Department of Pharmacy, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China.
Chengdu Second People's Hospital, Chengdu, China.
ESC Heart Fail. 2024 Oct;11(5):2648-2660. doi: 10.1002/ehf2.14855. Epub 2024 May 22.
There is a lack of tools for accurately identifying the risk of readmission for heart failure in elderly patients with arrhythmia. The aim of this study was to establish and compare the performance of the LACE [length of stay ('L'), acute (emergent) admission ('A'), Charlson comorbidity index ('C') and visits to the emergency department during the previous 6 months ('E')] index and machine learning in predicting 1 year readmission for heart failure in elderly patients with arrhythmia.
Elderly patients with arrhythmia who were hospitalized at Sichuan Provincial People's Hospital between 1 June 2018 and 31 May 2020 were enrolled. The LACE index was calculated for each patient, and the area under the receiver operating characteristic curve (AUROC) was calculated. Six machine learning algorithms, combined with three variable selection methods and clinically relevant features available at the time of hospital discharge, were used to develop machine learning models. AUROC and area under the precision-recall curve (AUPRC) were used to assess discrimination. Shapley additive explanations (SHAP) analysis was used to explain the contributions of the features.
A total of 523 patients were enrolled, and 108 patients experienced 1 year hospital readmission for heart failure. The AUROC of the LACE index was 0.5886. The complete machine learning model had the best predictive performance, with an AUROC of 0.7571 and an AUPRC of 0.4096. The most important predictors for 1 year readmission were educational level, total triiodothyronine (TT3), aspartate aminotransferase/alanine aminotransferase (AST/ALT), number of medications (NOM) and triglyceride (TG) level.
Compared with the LACE index, the machine learning model can accurately identify the risk of 1 year readmission for heart failure in elderly patients with arrhythmia.
目前缺乏准确识别老年心律失常患者心力衰竭再入院风险的工具。本研究旨在建立并比较 LACE（住院时间（L）、急性（紧急）入院（A）、Charlson 合并症指数（C）和前 6 个月就诊急诊次数（E））指数和机器学习在预测老年心律失常患者心力衰竭 1 年再入院风险中的表现。
纳入 2018 年 6 月 1 日至 2020 年 5 月 31 日在四川省人民医院住院的老年心律失常患者。为每位患者计算 LACE 指数，并计算其受试者工作特征曲线下面积（AUROC）。使用 6 种机器学习算法，结合 3 种变量选择方法和出院时临床相关特征，开发机器学习模型。使用 AUROC 和精度-召回曲线下面积（AUPRC）评估判别能力。使用 Shapley 加性解释（SHAP）分析解释特征的贡献。
共纳入 523 例患者，其中 108 例患者在 1 年内因心力衰竭再次住院。LACE 指数的 AUROC 为 0.5886。完整的机器学习模型具有最佳的预测性能，AUROC 为 0.7571，AUPRC 为 0.4096。1 年再入院的最重要预测因素是教育程度、总三碘甲状腺原氨酸（TT3）、天门冬氨酸氨基转移酶/丙氨酸氨基转移酶（AST/ALT）、用药种类（NOM）和甘油三酯（TG）水平。
与 LACE 指数相比，机器学习模型可以准确识别老年心律失常患者心力衰竭 1 年再入院的风险。
