Related Experiment Video
Updated: Jul 10, 2025
Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine
Chenggong Xu1, Hongxia Li1, Jianping Yang2
1The First Affiliated Hospital of Kunming Medical University, Kunming, China.
Insights
Machine learning models effectively predict 3-year mortality in chronic heart failure (CHF) patients. Interpretable AI, using SHAP values and permutation importance, identifies key risk factors like hospitalizations and age for personalized prognosis.
Area of Science:
- Cardiovascular Medicine
- Artificial Intelligence in Healthcare
- Medical Informatics
Background:
- Chronic heart failure (CHF) poses a significant challenge for long-term patient outcomes.
- Accurate prediction of all-cause mortality in CHF patients is crucial for effective management.
- Existing risk stratification models may lack precision and interpretability.
Purpose of the Study:
- To evaluate the performance of various machine learning (ML) models in predicting 3-year all-cause mortality in CHF patients.
- To develop an interpretable ML model for understanding and explaining mortality risk factors.
- To identify key clinical and laboratory variables associated with long-term mortality in CHF.
Main Methods:
- Utilized a dataset of hospitalized CHF patients (cardiac function class III-IV) from 2017-2019.
- Compared six ML models: logistic regression, naive Bayes, random forest, extreme gradient boost, K-nearest neighbor, and decision tree.
- Employed interpretable ML techniques, including SHAP values, permutation importance, and partial dependence plots (PDP).
Main Results:
- The Random Forest classifier demonstrated optimal performance for this dataset.
- Key predictors of 3-year all-cause mortality identified include: number of hospitalizations, age, glomerular filtration rate, BNP, NYHA class, lymphocyte count, serum albumin, hemoglobin, total cholesterol, and pulmonary artery systolic pressure.
- Interpretable methods provided insights into the contribution of each factor to mortality risk.
Conclusions:
- ML-based cardiovascular risk models can accurately assess and stratify 3-year mortality risk in CHF patients.
- Combining ML with interpretable techniques (SHAP, permutation importance, PDP) enhances individual risk prediction.
- These approaches offer clinicians intuitive understanding of model components and aid in personalized risk assessment.
Background:
The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure.
Methods:
The data in this paper were selected from patients with chronic heart failure who were hospitalized at the First Affiliated Hospital of Kunming Medical University, from 2017 to 2019 with cardiac function class III-IV. The dataset was explored using six different machine learning models, including logistic regression, naive Bayes, random forest classifier, extreme gradient boost, K-nearest neighbor, and decision tree. Finally, interpretable methods based on machine learning, such as SHAP value, permutation importance, and partial dependence plots, were used to estimate the 3-year all-cause mortality risk and produce individual interpretations of the model's conclusions.
Result:
In this paper, random forest was identified as the optimal aools lgorithm for this dataset. We also incorporated relevant machine learning interpretable tand techniques to improve disease prognosis, including permutation importance, PDP plots and SHAP values for analysis. From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure.
Conclusion:
The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. Machine learning in combination with permutation importance, PDP plots, and the SHAP value could offer a clear explanation of individual risk prediction and give doctors an intuitive knowledge of the functions of important model components.
More Related Videos
05:15Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
