Comparison of Machine Learning and Conventional Statistical Modeling for Predicting Readmission Following Acute Heart Failure Hospitalization

机器学习与传统统计模型预测急性心力衰竭住院后再入院的比较

• 批准号: 495410
• 负责人: Abdul-Samad Karem
• 金额: $ 0.11万
• 依托单位: University Health Network (Toronto)
• 依托单位国家: 加拿大
• 财政年份: 2023
• 资助国家: 加拿大
• 起止时间: 2023-09-01 至 2024-09-01
• 项目状态: 已结题
• 来源: https://webapps.cihr-irsc.gc.ca/decisions/p/project_details.html?applId=495410&lang=en
• 关键词: Acute Heart Failure; Machine Learning; Readmission; Statistical Modeling; Acute Heart Failure; Machine Learning; Readmission; Statistical Modeling

Heart Failure (HF) is a major cause of global hospitalizations. Presently, there are no reliable models for predicting HF patients at risk of hospitalization. Machine learning has shown promise in this area, yet its clinical effectiveness remains unclear.

心力衰竭（HF）是全球住院的主要原因。目前，没有可靠的模型来预测有住院风险的HF患者。机器学习在这一领域表现出了希望，但其临床有效性尚不清楚。