Key result
XGBoost model integrating echo and demographic parameters predicts AF risk in hypertension with ~0.88 AUC.
Why the study?
Early identification of AF allows for timely interventions to reduce cardiovascular complications, prompting the development of a machine learning model integrating echocardiographic and demographic parameters for AF risk assessment in hypertension.
Does an XGBoost-based machine learning model integrating echocardiographic and demographic parameters improve atrial fibrillation risk assessment in hypertensive patients compared to existing scores?
Observational (n=48,571)
Yes
Does an XGBoost-based machine learning model integrating echocardiographic and demographic parameters improve atrial fibrillation risk assessment in hypertensive patients compared to existing scores?
An XGBoost machine learning model integrating echocardiographic and demographic data provides high discriminative accuracy for assessing atrial fibrillation risk in hypertensive patients.
Answers are grounded in this paper and cite their sources.
May support echocardiography-based ML for AF risk stratification in hypertension; leaves open prospective validation against existing scores.
BACKGROUND: Early identification of atrial fibrillation (AF) allows for timely interventions to reduce cardiovascular complications. Risk scores including C OBJECTIVE: We aimed to develop and validate a machine learning model integrating echocardiographic and demographic parameters to assess AF risk in hypertension. METHODS: This study included 48,571 hypertensive patients from eight hospitals. AF was diagnosed based on electrocardiogram or medical records. Patients from the Second Affiliated Hospital of Chongqing Medical University (n=40,811) were randomly divided into training and internal test sets (7:3), while patients from other hospitals (n=7,760) were split into early (2014-2019, n=3,648) and late (2020-2021, n=4,112) temporal test sets. Eight machine learning models integrating echocardiographic and demographic parameters were developed and optimized via 10-fold cross-validation in the training set. The best-performing model was selected in the internal test set and further evaluated across all test sets using area under the receiver operating characteristic curve (AUC), calibration, and clinical utility. RESULTS: An XGBoost-based model achieved an AUC of 0.875 in both internal test (95% confidence interval [CI]: 0.861-0.888) and early temporal test sets (95% CI: 0.850-0.899), and 0.886 (95% CI: 0.865-0.904) in the late temporal test set, significantly outperforming C CONCLUSION: An XGBoost-based model integrating echocardiographic and demographic parameters outperformed existing scores, offering a reliable tool for AF risk assessment in hypertension.
No takes yet. Share an insight, caveat, or question.
Tang et al. (2026) conducted an observational in Hypertension (n=48,571). XGBoost-based machine learning model vs. Existing risk scores was evaluated on Atrial fibrillation risk assessment (Area under the receiver operating characteristic curve) (AUC 0.875, 95% CI 0.861-0.888). An XGBoost-based model integrating echocardiographic and demographic parameters assessed atrial fibrillation risk in hypertension with an AUC of 0.875.
Synapse has enriched 10 related papers. Consider them for comparative context: