Restoration's Longevity in Endodontically Treated Teeth: A Machine Learning Survival Analysis From Randomised Clinical Trials.

Background This investigation delves into the potential application of data-driven survival modeling approaches for prognostic assessments of breast cancer survival. The primary objective is to evaluate and compare the ability of machine learning (ML) models and conventional survival analysis techniques, to identify consistent key predictors of breast cancer survival outcomes. Methods This study employs data-driven survival modeling approaches to predict breast cancer survival, including survival-specific methods such as the Cox Proportional Hazards (CPH) model, Random Survival Forests (RSF), and Cox Proportional Deep Neural Networks (DeepSurv), as well as machine learning models like Random Forests (RF), XGBoost, Support Vector Machines (SVM) with an RBF Kernel, and LightGBM. The dataset, sourced from the National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) program, comprises 4,024 women diagnosed with infiltrating duct and lobular carcinoma breast cancer between 2006 and 2010. To ensure interpretability across all models, the Shapley Additive Explanation (SHAP) method was applied to RSF, DeepSurv, Random Forests (RF), and XGBoost. This enabled the identification of key predictors influencing breast cancer survival, highlighting consistent factors across models while uncovering unique insights specific to each approach. Results The performance of survival-specific and ML models were evaluated using the Concordance index (C-index), Integrated Brier Score (IBS), mean accuracy, and mean AUC. The CPH model achieved a C-index of 0.71±0.015 and an IBS of 0.08±0.006, while RSF demonstrated slightly better discriminatory power with a C-index of 0.72±0.0117. DeepSurv performed comparably, with a C-index of 0.71±0.0095 and an IBS of 0.09±0.0008. Both Cox and RSF models achieved the lowest IBS (0.08), indicating accurate survival probability predictions over time. For ML models, RF achieved a mean AUC of 0.74±0.0021, and XGBoost with a mean AUC 0.69±0.0183, reflecting fair discriminatory ability but not accounting for censoring in survival data. SHAP analysis for the top-performing models highlighted the extent of lymph node involvement, Regional Node-Positive (number of affected lymph nodes), tumor grade (cell abnormality and growth rate), progesterone status, and age as key predictors of breast cancer survival outcomes. Conclusions While ML models like XGBoost and RF can effectively identify important predictors and patterns in breast cancer outcomes, survival-specific methods such as the Cox model, RSF, and DeepSurv provide essential capabilities for handling time-to-event data and censoring, making them more suitable for accurate survival predictions. The primary objective of including ML models in this analysis was to leverage their interpretability in identifying key variables alongside survival-specific models, rather than to directly compare their performance against survival models. By examining both ML and survival models, this research highlights the complementary strengths of each approach. This study contributes to the integration of artificial intelligence in healthcare, emphasizing the value of data-driven survival modeling techniques in supporting healthcare professionals with accurate, personalized, and actionable insights for high-risk patients. Together, these approaches enhance the precision of survival predictions, paving the way for more informed clinical decision-making and improved patient care.

BackgroundPatients with type 2 diabetes (T2D) have an increased risk of developing colorectal cancer (CRC) compared to the general population. Several studies have suggested that the co-occurrence of these two...

Use of Machine Learning to Predict Onset of NAFLD in an All-Comers Cohort—Development and Validation in 2 Large Asian Cohorts

Epigenetic Profiling and Machine Learning for Enhanced Risk Stratification in Pediatric Acute Lymphoblastic Leukemia

Introduction Ensuring equitable performance of sleep-related machine learning (ML) models is vital for public health and health equity. This research sought to determine the impact of sociodemographic and health disparities factors on the performance and characteristics of ML models designed to predict OSA treatment initiation. Methods Our data source was the All-Payer Claims Database (APCD) for the Wisconsin Health Information Organization (WHIO). Inclusion criteria included continuous insurance coverage for >12 months prior and >30 months after OSA diagnosis (defined by OCD code G47.33), and having undergone OSA diagnostic testing (defined by CPT codes). OSA treatment was defined based on durable medical equipment charges for PAP machines and supplies. Sociodemographic variables were extracted from APCD and included race, gender, age, and area socioeconomic deprivation (Area Deprivation Index; ADI). The ADI is a validated marker of health risk based on 17 health disparities factors ranking relative disadvantage across communities. Random Forest ML models were trained to predict OSA treatment initiation using sociodemographic variables and a medication history including 39,712 unique medications codified across 94 medication categories. Results Of N=6,026,463 subjects in the ACPD, n=154,821 underwent OSA diagnostic testing, and n=43,601 were diagnosed with OSA. 10-Fold Cross-Validation training-testing was applied to estimate sensitivity-specificity of ML models for predicting treatment initiation. Receiver operating characteristic curve area-under-the-curve (ROC-AUC) analyses were used to compare relative differences in predictive power of each variable. In ROC-AUC analysis of individual variables, the power for predicting OSA treatment were observed in relative rank order by age (0.568), race (0.547), ADI national-level (0.545), ADI state-level (0.544), gender (0.524), and medication history (0.516). In ROC-AUC analysis of combination variables, the highest ML model performance was observed in the combination of only three-variables (age-gender-race, 0.600), while the combination of all-variables showed an ROC-AUC value of (0.594), and the resulting performance difference was not statistically significant based on comparison of the ROC-AUC measures. Conclusion Demographic and health disparity factors may play an important role in future development of predictive AI/ML models. Population sleep health data represents an important resource to identify and bridge care gaps, reduce sleep health disparities, and achieve health equity. Support (if any)

BackgroundObesity is a prevalent and clinically significant complication among individuals with diabetes mellitus (DM), contributing to increased cardiovascular risk, metabolic burden, and reduced quality of life. Despite its high prevalence, the risk factors for obesity within this population remain incompletely understood. With the growing availability of large-scale health datasets and advancements in machine learning, there is an opportunity to improve risk stratification. This study aimed to identify key predictors of obesity and develop a machine learning-based predictive model for patients with T2DM using data from the National Health and Nutrition Examination Survey (NHANES).MethodsData from adults with diabetes were extracted from the NHANES 2007–2018 cycles. Participants were categorized into obese and non-obese groups based on BMI. Least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation was used to select relevant features. Subsequently, nine machine learning algorithms—including logistic regression, random forest (RF), radial support vector machine (RSVM), k-nearest neighbors (KNN), XGBoost, LightGBM, decision tree (DT), elastic net regression (ENet), and multilayer perceptron (MLP)—were employed to construct predictive models. Model performance was evaluated based on area under the ROC curve (AUC), calibration curves, Brier score, and decision curve analysis (DCA). The best-performing model was visualized using a nomogram to enhance clinical applicability.ResultsA total of 3,794 participants with type 2 diabetes were included in the analysis, of whom 57.0% were classified as obese. LASSO regression identified 19 key variables associated with obesity. Among the nine machine learning models evaluated, the logistic regression model demonstrated the best overall performance, with the lowest Brier score. It also showed good discrimination (AUC = 0.751 in the training set and 0.781 in the test set), favorable calibration, and consistent clinical utility based on decision curve analysis (DCA). A nomogram was constructed based on the logistic regression model to facilitate individualized risk prediction, with total points corresponding to predicted probabilities of obesity.ConclusionObesity remains highly prevalent among individuals with type 2 diabetes. Our findings highlight key clinical features associated with obesity risk and provide a practical tool to aid in early identification and individualized management of high-risk patients.

Development and validation of a machine learning-based prediction model for in-ICU mortality in severe pneumonia: A dual-center retrospective study.

