Development and validation of an interpretable machine learning model for predicting atrial fibrillation risk in middle-aged and older patients with coronary heart disease
This data-driven, interpretable XGBoost model enables individualized AF risk assessment in middle-aged and older CHD patients, offering a practical tool for early identification and targeted intervention in clinical practice.
Abstract
Background Coronary heart disease (CHD) and atrial fibrillation (AF) frequently coexist, yet existing risk stratification tools inadequately capture the nonlinear, multidimensional determinants of AF in middle-aged and older CHD patients. This study aimed to develop and validate an interpretable machine learning-based prediction model leveraging electronic medical records (EMR) data. Methods A retrospective cohort of 47,617 hospitalized CHD patients (January 2020–December 2025) was analyzed. After random forest imputation and least absolute shrinkage and selection operator (LASSO) screening, eight machine learning algorithms were trained and validated (7:3 split). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA), with Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) applied for interpretability. Results LASSO regression identified 16 predictors, with pulse rate, total cholesterol, systolic blood pressure, creatinine, and triglycerides emerging as the top five contributors. XGBoost outperformed competing models, achieving AUCs of 0.867 (95% CI: 0.862–0.872) in the training set and 0.813 (95% CI: 0.802–0.823) in the validation set. Restricted cubic spline analysis revealed nonlinear dose–response relationships for multiple continuous variables. SHAP visualization quantified individualized feature contributions. LIME explanations demonstrated consistent local feature contributions at the individual level. Conclusions This data-driven, interpretable XGBoost model enables individualized AF risk assessment in middle-aged and older CHD patients, offering a practical tool for early identification and targeted intervention in clinical practice.
Purpose This study aimed to develop and validate an interpretable machine learning model to predict the 1- to 3-year risk of cardiovascular events in breast cancer patients by integrating baseline and treatment variables, while preliminarily investigating the potential association between short-term cardiac function decline and long-term adverse cardiovascular events. Methods We analyzed electronic medical records from 31,878 breast cancer patients. A composite cardiovascular event outcome was used. Predictors were selected via a two-step process: removing highly correlated variables (|r|≥0.7) and applying LASSO regression with 10-fold cross-validation, which refined 62 initial variables down to 18. Five models were built and compared using the area under the receiver operating characteristic curve (AUC-ROC). The optimal model was interpreted using SHapley Additive exPlanations (SHAP). Results Among 31,878 breast cancer patients, 3,960 (12.4%) experienced cardiovascular events. The XGBoost model demonstrated the best overall discriminative performance (AUC = 0.790). SHAP analysis identified endocrine therapy, anemia management therapy, and history of cerebrovascular disease as the top three predictors. Crucially, short-term decline in cardiac function was also selected as a significant predictor, supporting its role as a precursor to long-term events. Model robustness was confirmed via sensitivity analysis.
Luxin Wang, Rui Yan, Xinyu Zhu et al.· Frontiers in Oncology· 0 citations
Background Patients with coexisting type 2 diabetes mellitus (T2DM) and hypertension (HTN) face a synergistically elevated risk of major adverse cardiovascular events (MACE). Evidence for prediction models developed specifically in established T2DM-HTN comorbidity population remains limited. Objective To methodologically explore and preliminarily evaluate an interpretable machine learning framework for 1-year MACE prediction in hospitalized patients with coexisting T2DM and HTN using routine clinical data. Methods This retrospective study included 1,054 hospitalized patients with T2DM and HTN, of whom 249 (23.6%) experienced MACE during 1-year follow-up. The dataset was randomly divided into training (60%), validation (20%), and independent test (20%) cohorts using stratified sampling. LASSO regression was applied for feature selection from 69 clinical variables. Four algorithms, including logistic regression, random forest, support vector machine, and XGBoost, were developed and compared. Model performance was assessed using discrimination, calibration, and clinical utility metrics. SHapley Additive exPlanations (SHAP) were used to interpret the final model. Results LASSO identified six stable predictors: HbA1c, age, hypertension duration, cystatin C (CysC), T2DM duration, and carotid intima-media thickness (CIMT). Sex was additionally incorporated based on clinical relevance. Multivariable logistic regression showed that HbA1c, age, hypertension duration, T2DM duration, CysC, and CIMT were associated with 1-year MACE risk, whereas sex was not statistically significant. Logistic regression showed the best relative balance between discrimination, calibration, and simplicity on the validation set, although learning curves indicated limited incremental improvement with increasing training sample size. After isotonic regression recalibration, the final logistic regression model achieved an ROC-AUC of 0.828, a PR-AUC of 0.656, and a Brier score of 0.116 on the independent test set. Decision curve analysis indicated potential clinical net benefit. SHAP linked model predictions to glycemic burden, aging, cumulative disease exposure, renal-related risk, and subclinical atherosclerosis. Conclusion An interpretable logistic regression model based on seven routine clinical variables showed relatively good internal performance for predicting 1-year composite MACE risk in hospitalized patients with coexisting T2DM and HTN. CysC provided additional prognostic information beyond its conventional role as a renal filtration marker, although this association should be interpreted as prognostic rather than causal. External validation is required before the model can be considered for clinical decision support.
