融合多源数据与AI模型，提升肾病末期预测准确率
Enhancing End Stage Renal Disease Outcome Prediction: A Multi-Sourced Data-Driven Approach
- 整合临床与医保数据，用LSTM模型实现高精度预测
- 24个月观察窗口平衡早期预警与准确性，AUC达0.93
- 采用新eGFR公式降低种族偏差，适合临床决策支持
目标：通过机器学习（ML）和深度学习（DL）模型，结合多源临床与医保数据，利用不同观察窗口预测慢性肾病（CKD）进展至终末期肾病（ESRD），并借助可解释AI（XAI）提升结果可解释性、减少偏见。方法：使用2009–2018年间10,326名CKD患者的临床与医保数据，经预处理、队列识别与特征工程后，评估多种统计、ML与DL模型在五个不同观察窗口下的表现。采用特征重要性与Shapley值分析关键预测因子，检验模型稳健性、临床相关性、误分类误差及偏见问题。结果：综合数据模型优于单一来源模型，其中长短期记忆（LSTM）模型表现最佳，AUC达0.93，F1得分为0.65。24个月观察窗口为最优平衡点，兼顾早期发现与预测精度。2021年eGFR方程显著提升预测性能并降低种族偏见，尤其改善非裔患者预测效果。讨论：本研究在提升ESRD预测准确性、结果可解释性及偏见缓解方面具有重要意义，有望优化CKD与ESRD管理，支持精准早期干预，缩小医疗差距。结论：提出一种基于多源整合数据与AI/ML的可靠ESRD预测框架，助力临床决策与患者照护。未来将拓展数据融合，并探索该框架在其他慢性病中的应用。
原文摘要 · Abstract (English)
Objective: To improve prediction of Chronic Kidney Disease (CKD) progression to End Stage Renal Disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to an integrated clinical and claims dataset of varying observation windows, supported by explainable AI (XAI) to enhance interpretability and reduce bias. Materials and Methods: We utilized data about 10,326 CKD patients, combining their clinical and claims information from 2009 to 2018. Following data preprocessing, cohort identification, and feature engineering, we evaluated multiple statistical, ML and DL models using data extracted from five distinct observation windows. Feature importance and Shapley value analysis were employed to understand key predictors. Models were tested for robustness, clinical relevance, misclassification errors and bias issues. Results: Integrated data models outperformed those using single data sources, with the Long Short-Term Memory (LSTM) model achieving the highest AUC (0.93) and F1 score (0.65). A 24-month observation window was identified as optimal for balancing early detection and prediction accuracy. The 2021 eGFR equation improved prediction accuracy and reduced racial bias, notably for African American patients. Discussion: Improved ESRD prediction accuracy, results interpretability and bias mitigation strategies presented in this study have the potential to significantly enhance CKD and ESRD management, support targeted early interventions and reduce healthcare disparities. Conclusion: This study presents a robust framework for predicting ESRD outcomes in CKD patients, improving clinical decision-making and patient care through multi-sourced, integrated data and AI/ML methods. Future research will expand data integration and explore the application of this framework to other chronic diseases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。