Predicting 1 year readmission for heart failure: A comparative study of machine learning and the LACE index
Xuewu Song1, Yitong Tong2, Feng Xian3
1Department of Pharmacy, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China.
Insights
Machine learning models accurately predict 1-year heart failure readmission risk in elderly patients with arrhythmia, outperforming the LACE index. Key predictors include education, TT3, AST/ALT, NOM, and TG levels.
Area of Science:
- Cardiology
- Medical Informatics
- Geriatrics
Background:
- Heart failure readmission in elderly patients with arrhythmia poses a significant clinical challenge.
- Existing tools like the LACE index have limitations in accurately predicting this risk.
- Novel approaches are needed to improve risk stratification for this vulnerable population.
Purpose of the Study:
- To develop and compare the predictive performance of machine learning models against the LACE index for 1-year heart failure readmission in elderly patients with arrhythmia.
- To identify key clinical features contributing to readmission risk.
Main Methods:
- A cohort of elderly patients with arrhythmia hospitalized between June 2018 and May 2020 was analyzed.
- The LACE index was calculated, and its predictive accuracy was assessed using AUROC.
- Six machine learning algorithms were developed using discharge data, with performance evaluated by AUROC and AUPRC. SHAP analysis was employed for feature interpretation.
Main Results:
- The study included 523 patients, with 108 experiencing 1-year heart failure readmission.
- The LACE index demonstrated limited predictive ability (AUROC: 0.5886).
- The complete machine learning model achieved superior prediction (AUROC: 0.7571, AUPRC: 0.4096), identifying educational level, TT3, AST/ALT, NOM, and TG as significant predictors.
Conclusions:
- Machine learning models significantly outperform the LACE index in predicting 1-year heart failure readmission for elderly patients with arrhythmia.
- These models offer a more accurate tool for identifying high-risk individuals.
- The identified predictors provide insights for targeted interventions to reduce readmission rates.
Aims:
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.
Methods:
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.
Results:
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.
Conclusions:
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.
More Related Videos
09:20Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
Published on: February 13, 2021
04:05Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
Related Concept Videos
01:27Heart Failure I: Introduction
01:30Heart Failure IV: Classification and Diagnostic Evaluation