• Jing Zhang, Wuyu Xiong, Jiajuan Yang, Ye Sang, Huiling Zhen, Caiwei Tan, Cuiyuan Huang, Jin She, Li Liu, Wenqiang Li, Wei Wang, Songlin Zhang, and Jian Yang.
• Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University & Yichang Central People's Hospital, Yichang, China; Central Laboratory, The First College of Clinical Medical Science, China Three Gorges University & Yichang Central People's Hospital, Yichang, China; Hubei Key Laboratory of Ischemic Cardiovascular Disease, Yichang, China; Hubei Provincial Clinical Research Center for Ischemic Cardiovascular Disease, Yichang, China.
• J. Thorac. Cardiovasc. Surg. 2024 Sep 18.

ObjectiveDevelop and validate an interpretable machine learning model to predict one-year mortality in Type A aortic dissection (TAAD) patients, improving risk classification and aiding clinical decision-making.MethodsWe enrolled 289 TAAD patients, dividing them into a training cohort (202 patients) and a validation cohort (87 patients). The LASSO method with ten-fold cross-validation identified eight key factors related to one-year mortality. The Treebag model's performance was assessed using accuracy, F1-Score ,Brier score ,AUC and AUC-PR with calibration and clinical utility evaluated through decision curves. SHAP analysis determined the most influential predictors.ResultsThe Treebag model outperformed others, achieving a Brier score of 0.128 and an AUC of 0.91. Key risk factors included older age and elevated white blood cell count (WBC), while higher systolic blood pressure (SBP), lymphocyte (Lym), carbon dioxide combining power (CO2-Bp), eosinophil (Eos), β-receptor blocker use, and surgical intervention were protective. A web-based application, TAAD One-Year Prognostic Risk Assessment Web, was developed for clinical use, accessible at https://taad-1year-mortality-predictor.streamlit.app/. This platform allows for the prediction of one-year mortality in TAAD patients based on the identified predictive factors, facilitating clinical decision-making and patient management.ConclusionsThe Treebag ML model effectively predicts one-year mortality in TAAD patients, stratifying risk profiles. Key factors for enhancing survival include surgical intervention, β-blocker administration, and management of SBP, Lym, CO2-Bp, Eos, and WBC levels, offering a valuable tool for improving patient outcomes.Copyright © 2024. Published by Elsevier Inc.

3 keywords...

hide…