19.5% (95% CI:16.2, 23.3) of pregnancies. The final prediction model incorporated mid-upper arm circumference, gravidity, history of abortion, antenatal care, comorbidity, intimate partner violence, and anemia as predictors of preeclampsia. The AUC of the model was 0.687 (95% CI: 0.62, 0.75). The calibration plot demonstrated a good calibration with a p-value of 0.713 for the Hosmer–Lemeshow goodness of fit test. The model can identify pregnant women at high risk of preterm birth. It is applicable in daily clinical practice and could contribute to the improvement of the health of women and newborns in primary care settings with limited resources. Healthcare providers in rural areas could use this prediction model to improve clinical decision-making and reduce obstetrics complications. [ABSTRACT FROM AUTHOR]

Malnutrition in patients is associated with reduced tolerance to treatment-related side effects and higher risks of complications, directly impacting patient prognosis. Consequently, a pressing requirement exists for the development of uncomplicated yet efficient screening methods to detect patients at heightened nutritional risk. The aim of this study was to formulate a concise nutritional risk prediction model for prompt assessment by oncology medical personnel, facilitating the effective identification of hepatocellular carcinoma patients at an elevated nutritional risk. Retrospective cohort data were collected from hepatocellular carcinoma patients who met the study's inclusion and exclusion criteria between March 2021 and April 2022. The patients were categorized into two groups: a normal nutrition group and a malnutrition group based on body composition assessments. Subsequently, the collected data were analyzed, and predictive models were constructed, followed by simplification. A total of 220 hepatocellular carcinoma patients were included in this study, and the final model incorporated four predictive factors: age, tumor diameter, TNM stage, and anemia. The area under the ROC curve for the short-term nutritional risk prediction model was 0.990 [95% CI (0.966–0.998)]. Further simplification of the scoring rule resulted in an area under the ROC curve of 0.986 [95% CI (0.961, 0.997)]. The developed model provides a rapid and efficient approach to assess the short-term nutritional risk of hepatocellular carcinoma patients. With easily accessible and swift indicators, the model can identify patients with potential nutritional risk more effectively and timely. [ABSTRACT FROM AUTHOR]

High altitude exposure increases the risk of myocardial ischemia (MI) and subsequent cardiovascular death. Machine learning techniques have been used to develop cardiovascular disease prediction models, but no reports exist for high altitude induced myocardial ischemia. Our objective was to establish a machine learning-based MI prediction model and identify key risk factors. Using a prospective cohort study, a predictive model was developed and validated for high-altitude MI. We consolidated the health examination and self-reported electronic questionnaire data (collected between January and June 2022 in 920th Joint Logistic Support Force Hospital of china) of soldiers undergoing high-altitude training, along with the health examination and second self-reported electronic questionnaire data (collected between December 2022 and January 2023) subsequent to their completion on the plateau, into a unified dataset. Participants were subsequently allocated to either the training or test dataset in a 3:1 ratio using random assignment. A predictive model based on clinical features, physical examination, and laboratory results was designed using the training dataset, and the model's performance was evaluated using the area under the receiver operating characteristic curve score (AUC) in the test dataset. Using the training dataset (n = 2141), we developed a myocardial ischemia prediction model with high accuracy (AUC = 0.86) when validated on the test dataset (n = 714). The model was based on five laboratory results: Eosinophils percentage (Eos.Per), Globulin (G), Ca, Glucose (GLU), and Aspartate aminotransferase (AST). Our concise and accurate high-altitude myocardial ischemia incidence prediction model, based on five laboratory results, may be used to identify risks in advance and help individuals and groups prepare before entering high-altitude areas. Further external validation, including female and different age groups, is necessary. [ABSTRACT FROM AUTHOR]

High altitude exposure increases the risk of myocardial ischemia (MI) and subsequent cardiovascular death. Machine learning techniques have been used to develop cardiovascular disease prediction models, but no reports exist for high altitude induced myocardial ischemia. Our objective was to establish a machine learning-based MI prediction model and identify key risk factors. Using a prospective cohort study, a predictive model was developed and validated for high-altitude MI. We consolidated the health examination and self-reported electronic questionnaire data (collected between January and June 2022 in 920th Joint Logistic Support Force Hospital of china) of soldiers undergoing high-altitude training, along with the health examination and second self-reported electronic questionnaire data (collected between December 2022 and January 2023) subsequent to their completion on the plateau, into a unified dataset. Participants were subsequently allocated to either the training or test dataset in a 3:1 ratio using random assignment. A predictive model based on clinical features, physical examination, and laboratory results was designed using the training dataset, and the model's performance was evaluated using the area under the receiver operating characteristic curve score (AUC) in the test dataset. Using the training dataset (n = 2141), we developed a myocardial ischemia prediction model with high accuracy (AUC = 0.86) when validated on the test dataset (n = 714). The model was based on five laboratory results: Eosinophils percentage (Eos.Per), Globulin (G), Ca, Glucose (GLU), and Aspartate aminotransferase (AST). Our concise and accurate high-altitude myocardial ischemia incidence prediction model, based on five laboratory results, may be used to identify risks in advance and help individuals and groups prepare before entering high-altitude areas. Further external validation, including female and different age groups, is necessary. [ABSTRACT FROM AUTHOR]

The occurrence of systemic inflammatory response after percutaneous transhepatic gallbladder drainage brings great risks to patients and is one of the challenges faced by clinicians. Therefore, it is of great significance to find a suitable prediction method for clinicians to intervene early and reduce the transformation of serious complications. Easy-to-obtain and objectively measured clinical features were screened, and logistic regression was used to construct a prediction model. The predictive ability of the model was evaluated by using the receiver operating characteristic curve and the decision curve in the validation set and the training set, respectively. Nine clinical features (CRP, Fever, DBIL, Obstruction, Bile properties, PCT, Length, Width, and Volume factor) were used to construct the prediction model, and the validation results showed that the prediction model had good performance in the training set (AUC = 0.83) and the validation set (AUC = 0.81). The decision curve also showed that the predictive ability of the model incorporating nine clinical features is better than that of a single clinical feature. The model we constructed can accurately predict the occurrence of SIRS, which can guide clinicians to take treatment measures and avoid the deterioration of complications. [ABSTRACT FROM AUTHOR]

Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict post-cardiovascular surgery delirium. Patients aged ≥ 40 years who underwent cardiovascular surgery at a single hospital were prospectively enrolled. Preoperative and intraoperative factors were assessed. Each patient was evaluated for postoperative delirium 7 days after surgery. We developed machine learning models using the Bernoulli naive Bayes, Support vector machine, Random forest, Extra-trees, and XGBoost algorithms. Stratified fivefold cross-validation was performed for each developed model. Of the 87 patients, 24 (27.6%) developed postoperative delirium. Age, use of psychotropic drugs, cognitive function (Mini-Cog < 4), index of activities of daily living (Barthel Index < 100), history of stroke or cerebral hemorrhage, and eGFR (estimated glomerular filtration rate) < 60 were selected to develop delirium prediction models. The Extra-trees model had the best area under the receiver operating characteristic curve (0.76 [standard deviation 0.11]; sensitivity: 0.63; specificity: 0.78). XGBoost showed the highest sensitivity (AUROC, 0.75 [0.07]; sensitivity: 0.67; specificity: 0.79). Machine learning algorithms could predict post-cardiovascular delirium using preoperative data. Trial registration: UMIN-CTR (ID; UMIN000049390). [ABSTRACT FROM AUTHOR]

Accurate prognostic prediction is crucial for treatment decision-making in lung papillary adenocarcinoma (LPADC). The aim of this study was to predict cancer-specific survival in LPADC using ensemble machine learning and classical Cox regression models. Moreover, models were evaluated to provide recommendations based on quantitative data for personalized treatment of LPADC. Data of patients diagnosed with LPADC (2004–2018) were extracted from the Surveillance, Epidemiology, and End Results database. The set of samples was randomly divided into the training and validation sets at a ratio of 7:3. Three ensemble models were selected, namely gradient boosting survival (GBS), random survival forest (RSF), and extra survival trees (EST). In addition, Cox proportional hazards (CoxPH) regression was used to construct the prognostic models. The Harrell's concordance index (C-index), integrated Brier score (IBS), and area under the time-dependent receiver operating characteristic curve (time-dependent AUC) were used to evaluate the performance of the predictive models. A user-friendly web access panel was provided to easily evaluate the model for the prediction of survival and treatment recommendations. A total of 3615 patients were randomly divided into the training and validation cohorts (n = 2530 and 1085, respectively). The extra survival trees, RSF, GBS, and CoxPH models showed good discriminative ability and calibration in both the training and validation cohorts (mean of time-dependent AUC: > 0.84 and > 0.82; C-index: > 0.79 and > 0.77; IBS: < 0.16 and < 0.17, respectively). The RSF and GBS models were more consistent than the CoxPH model in predicting long-term survival. We implemented the developed models as web applications for deployment into clinical practice (accessible through https://shinyshine-820-lpaprediction-model-z3ubbu.streamlit.app/). All four prognostic models showed good discriminative ability and calibration. The RSF and GBS models exhibited the highest effectiveness among all models in predicting the long-term cancer-specific survival of patients with LPADC. This approach may facilitate the development of personalized treatment plans and prediction of prognosis for LPADC. [ABSTRACT FROM AUTHOR]

Septic patients in the intensive care unit (ICU) often develop sepsis-associated delirium (SAD), which is strongly associated with poor prognosis. The aim of this study is to develop a machine learning-based model for the early prediction of SAD. Patient data were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD). The MIMIC-IV data were divided into a training set and an internal validation set, while the eICU-CRD data served as an external validation set. Feature variables were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, support vector machines, decision trees, random forests, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. The performance of the models was evaluated in the validation set. The model was also applied to a group of patients who were not assessed or could not be assessed for delirium. The MIMIC-IV and eICU-CRD databases included 14,620 and 1723 patients, respectively, with a median time to diagnosis of SAD of 24 and 30 h. Compared with Non-SAD patients, SAD patients had higher 28-days ICU mortality rates and longer ICU stays. Among the models compared, the XGBoost model had the best performance and was selected as the final model (internal validation area under the receiver operating characteristic curves (AUROC) = 0.793, external validation AUROC = 0.701). The XGBoost model outperformed other models in predicting SAD. The establishment of this predictive model allows for earlier prediction of SAD compared to traditional delirium assessments and is applicable to patients who are difficult to assess with traditional methods. [ABSTRACT FROM AUTHOR]

Older adults are more likely to require emergency department (ED) visits than others, which might be attributed to their medication use. Being able to predict the likelihood of an ED visit using prescription information and readily available data would be useful for primary care. This study aimed to predict the likelihood of ED visits using extensive medication variables generated according to explicit clinical criteria for elderly people and high-risk medication categories by applying machine learning (ML) methods. Patients aged ≥ 65 years were included, and ED visits were predicted with 146 variables, including demographic and comprehensive medication-related factors, using nationwide claims data. Among the eight ML models, the final model was developed using LightGBM, which showed the best performance. The final model incorporated 93 predictors, including six sociodemographic, 28 comorbidity, and 59 medication-related variables. The final model had an area under the receiver operating characteristic curve of 0.689 in the validation cohort. Approximately half of the top 20 strong predictors were medication-related variables. Here, an ED visit risk prediction model for older people was developed and validated using administrative data that can be easily applied in clinical settings to screen patients who are likely to visit an ED. [ABSTRACT FROM AUTHOR]

Febrile seizures (FS) are the most prevalent type of seizures in children. Existing predictive models for FS exhibit limited predictive ability. To build a better-performing predictive model, a retrospective analysis study was conducted on febrile children who visited the Children's Hospital of Shanghai from July 2020 to March 2021. These children were divided into training set (n = 1453), internal validation set (n = 623) and external validation set (n = 778). The variables included demographic data and complete blood counts (CBCs). The least absolute shrinkage and selection operator (LASSO) method was used to select the predictors of FS. Multivariate logistic regression analysis was used to develop a predictive model. The coefficients derived from the multivariate logistic regression were used to construct a nomogram that predicts the probability of FS. The calibration plot, area under the receiver operating characteristic curve (AUC), and decision curve analysis (DCA) were used to evaluate model performance. Results showed that the AUC of the predictive model in the training set was 0.884 (95% CI 0.861 to 0.908, p < 0.001) and C-statistic of the nomogram was 0.884. The AUC of internal validation set was 0.883 (95% CI 0.844 to 0.922, p < 0.001), and the AUC of external validation set was 0.858 (95% CI 0.820 to 0.896, p < 0.001). In conclusion, the FS predictive model constructed based on CBCs in this study exhibits good predictive ability and has clinical application value. [ABSTRACT FROM AUTHOR]

Accurate prognostic prediction is crucial for treatment decision-making in lung papillary adenocarcinoma (LPADC). The aim of this study was to predict cancer-specific survival in LPADC using ensemble machine learning and classical Cox regression models. Moreover, models were evaluated to provide recommendations based on quantitative data for personalized treatment of LPADC. Data of patients diagnosed with LPADC (2004–2018) were extracted from the Surveillance, Epidemiology, and End Results database. The set of samples was randomly divided into the training and validation sets at a ratio of 7:3. Three ensemble models were selected, namely gradient boosting survival (GBS), random survival forest (RSF), and extra survival trees (EST). In addition, Cox proportional hazards (CoxPH) regression was used to construct the prognostic models. The Harrell's concordance index (C-index), integrated Brier score (IBS), and area under the time-dependent receiver operating characteristic curve (time-dependent AUC) were used to evaluate the performance of the predictive models. A user-friendly web access panel was provided to easily evaluate the model for the prediction of survival and treatment recommendations. A total of 3615 patients were randomly divided into the training and validation cohorts (n = 2530 and 1085, respectively). The extra survival trees, RSF, GBS, and CoxPH models showed good discriminative ability and calibration in both the training and validation cohorts (mean of time-dependent AUC: > 0.84 and > 0.82; C-index: > 0.79 and > 0.77; IBS: < 0.16 and < 0.17, respectively). The RSF and GBS models were more consistent than the CoxPH model in predicting long-term survival. We implemented the developed models as web applications for deployment into clinical practice (accessible through https://shinyshine-820-lpaprediction-model-z3ubbu.streamlit.app/). All four prognostic models showed good discriminative ability and calibration. The RSF and GBS models exhibited the highest effectiveness among all models in predicting the long-term cancer-specific survival of patients with LPADC. This approach may facilitate the development of personalized treatment plans and prediction of prognosis for LPADC. [ABSTRACT FROM AUTHOR]