Juan Lv, Xi-Rui Wang, Zhengyi Zhang· Frontiers in Medicine· 0 citations
Type 2 diabetes mellitus (T2DM) is a prevalent chronic condition, particularly in the elderly, and is associated with an increased risk of cognitive decline, including mild cognitive impairment (MCI). This study aimed to develop and validate an interpretable machine learning (IML) model to predict MCI in elderly T2DM patients using routine clinical data. A retrospective cohort of 923 elderly T2DM patients (≥ 60 years) was analyzed, with data collected from January 2021 to January 2025. Key MCI predictors were selected using a two-stage feature selection process involving Boruta and least absolute shrinkage and selection operator (LASSO). Six machine learning (ML) algorithms-logistic regression (LR), extreme gradient boosting (XGBoost), support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and decision tree (DT)-were trained and evaluated. SHapley Additive exPlanations (SHAP) were employed to interpret model predictions and provide insights into feature importance. Among 923 participants, 424 (45.9%) had MCI. Baseline characteristics were comparable between the training and validation sets, with similar MCI prevalence (46.1% vs. 45.5%). Seven predictors were consistently selected: age, years of education, duration of diabetes, regular physical activity, cerebrovascular disease, glycated hemoglobin (HbA1c), and fasting plasma glucose (FPG). Among the six models, the RF model demonstrated the best overall performance, achieving an AUC of 0.842 in the validation set, with favorable discrimination, calibration, and net clinical benefit. SHAP analysis identified duration of diabetes as the most influential predictor, followed by HbA1c and FPG, emphasizing the role of both cumulative and current glycemic burden. An interpretable RF-based model using routine clinical data effectively predicted MCI in elderly patients with T2DM and provided clinically intuitive explanations of risk drivers. This approach may support risk-stratified cognitive screening and individualized management; external multicenter validation and prospective evaluation are warranted.
Beibei Dong, Le Wang, Wen-Wen Shi et al.· Scientific Reports· 0 citations
Venous thromboembolism (VTE) is a leading preventable cause of in-hospital mortality in older adults, yet early risk stratification remains a key clinical challenge. This study aimed to develop and internally validate an explainable machine learning model for incident VTE prediction in hospitalized older adult patients. We enrolled 28,231 patients aged ≥65 years admitted between January 2023 and December 2024, excluding those with VTE on admission. The primary endpoint was imaging-confirmed incident in-hospital VTE. Patients were split into training/test sets (7:3) via outcome-stratified sampling. Missing data were handled with multivariate imputation by chained equations imputation (training set only). Five machine learning models were constructed with 10-fold cross-validation and hyperparameter tuning, evaluated by pooled area under the curve (AUC), calibration curves, and decision curve analysis, with SHAP for model interpretation. 1797 (6.38%) incident VTE events were recorded. XGBoost showed optimal performance, with a training AUC of 0.753 and a test AUC of 0.712, favorable calibration, and stable clinical net benefit. Top predictors included diabetic nephropathy, triglycerides, great saphenous vein varicosity, fatty liver, cerebrovascular accident and age. We developed and validated an explainable XGBoost model for VTE risk prediction in older inpatients, enabling early risk stratification to support individualized thromboprophylaxis. Multicenter prospective external validation is warranted for clinical implementation.