e13647 Background: Sarculator, a Cox model-based nomogram, has been widely used for survival predictions in patients with extremity soft tissue sarcomas (eSTS), demonstrating user-friendliness and reliability. With growing interest in machine learning (ML), this study investigates whether, given the Sarculator prognostic variables, these more complex approaches offer meaningful improvements. Methods: Data from 3,748 patients with eSTS from four international cohorts were used, including the Sarculator’s development cohort (1,452 patients, Milan, Italy) and the three original external validation cohorts (Toronto, Canada; Villejuif, France; London, UK). Predictions were compared in terms of discrimination (C-index, the higher the better), and calibration (plots; 5- and 10-year Brier score, the lower the better. Four ML models — Extreme Gradient Boosting (XGBoost), Model-Based Boosting (MBoost), Random Survival Forests (RSF), and Optimal Survival Trees (OST)—were benchmarked against Sarculator, all including the same Sarculator covariates. A hybrid SuperLearner, which combined predictions from the Sarculator Cox model and the best-performing ML model, was also evaluated. Results: Sarculator Cox model consistently performed well across the four cohorts (C-index: 0.698–0.775) with reliable calibration and low Brier scores. ML models, particularly XGBoost, demonstrated slightly better calibration but poorer generalizability in external cohorts. MBoost and RSF exhibited calibration-discrimination trade-offs, while OST underperformed compared to all the other models. The SuperLearner, integrating predictions from the Cox and XGBoost models, marginally improved calibration but provided limited additional value compared to the Cox model. Conclusions: Sarculator’s robust performance across development and validation cohorts highlights that traditional Cox models remain clinically valuable. The added complexity of ML approaches does not necessarily result in superior prediction accuracy. Importantly, Cox models retain their interpretability, essential for clinical application, whereas ML models required complex tools for explanation. In the context of clinical-based variables, clinicians might be more likely to prioritize models offering simplicity and reliability over less interpretable, marginally improved alternatives. Model performance across development and validation cohorts. Metric Cox model XGBoost MBoost RSF OST SuperLearner C-index (Development) 0.767 0.806 0.792 0.765 0.755 0.781 C-index (Mean, Validation) 0.745 0.726 0.727 0.667 0.693 0.746 5y Brier Score (Development) 0.478 0.478 0.475 0.523 0.491 0.475 5y Brier Score (Mean, Validation) 0.476 0.434 0.560 0.476 0.464 0.467 10y Brier Score (Development) 0.503 0.497 0.489 0.561 0.519 0.500 10y Brier Score (Mean, Validation) 0.480 0.450 0.510 0.457 0.470 0.470

Deep Phenotyping and Prediction of Long-term Cardiovascular Disease: Optimized by Machine Learning.

Background: This study aims to develop a machine learning (ML) algorithm to predict survival probabilities for patients with epithelial ovarian cancer (EOC). Research design and methods Data were obtained from the SEER database for women diagnosed with EOC between 2004 and 2020. Clinical features, treatment regimens and overall survival (OS) were analyzed. Cox regression was conducted to identify prognostic factors associated with EOC. We employed 5-fold cross-validation to improve the accuracy of the model. Random Survival Forest (RSF), Gradient Boosting Survival Analysis (GBSA) and Support Vector Machine (SVM) were used to develop ML models, then compared with the Cox model. The predictive performance of these models was assessed using AUC, concordance index (C-index), and Brier scores. Results A total of 12,949 EOC patients were selected from the SEER database. We identified 14 independent prognostic factors for OS and constructed predictive models. The GBSA model demonstrated superior AUC, C-index, and Brier scores across different time points, outperforming the Cox model. SHAP analysis showed that FIGO stage, grade, and lymph node dissection were the most important features in the GBSA model. Conclusions The GBSA model outperforms traditional methods in survival prediction, offering a valuable tool for clinicians to make informed decisions about patient prognosis.

Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses. In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35–60) and 48 (IQR 38–57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ± 0.01, 0.88 ± 0.01 and 0.85 ± 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models. Further prospective evaluation of the classification performance of this ML model against existing methods is required.

1638 Background: Adults with cancer in the U.S. face an elevated mortality risk compared to the general population, with social risk factors playing a critical role – particularly among those with comorbidities. However, traditional mortality risk prediction models often focus on treatment exposures and basic demographic factors, overlooking social risk factors. We aim to develop a machine learning (ML) model that integrates comprehensive social risk factors with traditional predictors to predict overall survival for adults with cancer in the U.S. Methods: We analyzed data from 6,181 nationally representative adults diagnosed with cancer from the National Health Interview Survey (NHIS; 2013-2014). A total of 74 risk factors, including basic demographics (e.g., age at the survey, sex, marital status, body mass index [BMI]), personal and household socioeconomic status (SES; e.g., education, food insecurity), lifestyle, social support, and health status (e.g., chronic health conditions [CHCs], disability), were included in modeling. The primary endpoint was 5-year overall survival from the survey completion date, with secondary endpoints of 1- and 2-year survival. Death from any cause after the survey was defined as an event, and subjects were censored 5 years post-survey. The sample was randomly split into 70% training and 30% testing. A random survival forest (RSF) model predicted survival. The time-dependent area under the receiver operating characteristic (AUROC) curve and the Brier score (BS) assessed the model performance. Both AUROC and BS range from 0 to 1, with higher AUROC for higher accuracy (discrimination) and lower BS for better alignment between predicted and observed risk (calibration). The Shapley additive explanations (SHAP) values were used to interpret variable importance in the established RSF model. Results: The mean age of subjects during the survey was 65.6±13.8 years, and 40.2% were male. For the established RSF model, the AUROC (mean ± standard deviation) for predicting 1-, 2-, and 5-year survival was 0.795 ± 0.026, 0.810 ± 0.018, and 0.831 ± 0.011, respectively, reflecting high and improved predictive accuracy over time. The BS for 1-, 2-, and 5-year survival was 0.039 ± 0.004, 0.065 ± 0.005, and 0.119 ± 0.005, respectively, indicating excellent calibration. The top five variables ranked by SHAP values include age at the survey (0.048), use of special equipment due to health problems (0.029), employment status (0.020), number of CHCs (0.016), and BMI (0.015). Conclusions: By integrating social risk factors with traditional risk predictors, we developed an ML model that predicts overall survival with high accuracy and excellent calibration for adults with cancer in the U.S. Identifying key risk social factors enables targeted interventions, potentially improving health outcomes and management for the adult cancer population.