Prediction of bacteremia is a clinically important but challenging task. An artificial intelligence (AI) model has the potential to facilitate early bacteremia prediction, aiding emergency department (ED) physicians in making timely decisions and reducing unnecessary medical costs. In this study, we developed and externally validated a Bayesian neural network-based AI bacteremia prediction model (AI-BPM). We also evaluated its impact on physician predictive performance considering both AI and physician uncertainties using historical patient data. A retrospective cohort of 15,362 adult patients with blood cultures performed in the ED was used to develop the AI-BPM. The AI-BPM used structured and unstructured text data acquired during the early stage of ED visit, and provided both the point estimate and 95% confidence interval (CI) of its predictions. High AI-BPM uncertainty was defined as when the predetermined bacteremia risk threshold (5%) was included in the 95% CI of the AI-BPM prediction, and low AI-BPM uncertainty was when it was not included. In the temporal validation dataset (N = 8,188), the AI-BPM achieved area under the receiver operating characteristic curve (AUC) of 0.754 (95% CI 0.737–0.771), sensitivity of 0.917 (95% CI 0.897–0.934), and specificity of 0.340 (95% CI 0.330–0.351). In the external validation dataset (N = 7,029), the AI-BPM's AUC was 0.738 (95% CI 0.722–0.755), sensitivity was 0.927 (95% CI 0.909–0.942), and specificity was 0.319 (95% CI 0.307–0.330). The AUC of the post-AI physicians predictions (0.703, 95% CI 0.654–0.753) was significantly improved compared with that of the pre-AI predictions (0.639, 95% CI 0.585–0.693; p-value < 0.001) in the sampled dataset (N = 1,000). The AI-BPM especially improved the predictive performance of physicians in cases with high physician uncertainty (low subjective confidence) and low AI-BPM uncertainty. Our results suggest that the uncertainty of both the AI model and physicians should be considered for successful AI model implementation. [ABSTRACT FROM AUTHOR]

We compared the prediction performance of machine learning-based undiagnosed diabetes prediction models with that of traditional statistics-based prediction models. We used the 2014–2020 Korean National Health and Nutrition Examination Survey (KNHANES) (N = 32,827). The KNHANES 2014–2018 data were used as training and internal validation sets and the 2019–2020 data as external validation sets. The receiver operating characteristic curve area under the curve (AUC) was used to compare the prediction performance of the machine learning-based and the traditional statistics-based prediction models. Using sex, age, resting heart rate, and waist circumference as features, the machine learning-based model showed a higher AUC (0.788 vs. 0.740) than that of the traditional statistical-based prediction model. Using sex, age, waist circumference, family history of diabetes, hypertension, alcohol consumption, and smoking status as features, the machine learning-based prediction model showed a higher AUC (0.802 vs. 0.759) than the traditional statistical-based prediction model. The machine learning-based prediction model using features for maximum prediction performance showed a higher AUC (0.819 vs. 0.765) than the traditional statistical-based prediction model. Machine learning-based prediction models using anthropometric and lifestyle measurements may outperform the traditional statistics-based prediction models in predicting undiagnosed diabetes. [ABSTRACT FROM AUTHOR]

Septic patients in the intensive care unit (ICU) often develop sepsis-associated delirium (SAD), which is strongly associated with poor prognosis. The aim of this study is to develop a machine learning-based model for the early prediction of SAD. Patient data were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD). The MIMIC-IV data were divided into a training set and an internal validation set, while the eICU-CRD data served as an external validation set. Feature variables were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, support vector machines, decision trees, random forests, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. The performance of the models was evaluated in the validation set. The model was also applied to a group of patients who were not assessed or could not be assessed for delirium. The MIMIC-IV and eICU-CRD databases included 14,620 and 1723 patients, respectively, with a median time to diagnosis of SAD of 24 and 30 h. Compared with Non-SAD patients, SAD patients had higher 28-days ICU mortality rates and longer ICU stays. Among the models compared, the XGBoost model had the best performance and was selected as the final model (internal validation area under the receiver operating characteristic curves (AUROC) = 0.793, external validation AUROC = 0.701). The XGBoost model outperformed other models in predicting SAD. The establishment of this predictive model allows for earlier prediction of SAD compared to traditional delirium assessments and is applicable to patients who are difficult to assess with traditional methods. [ABSTRACT FROM AUTHOR]

This study aims to evaluate the specific characteristics of various multileaf collimator (MLC) position errors that are correlated with the indices using dose distribution. The dose distribution was investigated using the gamma, structural similarity, and dosiomics indices. Cases from the American Association of Physicists in Medicine Task Group 119 were planned, and systematic and random MLC position errors were simulated. The indices were obtained from distribution maps and statistically significant indices were selected. The final model was determined when all values of the area under the curve, accuracy, precision, sensitivity, and specificity were higher than 0.8 (p < 0.05). The dose–volume histogram (DVH) relative percentage difference between the error-free and error datasets was examined to investigate clinical relations. Seven multivariate predictive models were finalized. The common significant dosiomics indices (GLCM Energy and GLRLM_LRHGE) can characterize the MLC position error. In addition, the finalized logistic regression model for MLC position error prediction showed excellent performance with AUC > 0.9. Furthermore, the results of the DVH were related to dosiomics analysis in that it reflects the characteristics of the MLC position error. It was also shown that dosiomics analysis could provide important information on localized dose-distribution differences in addition to DVH information. [ABSTRACT FROM AUTHOR]

The association between the embryo quality, clinical characteristics, miRNAs (secreted by blastocysts in the culture medium) and pregnancy outcomes has been well-established. Studies on prediction models for pregnancy outcome, using clinical characteristics and miRNA expression, are limited. We aimed to establish the prediction model for prediction of pregnancy outcome of woman after a fresh cycle of Day 5 single blastocyst transfer (Day 5 SBT) based on clinical data and miRNA expression. A total of 86 women, 50 with successful pregnancy and 36 with pregnancy failure after fresh cycle of Day 5 SBT, were enrolled in this study. All samples were divided into training set and test set (3:1). Based on clinical index statistics of enrolled population and miRNA expression, the prediction model was constructed, followed by validation of the prediction model. Four clinical indicators, female age, sperm DNA fragmentation index, anti-mullerian hormone, estradiol, can be used as independent predictors of pregnancy failure after fresh cycle of Day 5 SBT. Three miRNAs (hsa-miR-199a-3p, hsa-miR-199a-5p and hsa-miR-99a-5p) had a potential diagnostic value for pregnancy failure after Day 5 SBT. The predictive effect of model combining 4 clinical indicators and 3 miRNAs (area under the receiver operating characteristic curve, AUC = 0.853) was better than models combining single 4 clinical indicators (AUC = 0.755) or 3 miRNAs (AUC = 0.713). Based on 4 clinical indicators and 3 miRNAs, a novel model to predict pregnancy outcome in woman after fresh cycle of Day 5 SBT has been developed and validated. The predictive model may be valuable for clinicians to make the optimal clinical decision and patient selection. [ABSTRACT FROM AUTHOR]