Si-Yu Zhou, Zhen-Rui Tang, Y. Tan et al.· Medicine· 0 citations
Background Cerebral small vessel disease (CSVD) is a common, clinically significant vascular disorder that frequently leads to cognitive impairment, dementia, and poor overall prognosis. Owing to its complex hemodynamic characteristics and multifactorial pathophysiology, early identification of individuals at high risk for CSVD remains a clinical challenge. This study aimed to develop and validate an interpretable machine learning (ML) model for predicting the occurrence of CSVD. Methods We retrospectively enrolled 1,640 adult patients treated at the Fifth Affiliated Hospital of Xinjiang Medical University between September 2019 and December 2024. Twenty-three candidate variables (demographics, vitals, biomarkers, comorbidities) were evaluated. Feature selection was performed using least absolute shrinkage and selection operator (LASSO) regression, followed by stepwise backward elimination in multivariable logistic regression. Six supervised ML algorithms (DT, KNN, LR, LightGBM, XGBoost, SVM) were compared. Performance was assessed using ROC curves, calibration plots, and decision curve analysis (DCA). The optimal model was interpreted using SHapley Additive exPlanations (SHAP), and a bedside clinical nomogram was constructed. Results Ten independent predictors were identified: blood glucose, history of hypertension, systolic blood pressure, age, triglycerides, history of stroke, cystatin C, C-reactive protein, homocysteine, and body mass index. Among all models, XGBoost demonstrated the best performance, with an AUC of 0.968 in the training cohort and 0.938 in the validation cohort. Calibration plots and DCA confirmed its clinical utility. The derived nomogram demonstrated strong prognostic discrimination (p < 0.0001). The XGBoost model achieved an accuracy of 88.0%, sensitivity of 80.9%, specificity of 93.8%, and an F1 score of 0.86, corresponding to a 5.4-percentage-point gain in AUC over logistic regression. Ten-fold cross-validation confirmed this ranking, with a mean AUC of 0.934 ± 0.016. Conclusions We validated an interpretable XGBoost-based ML model that facilitates early risk stratification and targeted interventions for CSVD. Because the model relies only on routinely collected, low-cost variables and open-source software, it is readily transferable to resource-limited settings; future work will focus on prospective, multicentre external validation and on embedding the nomogram into electronic-health-record decision support.
Xi Zhu, Xuhui Liu, Xujie Wang et al.· Frontiers in Neurology· 0 citations
Background Coronary heart disease (CHD) remains a leading cause of morbidity and mortality worldwide. Early identification of high-risk hypertensive patients is crucial for preventing cardiovascular events. While traditional risk scores rely on static clinical measurements, 24-h ambulatory blood pressure monitoring (ABPM)-derived time in target range (TTR) captures dynamic blood pressure control patterns that may improve risk stratification. Machine learning methods, particularly deep neural networks, offer an enhanced capability to model complex non-linear relationships in high-dimensional clinical data, compared with conventional statistical approaches. Methods This single-center retrospective cohort study included 1,026 patients admitted between January 2023 and December 2024, with 718 patients allocated to model development and 308 to internal validation. A deep neural network model with three hidden layers was developed and compared against eight conventional machine learning algorithms (logistic regression, naïve Bayes, k-nearest neighbors, random forest, support vector machine, XGBoost, LightGBM, and CatBoost). Thirty-two variables spanning demographics, clinical data, laboratory results, echocardiographic measures, and blood pressure indices were evaluated. Continuous variables were discretized into quartile-based categories to enhance clinical interpretability. Feature selection employed a two-step process combining the Boruta algorithm and least absolute shrinkage and selection operator (LASSO) regression, with variance inflation factor analysis confirming the absence of collinearity. Model selection prioritized balanced performance across discrimination (AUC), calibration (Brier score), and clinical utility (decision curve analysis) in the independent validation cohort. Interpretability was evaluated using SHAP (SHapley Additive exPlanations) values. Results The deep neural network model achieved optimal balanced performance with an AUC of 0.822 (95% CI: 0.793–0.850) in the training cohort and 0.796 (95% CI: 0.749–0.846) in the validation cohort, accompanied by the lowest Brier score (0.172), indicating superior calibration. Nine predictors were retained: diabetes mellitus, mean systolic blood pressure, time in target range of systolic blood pressure, left atrial diameter, left ventricular end-systolic diameter, left ventricular ejection fraction, use of antihypertensive medications, calcium channel blockers, and β-blockers. SHAP analysis identified TTR and blood pressure control parameters as the primary drivers of model predictions. Conclusion The developed deep neural network model enables early identification of high-risk CHD patients with hypertension through interpretable, routinely available clinical variables. Prospective multicenter external validation is warranted to confirm its generalizability across diverse populations and clinical settings.
Li Wang, Ji Song, Yingzhu Xie et al.· Frontiers in Medicine· 0 citations