Prediction of Outcomes after Radiotherapy for Hepatocellular Carcinoma Independently Validated Using Multi-Institutional Data

BackgroundsWe aimed to develop and validate machine learning (ML) models for 30-day stroke mortality for mortality risk stratification and as benchmarking models for quality improvement in stroke care.MethodsData from the UK Sentinel Stroke National Audit Program between 2013 to 2019 were used. Models were developed using XGBoost, Logistic Regression (LR), LR with elastic net with/without interaction terms using 80% randomly selected admissions from 2013 to 2018, validated on the 20% remaining admissions, and temporally validated on 2019 admissions. The models were developed with 30 variables. A reference model was developed using LR and 4 variables. Performances of all models was evaluated in terms of discrimination, calibration, reclassification, Brier scores and Decision-curves.ResultsIn total, 488,497 stroke patients with a 12.3% 30-day mortality rate were included in the analysis. In 2019 temporal validation set, XGBoost model obtained the lowest Brier score (0.069 (95% CI: 0.068–0.071)) and the highest area under the ROC curve (AUC) (0.895 (95% CI: 0.891–0.900)) which outperformed LR reference model by 0.04 AUC (p < 0.001) and LR with elastic net and interaction term model by 0.003 AUC (p < 0.001). All models were perfectly calibrated for low (< 5%) and moderate risk groups (5–15%) and ≈1% underestimation for high-risk groups (> 15%). The XGBoost model reclassified 1648 (8.1%) low-risk cases by the LR reference model as being moderate or high-risk and gained the most net benefit in decision curve analysis.ConclusionsAll models with 30 variables are potentially useful as benchmarking models in stroke-care quality improvement with ML slightly outperforming others.

The study aimed to develop an interpretable machine learning (ML) model to assess and stratify the risk of long-term major adverse cardiovascular events (MACEs) in patients with premature myocardial infarction (PMI) and to analyze the key variables affecting prognosis. This prospective study consecutively included patients (male ≤50 years, female ≤55 years) diagnosed with acute myocardial infarction (AMI) at Tianjin Chest Hospital between January 2017 and December 2022. The study endpoint was the occurrence of MACEs during the follow-up period, which was defined as cardiac death, nonfatal stroke, readmission for heart failure, nonfatal recurrent myocardial infarction, and unplanned coronary revascularization. Four machine learning models were built: COX proportional hazards model (COX) regression, random survival forest (RSF), extreme gradient boosting (XGBoost), and DeepSurv. Models were evaluated using concordance index (C-index), Brier score, and decision curve analysis to select the best model for prediction and risk stratification. A total of 1202 patients with PMI were included, with a median follow-up of 26 months, and MACEs occurred in 200 (16.6%) patients. The RSF model demonstrated the best predictive performance (C-index, 0.815; Brier, 0.125) and could effectively discriminate between high- and low-risk patients. The Kaplan-Meier curve demonstrated that patients categorized as low risk showed a better prognosis (p < 0.0001). The prognostic model constructed based on RSF can accurately assess and stratify the risk of long-term MACEs in PMI patients. This can help clinicians make more targeted decisions and treatments, thus delaying and reducing the occurrence of poor prognoses.