To investigate whether the combination scheme of deep learning score (DL-score) and radiomics can improve preoperative diagnosis in the presence of micropapillary/solid (MPP/SOL) patterns in lung adenocarcinoma (ADC). A retrospective cohort of 514 confirmed pathologically lung ADC in 512 patients after surgery was enrolled. The clinicoradiographic model (model 1) and radiomics model (model 2) were developed with logistic regression. The deep learning model (model 3) was constructed based on the deep learning score (DL-score). The combine model (model 4) was based on DL-score and R-score and clinicoradiographic variables. The performance of these models was evaluated with area under the receiver operating characteristic curve (AUC) and compared using DeLong's test internally and externally. The prediction nomogram was plotted, and clinical utility depicted with decision curve. The performance of model 1, model 2, model 3 and model 4 was supported by AUCs of 0.848, 0.896, 0.906, 0.921 in the Internal validation set, that of 0.700, 0.801, 0.730, 0.827 in external validation set, respectively. These models existed statistical significance in internal validation (model 4 vs model 3, P = 0.016; model 4 vs model 1, P = 0.009, respectively) and external validation (model 4 vs model 2, P = 0.036; model 4 vs model 3, P = 0.047; model 4 vs model 1, P = 0.016, respectively). The decision curve analysis (DCA) demonstrated that model 4 predicting the lung ADC with MPP/SOL structure would be more beneficial than the model 1and model 3 but comparable with the model 2. The combined model can improve preoperative diagnosis in the presence of MPP/SOL pattern in lung ADC in clinical practice. [ABSTRACT FROM AUTHOR]

The behavioral and psychological symptoms of dementia (BPSD) are challenging aspects of dementia care. This study used machine learning models to predict the occurrence of BPSD among community-dwelling older adults with dementia. We included 187 older adults with dementia for model training and 35 older adults with dementia for external validation. Demographic and health data and premorbid personality traits were examined at the baseline, and actigraphy was utilized to monitor sleep and activity levels. A symptom diary tracked caregiver-perceived symptom triggers and the daily occurrence of 12 BPSD classified into seven subsyndromes. Several prediction models were also employed, including logistic regression, random forest, gradient boosting machine, and support vector machine. The random forest models revealed the highest area under the receiver operating characteristic curve (AUC) values for hyperactivity, euphoria/elation, and appetite and eating disorders; the gradient boosting machine models for psychotic and affective symptoms; and the support vector machine model showed the highest AUC. The gradient boosting machine model achieved the best performance in terms of average AUC scores across the seven subsyndromes. Caregiver-perceived triggers demonstrated higher feature importance values across the seven subsyndromes than other features. Our findings demonstrate the possibility of predicting BPSD using a machine learning approach. [ABSTRACT FROM AUTHOR]

To develop a predictive model for successful cervical ripening in women that undergo induction of labour by means of a vaginal prostaglandin slow-release delivery system (Propess®). Prospective observational study on 204 women that required induction of labour between February 2019 and May 2020 at "La Mancha Centro" hospital in Alcázar de San Juan, Spain. The main variable studied was effective cervical ripening (Bishop score > 6). Using multivariate analysis and binary logistic regression, we created three initial predictive models (model A: Bishop Score + Ultrasound cervical length + clinical variables (estimated fetal weight, premature rupture of membranes and body mass index)); model B: Ultrasound cervical lenght + clinical variables; and model C: Bishop score + clinical variables) to predict effective cervical ripening. All three predictive models obtained (A, B and C) presented good predictive capabilities, with an area under the ROC curve ≥ 0.76. Predictive model C, composed of the variables: gestational age (OR 1.55, 95% CI 1.18–2.03, p = 0.002), premature rupture of membranes (OR 3.21 95% CI 1.34–7.70, p = 0.09) body mass index (OR 0.93, 95% CI 0.87–0.98, p = 0.012), estimated fetal weight (OR 0.99, 95% CI 0.99–1.00, p = 0.068) and Bishop score (OR 1.49 95% CI 1.18–1.81, p = 0.001), is presented as the model of choice with an area under the ROC curve of 0.76 (95% CI 0.70–0.83, p < 0.001). A predictive model composed of the variables: gestational age, premature rupture of membranes, body mass index, estimated fetal weight and Bishop score upon admission presents good capabilities in predicting successful cervical ripening following administration of prostaglandins. This tool could be useful in making clinical decisions with regard to induction of labour. [ABSTRACT FROM AUTHOR]

To establish a risk prediction model and make individualized assessment for the susceptible diabetic retinopathy (DR) population in type 2 diabetic mellitus (T2DM) patients. According to the retrieval strategy, inclusion and exclusion criteria, the relevant meta-analyses on DR risk factors were searched and evaluated. The pooled odds ratio (OR) or relative risk (RR) of each risk factor was obtained and calculated for β coefficients using logistic regression (LR) model. Besides, an electronic patient-reported outcome questionnaire was developed and 60 cases of DR and non-DR T2DM patients were investigated to validate the developed model. Receiver operating characteristic curve (ROC) was drawn to verify the prediction accuracy of the model. After retrieving, eight meta-analyses with a total of 15,654 cases and 12 risk factors associated with the onset of DR in T2DM, including weight loss surgery, myopia, lipid-lowing drugs, intensive glucose control, course of T2DM, glycated hemoglobin (HbA1c), fasting plasma glucose, hypertension, gender, insulin treatment, residence, and smoking were included for LR modeling. These factors, followed by the respective β coefficient was bariatric surgery (− 0.942), myopia (− 0.357), lipid-lowering drug follow-up < 3y (− 0.994), lipid-lowering drug follow-up > 3y (− 0.223), course of T2DM (0.174), HbA1c (0.372), fasting plasma glucose (0.223), insulin therapy (0.688), rural residence (0.199), smoking (− 0.083), hypertension (0.405), male (0.548), intensive glycemic control (− 0.400) with constant term α (− 0.949) in the constructed model. The area under receiver operating characteristic curve (AUC) of the model in the external validation was 0.912. An application was presented as an example of use. In conclusion, the risk prediction model of DR is developed, which makes individualized assessment for the susceptible DR population feasible and needs to be further verified with large sample size application. [ABSTRACT FROM AUTHOR]

Pandemic plastics (e.g., masks, gloves, aprons, and sanitizer bottles) are global consequences of COVID-19 pandemic-infected waste, which has increased significantly throughout the world. These hazardous wastes play an important role in environmental pollution and indirectly spread COVID-19. Predicting the environmental impacts of these wastes can be used to provide situational management, conduct control procedures, and reduce the COVID-19 effects. In this regard, the presented study attempted to provide a deep learning-based predictive model for forecasting the expansion of the pandemic plastic in the megacities of Iran. As a methodology, a database was gathered from February 27, 2020, to October 10, 2021, for COVID-19 spread and personal protective equipment usage in this period. The dataset was trained and validated using training (80%) and testing (20%) datasets by a deep neural network (DNN) procedure to forecast pandemic plastic pollution. Performance of the DNN-based model is controlled by the confusion matrix, receiver operating characteristic (ROC) curve, and justified by the k-nearest neighbours, decision tree, random forests, support vector machines, Gaussian naïve Bayes, logistic regression, and multilayer perceptron methods. According to the comparative modelling results, the DNN-based model was found to predict more accurately than other methods and have a significant predominance over others with a lower errors rate (MSE = 0.024, RMSE = 0.027, MAPE = 0.025). The ROC curve analysis results (overall accuracy) indicate the DNN model (AUC = 0.929) had the highest score among others. [ABSTRACT FROM AUTHOR]

This study explored the risk factors and established a prediction model for intraoperative hypothermia (IOH) in patients undergoing robotic surgery. We conducted a retrospective survey of patients undergoing elective robotic surgery at the China-Japan Union Hospital of Jilin University during June 2020–October 2021 using institutional medical records. Intraoperative core temperatures and potential influencing factors were collected, and regression analyses were used to assess the risk factors for IOH and establish a prediction model for the incidence of IOH. Overall, 833 patients who underwent robotic surgery were included in the final analysis; IOH was observed in 344 patients (incidence, 0.41; 95% confidence interval [CI] 0.38–0.45). A higher body mass index (BMI) and baseline core temperature were protective factors for IOH. A final prediction model for IOH was developed based on the determining factors with an area under the receiver operating characteristic curve of 0.85 under fivefold cross validation (95% CI 0.83–0.88). Accordingly, a lower BMI and baseline core temperature, thoracic surgeries, morning surgeries, and surgeries with longer durations were risk factors for IOH during robotic surgeries. Our prediction model has an excellent discrimination ability for predicting IOH in robotic surgeries. [ABSTRACT FROM AUTHOR]

Chemotherapy-related thrombocytopenia (CIT) is a significant adverse event during chemotherapy, which can lead to reduced relative dose intensity, increased risk of serious bleeding and additional medical expenditure. Herein, we aimed to develop and validate a predictive nomogram model for prediction of CIT in patients with solid tumor. From Jun 1, 2018 to Sep 9, 2021, a total of 1541 patients who received 5750 cycles of chemotherapy were retrospectively enrolled. Cox regression analysis was performed to identify predictive factors to establish the nomogram model for CIT. The incidence of chemotherapy-induced thrombocytopenia was 21.03% for patient-based and 10.26% for cycles of chemotherapy. The top five solid tumors with CIT are cervix, gastric, bladder, biliary systemic, and ovarian. The incidence of chemotherapy dose delays in any cycle because of CIT was 5.39%. Multivariate analysis showed that tumor site, treatment line, AST, oxaliplatin, and capecitabine were significantly associated with CIT. Moreover, we established a nomogram model for CIT probability prediction, and the model was well calibrated (Hosme-Lemeshow P = 0.230) and the area under the receiver operating characteristic curve was 0.844 (Sensitivity was 0.625, Specificity was 0.901). We developed a predictive model for chemotherapy-induced thrombocytopenia based on readily available and easily assessable clinical characteristics. The predictive model based on clinical and laboratory indices represents a promising tool in the prediction of CIT, which might complement the clinical management of thrombocytopenia. [ABSTRACT FROM AUTHOR]

Risk prediction requires comprehensive integration of clinical information and concurrent radiological findings. We present an upgraded chest radiograph (CXR) explainable artificial intelligence (xAI) model, which was trained on 241,723 well-annotated CXRs obtained prior to the onset of the COVID-19 pandemic. Mean area under the receiver operating characteristic curve (AUROC) for detection of 20 radiographic features was 0.955 (95% CI 0.938–0.955) on PA view and 0.909 (95% CI 0.890–0.925) on AP view. Coexistent and correlated radiographic findings are displayed in an interpretation table, and calibrated classifier confidence is displayed on an AI scoreboard. Retrieval of similar feature patches and comparable CXRs from a Model-Derived Atlas provides justification for model predictions. To demonstrate the feasibility of a fine-tuning approach for efficient and scalable development of xAI risk prediction models, we applied our CXR xAI model, in combination with clinical information, to predict oxygen requirement in COVID-19 patients. Prediction accuracy for high flow oxygen (HFO) and mechanical ventilation (MV) was 0.953 and 0.934 at 24 h and 0.932 and 0.836 at 72 h from the time of emergency department (ED) admission, respectively. Our CXR xAI model is auditable and captures key pathophysiological manifestations of cardiorespiratory diseases and cardiothoracic comorbidities. This model can be efficiently and broadly applied via a fine-tuning approach to provide fully automated risk and outcome predictions in various clinical scenarios in real-world practice. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) and heart failure (HF) are the first and most frequent comorbidities associated with mortality risks in early-stage type 2 diabetes mellitus (T2DM). However, efficient screening and risk assessment strategies for identifying T2DM patients at high risk of developing CKD and/or HF (CKD/HF) remains to be established. This study aimed to generate a novel machine learning (ML) model to predict the risk of developing CKD/HF in early-stage T2DM patients. The models were derived from a retrospective cohort of 217,054 T2DM patients without a history of cardiovascular and renal diseases extracted from a Japanese claims database. Among algorithms used for the ML, extreme gradient boosting exhibited the best performance for CKD/HF diagnosis and hospitalization after internal validation and was further validated using another dataset including 16,822 patients. In the external validation, 5-years prediction area under the receiver operating characteristic curves for CKD/HF diagnosis and hospitalization were 0.718 and 0.837, respectively. In Kaplan–Meier curves analysis, patients predicted to be at high risk showed significant increase in CKD/HF diagnosis and hospitalization compared with those at low risk. Thus, the developed model predicted the risk of developing CKD/HF in T2DM patients with reasonable probability in the external validation cohort. Clinical approach identifying T2DM at high risk of developing CKD/HF using ML models may contribute to improved prognosis by promoting early diagnosis and intervention. [ABSTRACT FROM AUTHOR]

Lymph node metastasis (LNM) is a well-established prognostic factor in endometrial cancer (EC). We aimed to construct a model that predicts LNM and prognosis using preoperative factors such as myometrial invasion (MI), enlarged lymph nodes (LNs), histological grade determined by endometrial biopsy, and serum cancer antigen 125 (CA125) level using two independent cohorts consisting of 254 EC patients. The area under the receiver operating characteristic curve (AUC) of the constructed model was 0.80 regardless of the machine learning techniques. Enlarged LNs and higher serum CA125 levels were more significant in patients with low-grade EC (LGEC) and LNM than in patients without LNM, whereas deep MI and higher CA125 levels were more significant in patients with high-grade EC (HGEC) and LNM than in patients without LNM. The predictive performance of LNM in the HGEC group was higher than that in the LGEC group (AUC = 0.84 and 0.75, respectively). Patients in the group without postoperative pathological LNM and positive LNM prediction had significantly worse relapse-free and overall survival than patients with negative LNM prediction (log-rank test, P < 0.01). This study showed that preoperative clinicopathological factors can predict LNM with high precision and detect patients with poor prognoses. Furthermore, clinicopathological factors associated with LNM were different between HGEC and LGEC patients. [ABSTRACT FROM AUTHOR]

Identifying lncRNA-disease associations is conducive to the diagnosis, treatment and prevention of diseases. Due to the expensive and time-consuming methods verified by biological experiments, prediction methods based on computational models have gradually become an important means of lncRNA-disease associations discovery. However, existing methods still have challenges to make full use of network topology information to identify potential associations between lncRNA and disease in multi-source data. In this study, we propose a novel method called HGNNLDA for lncRNA-disease association prediction. First, HGNNLDA constructs a heterogeneous network composed of lncRNA similarity network, lncRNA-disease association network and lncRNA-miRNA association network; Then, on this heterogeneous network, various types of strong correlation neighbors with fixed size are sampled for each node by restart random walk; Next, the embedding information of lncRNA and disease in each lncRNA-disease association pair is obtained by the method of type-based neighbor aggregation and all types combination though heterogeneous graph neural network, in which attention mechanism is introduced considering that different types of neighbors will make different contributions to the prediction of lncRNA-disease association. As a result, the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPR) under fivefold cross-validation (5FCV) are 0.9786 and 0.8891, respectively. Compared with five state-of-art prediction models, HGNNLDA has better prediction performance. In addition, in two types of case studies, it is further verified that our method can effectively predict the potential lncRNA-disease associations, and have ability to predict new diseases without any known lncRNAs. [ABSTRACT FROM AUTHOR]

We sought to verify the reliability of machine learning (ML) in developing diabetes prediction models by utilizing big data. To this end, we compared the reliability of gradient boosting decision tree (GBDT) and logistic regression (LR) models using data obtained from the Kokuho-database of the Osaka prefecture, Japan. To develop the models, we focused on 16 predictors from health checkup data from April 2013 to December 2014. A total of 277,651 eligible participants were studied. The prediction models were developed using a light gradient boosting machine (LightGBM), which is an effective GBDT implementation algorithm, and LR. Their reliabilities were measured based on expected calibration error (ECE), negative log-likelihood (Logloss), and reliability diagrams. Similarly, their classification accuracies were measured in the area under the curve (AUC). We further analyzed their reliabilities while changing the sample size for training. Among the 277,651 participants, 15,900 (7978 males and 7922 females) were newly diagnosed with diabetes within 3 years. LightGBM (LR) achieved an ECE of 0.0018 ± 0.00033 (0.0048 ± 0.00058), a Logloss of 0.167 ± 0.00062 (0.172 ± 0.00090), and an AUC of 0.844 ± 0.0025 (0.826 ± 0.0035). From sample size analysis, the reliability of LightGBM became higher than LR when the sample size increased more than 10 4 . Thus, we confirmed that GBDT provides a more reliable model than that of LR in the development of diabetes prediction models using big data. ML could potentially produce a highly reliable diabetes prediction model, a helpful tool for improving lifestyle and preventing diabetes. [ABSTRACT FROM AUTHOR]

In recent years, nonalcoholic fatty liver disease (NAFLD) has become the most important chronic liver disease worldwide. The prevalence of NAFLD in China has also increased year by year. This study aimed to detect NAFLD early by developing a nomogram model in Chinese individuals. A total of 8861 subjects who underwent physical examination in Karamay and were 18 to 62 years old were enrolled. Clinical information, laboratory results and ultrasound findings were retrieved. The participants were randomly assigned to the development set (n = 6203) and the validation set (n = 2658). Significant variables independently associated with NAFLD were identified by least absolute shrinkage and selection operator (LASSO) regression and the multiple logistic regression model. Six variables were selected to construct the nomogram: age, sex, waist circumference (WC), body mass index (BMI), alanine aminotransferase (ALT), triglycerides and glucose index (TyG). The area under the receiver operating characteristic curve (AUROC) of the development set and validation set was 0.886 and 0.894, respectively. The calibration curves showed excellent accuracy of the nomogram model. This physical examination and laboratory test-based nomogram can predict the risk of NAFLD intuitively and individually. [ABSTRACT FROM AUTHOR]

Genome changes play a crucial role in carcinogenesis, and many biomarkers can be used as effective prognostic indicators in various tumors. Although previous studies have constructed many predictive models for hepatocellular carcinoma (HCC) based on molecular signatures, the performance is unsatisfactory. Because multi-omics data can more comprehensively reflect the biological phenomenon of disease, we hope to build a more accurate predictive model by multi-omics analysis. We use the TCGA to identify crucial biomarkers and construct prognostic models through difference analysis, univariate Cox, and LASSO/stepwise Cox analysis. The performances of predictive models were evaluated and validated through survival analysis, Harrell's concordance index (C-index), receiver operating characteristic (ROC) curve, and decision curve analysis (DCA). Multiple mRNAs, lncRNAs, miRNAs, CNV genes, and SNPs were significantly associated with the prognosis of HCC. We constructed five single-omic models, and the mRNA and lncRNA models showed good performance with c-indexes over 0.70. The multi-omics model presented a robust predictive ability with a c-index over 0.77. This study identified many biomarkers that may help study underlying carcinogenesis mechanisms in HCC. In addition, we constructed multiple single-omic models and an integrated multi-omics model that may provide practical and reliable guides for prognosis assessment. [ABSTRACT FROM AUTHOR]

We sought to evaluate the performance of machine learning prediction models for identifying vision-threatening diabetic retinopathy (VTDR) in patients with type 2 diabetes mellitus using only medical data from data warehouse. This is a multicenter electronic medical records review study. Patients with type 2 diabetes screened for diabetic retinopathy and followed-up for 10 years were included from six referral hospitals sharing same electronic medical record system (n = 9,102). Patient demographics, laboratory results, visual acuities (VAs), and occurrence of VTDR were collected. Prediction models for VTDR were developed using machine learning models. F1 score, accuracy, specificity, and area under the receiver operating characteristic curve (AUC) were analyzed. Machine learning models revealed F1 score, accuracy, specificity, and AUC values of up 0.89, 0.89.0.95, and 0.96 during training. The trained models predicted the occurrence of VTDR at 10-year with F1 score, accuracy, and specificity up to 0.81, 0.70, and 0.66, respectively, on test set. Important predictors included baseline VA, duration of diabetes treatment, serum level of glycated hemoglobin and creatinine, estimated glomerular filtration rate and blood pressure. The models could predict the long-term occurrence of VTDR with fair performance. Although there might be limitation due to lack of funduscopic findings, prediction models trained using medical data can facilitate proper referral of subjects at high risk for VTDR to an ophthalmologist from primary care. [ABSTRACT FROM AUTHOR]

Currently, there are no effective approaches for differentiating ovarian fibrothecoma (OF) from broad ligament myoma (BLM). This retrospective study aimed to construct a nomogram prediction model based on MRI to differentiate OF from BLM. The quantitative and qualitative MRI features of 41 OFs and 51 BLMs were compared. Three models were established based on the combination of these features. The ability of the models to differentiate between the two cancers was assessed by ROC analysis. A nomogram based on the best model was constructed for clinical application. The three models showed good performance in differentiating between OF and BLM. The areas under the curve (AUC) of the models based on quantitative and qualitative variables were 0.88 (95% CI: 0.79–0.96) and 0.85 (95% CI: 0.76–0.93), respectively. The combined model designed from the significant variables exhibited the best diagnostic performance with the highest AUC of 0.92 (95% CI: 0.86–0.98). Calibration of the nomogram showed that the predicted probability matched the actual probability well. Analysis of the decision curve demonstrated that the nomogram was clinically useful. Relative T1 value, stone paving sign, enhancement patterns, and ascites were identified as valuable predictors for identifying OF or BLM. The MRI-based nomogram can serve as a preoperative tool to differentiate OF from BLM. [ABSTRACT FROM AUTHOR]

Infertility is a significant health problem and assisted reproductive technologies to treat infertility. Despite all efforts, the success rate of these methods is still low. Also, each of these methods has side effects and costs. Therefore, accurate prediction of treatment success rate is a clinical challenge. This retrospective study aimed to internally validate and compare various machine learning models for predicting the clinical pregnancy rate (CPR) of infertility treatment. For this purpose, data from 1931 patients consisting of in vitro fertilization (IVF) or intra cytoplasmic sperm injection (ICSI) (733) and intra uterine insemination (IUI) (1196) treatments were included. Also, no egg or sperm donation data were used. The performance of machine learning algorithms to predict clinical pregnancy were expressed in terms of accuracy, recall, F-score, positive predictive value (PPV), brier score (BS), Matthew correlation coefficient (MCC), and receiver operating characteristic. The significance of the features with CPR and AUCs was evaluated by Student's t test and DeLong's algorithm. Random forest (RF) model had the highest accuracy in the IVF/ICSI treatment. The sensitivity, F1 score, PPV, and MCC of the RF model were 0.76, 0.73, 0.80, and 0.5, respectively. These values for IUI treatment were 0.84, 0.80, 0.82, and 0.34, respectively. The BS was 0.13 and 0.15 for IVF/ICS and IUI, respectively. In addition, the estimated AUCs of the RF model for IVF/ICS and IUI were 0.73 and 0.7, respectively. Some essential features were obtained based on RF ranking for the two datasets, including age, follicle stimulation hormone, endometrial thickness, and infertility duration. The results showed a strong relationship between clinical pregnancy and a woman's age. Also, endometrial thickness and the number of follicles decreased with increasing female age in both treatments. [ABSTRACT FROM AUTHOR]

The purpose of our study was to develop a predictive model to rule out pheochromocytoma among adrenal tumours, based on unenhanced computed tomography (CT) and/or magnetic resonance imaging (MRI) features. We performed a retrospective multicentre study of 1131 patients presenting with adrenal lesions including 163 subjects with histological confirmation of pheochromocytoma (PHEO), and 968 patients showing no clinical suspicion of pheochromocytoma in whom plasma and/or urinary metanephrines and/or catecholamines were within reference ranges (non-PHEO). We found that tumour size was significantly larger in PHEO than non-PHEO lesions (44.3 ± 33.2 versus 20.6 ± 9.2 mm respectively; P < 0.001). Mean unenhanced CT attenuation was higher in PHEO (52.4 ± 43.1 versus 4.7 ± 17.9HU; P < 0.001). High lipid content in CT was more frequent among non-PHEO (83.6% versus 3.8% respectively; P < 0.001); and this feature alone had 83.6% sensitivity and 96.2% specificity to rule out pheochromocytoma with an area under the receiver operating characteristics curve (AUC-ROC) of 0.899. The combination of high lipid content and tumour size improved the diagnostic accuracy (AUC-ROC 0.961, sensitivity 88.1% and specificity 92.3%). The probability of having a pheochromocytoma was 0.1% for adrenal lesions smaller than 20 mm showing high lipid content in CT. Ninety percent of non-PHEO presented loss of signal in the "out of phase" MRI sequence compared to 39.0% of PHEO (P < 0.001), but the specificity of this feature for the diagnosis of non-PHEO lesions low. In conclusion, our study suggests that sparing biochemical screening for pheochromocytoma might be reasonable in patients with adrenal lesions smaller than 20 mm showing high lipid content in the CT scan, if there are no typical signs and symptoms of pheochromocytoma. [ABSTRACT FROM AUTHOR]

Type 2 diabetes mellitus (T2DM) with hypertension (DH) is the most common diabetic comorbidity. Patients with DH have significantly higher rates of cardiovascular disease morbidity and mortality. The objective of this study was to develop and validate a nomogram model for the prediction of an individual's risk of developing DH. A total of 706 T2DM patients who met the criteria were selected and divided into a training set (n = 521) and a validation set (n = 185) according to the discharge time of patients. By using multivariate logistic regression analysis and stepwise regression, the DH nomogram prediction model was created. Calibration curves were used to evaluate the model's accuracy, while decision curve analysis (DCA) and receiver operating characteristic (ROC) curves were used to evaluate the model's clinical applicability and discriminatory power. Age, body mass index (BMI), diabetic nephropathy (DN), and diabetic retinopathy (DR) were all independent risk factors for DH (P < 0.05). Based on independent risk factors identified by multivariate logistic regression, the nomogram model was created. The model produces accurate predictions. If the total nomogram score is greater than 120, there is a 90% or higher chance of developing DH. In the training and validation sets, the model's ROC curves are 0.762 (95% CI 0.720–0.803) and 0.700 (95% CI 0.623–0.777), respectively. The calibration curve demonstrates that there is good agreement between the model's predictions and the actual outcomes. The decision curve analysis findings demonstrated that the nomogram model was clinically helpful throughout a broad threshold probability range. The DH risk prediction nomogram model constructed in this study can help clinicians identify individuals at high risk for DH at an early stage, which is a guideline for personalized prevention and treatments. [ABSTRACT FROM AUTHOR]

Venous thromboembolism (VTE), clinically presenting as deep vein thrombosis (DVT) or pulmonary embolism (PE). Not all DVT patients carry the same risk of developing acute pulmonary embolism (APE). To develop and validate a prediction model to estimate risk of APE in DVT patients combined with past medical history, clinical symptoms, physical signs, and the sign of the electrocardiogram. We analyzed data from a retrospective cohort of patients who were diagnosed as symptomatic VTE from 2013 to 2018 (n = 1582). Among them, 122 patients were excluded. All enrolled patients confirmed by pulmonary angiography or computed tomography pulmonary angiography (CTPA) and compression venous ultrasonography. Using the LASSO and logistics regression, we derived a predictive model with 16 candidate variables to predict the risk of APE and completed internal validation. Overall, 52.9% patients had DVT + APE (773 vs 1460), 47.1% patients only had DVT (687 vs 1460). The APE risk prediction model included one pre-existing disease or condition (respiratory failure), one risk factors (infection), three symptoms (dyspnea, hemoptysis and syncope), five signs (skin cold clammy, tachycardia, diminished respiration, pulmonary rales and accentuation/splitting of P2), and six ECG indicators (SIQIIITIII, right axis deviation, left axis deviation, S1S2S3, T wave inversion and Q/q wave), of which all were positively associated with APE. The ROC curves of the model showed AUC of 0.79 (95% CI, 0.77–0.82) and 0.80 (95% CI, 0.76–0.84) in the training set and testing set. The model showed good predictive accuracy (calibration slope, 0.83 and Brier score, 0.18). Based on a retrospective single-center population study, we developed a novel prediction model to identify patients with different risks for APE in DVT patients, which may be useful for quickly estimating the probability of APE before obtaining definitive test results and speeding up emergency management processes. [ABSTRACT FROM AUTHOR]

Respiratory syncytial virus (RSV) is a leading cause of childhood morbidity, however there is no systematic testing in children hospitalised with respiratory symptoms. Therefore, current RSV incidence likely underestimates the true burden. We used probabilistically linked perinatal, hospital, and laboratory records of 321,825 children born in Western Australia (WA), 2000–2012. We generated a predictive model for RSV positivity in hospitalised children aged < 5 years. We applied the model to all hospitalisations in our population-based cohort to determine the true RSV incidence, and under-ascertainment fraction. The model's predictive performance was determined using cross-validated area under the receiver operating characteristic (AUROC) curve. From 321,825 hospitalisations, 37,784 were tested for RSV (22.8% positive). Predictors of RSV positivity included younger admission age, male sex, non-Aboriginal ethnicity, a diagnosis of bronchiolitis and longer hospital stay. Our model showed good predictive accuracy (AUROC: 0.87). The respective sensitivity, specificity, positive predictive value and negative predictive values were 58.4%, 92.2%, 68.6% and 88.3%. The predicted incidence rates of hospitalised RSV for children aged < 3 months was 43.7/1000 child-years (95% CI 42.1–45.4) compared with 31.7/1000 child-years (95% CI 30.3–33.1) from laboratory-confirmed RSV admissions. Findings from our study suggest that the true burden of RSV may be 30–57% higher than current estimates. [ABSTRACT FROM AUTHOR]

Currently, the most widely used screening methods for hyperuricemia (HUA) involves invasive laboratory tests, which are lacking in many rural hospitals in China. This study explored the use of non-invasive physical examinations to construct a simple prediction model for HUA, in order to reduce the economic burden and invasive operations such as blood sampling, and provide some help for the health management of people in poor areas with backward medical resources. Data of 9252 adults from April to June 2017 in the Affiliated Hospital of Guilin Medical College were collected and divided randomly into a training set (n = 6364) and a validation set (n = 2888) at a ratio of 7:3. In the training set, non-invasive physical examination indicators of age, gender, body mass index (BMI) and prevalence of hypertension were included for logistic regression analysis, and a nomogram model was established. The classification and regression tree (CART) algorithm of the decision tree model was used to build a classification tree model. Receiver operating characteristic (ROC) curve, calibration curve and decision curve analyses (DCA) were used to test the distinction, accuracy and clinical applicability of the two models. The results showed age, gender, BMI and prevalence of hypertension were all related to the occurrence of HUA. The area under the ROC curve (AUC) of the nomogram model was 0.806 and 0.791 in training set and validation set, respectively. The AUC of the classification tree model was 0.802 and 0.794 in the two sets, respectively, but were not statistically different. The calibration curves and DCAs of the two models performed well on accuracy and clinical practicality, which suggested these models may be suitable to predict HUA for rural setting. [ABSTRACT FROM AUTHOR]

The development of predictive maps for geothermal resources is fundamental for its exploration across Nigeria. In this study, spatial exploration data consisting of geology, geophysics and remote sensing was initially analysed using the Shannon entropy method to ascertain a correlation to known geothermal manifestation. The application of statistical index, frequency ratio and weight of evidence modelling was then used for integrating every predictive data for the generation of geothermal favourability maps. The receiver operating/area under curve (ROC/AUC) analysis was then employed to ascertain the prediction accuracy for all models. Basically, all spatial data displayed a significant statistical correlation with geothermal occurrence. The integration of these data suggests a high probability for geothermal manifestation within the central part of the study location. Accuracy assessment for all models using the ROC/AUC analysis suggests a high prediction capability (above 75%) for all models. Highest prediction accuracy was obtained from the frequency ratio (83.3%) followed by the statistical index model (81.3%) then the weight of evidence model (79.6%). Evidence from spatial and predictive analysis suggests geological data integration is highly efficient for geothermal exploration across the middle Benue trough. [ABSTRACT FROM AUTHOR]

Radiomic features hold potential to improve prediction of disease-free survival (DFS) in triple-negative breast cancer (TNBC) and may show better performance if developed from TNBC patients. We aimed to develop a radiomics score based on MRI features to estimate DFS in patients with TNBC. A total of 228 TNBC patients who underwent preoperative MRI and surgery between April 2012 and December 2016 were included. Patients were temporally divided into the training (n = 169) and validation (n = 59) set. Radiomic features of the tumor were extracted from T2-weighted and contrast-enhanced T1- weighted MRI. Then a radiomics score was constructed with the least absolute shrinkage and selection operator regression in the training set. Univariate and multivariate Cox proportional hazards models were used to determine what associations the radiomics score and clinicopathologic variables had with DFS. A combined clinicopathologic-radiomic (CCR) model was constructed based on multivariate Cox analysis. The incremental values of the radiomics score were evaluated by using the integrated area under the receiver operating characteristic curve (iAUC) and bootstrapping (n = 1000). The radiomics score, which consisted of 5 selected MRI features, was significantly associated with worse DFS in both the training and validation sets (p = 0.002, p = 0.033, respectively). In both the training and validation set, the radiomics score showed comparable performance with the clinicopathologic model. The CCR model demonstrated better performance than the clinicopathologic model in the training set (iAUC, 0.844; difference in iAUC, p < 0.001) and validation set (iAUC, 0.765, difference in iAUC, p < 0.001). In conclusion, MRI-based radiomic features can improve the prediction of DFS when integrated with clinicopathologic data in patients with TNBC. [ABSTRACT FROM AUTHOR]