Related Experiment Video
Updated: May 30, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Explainable machine learning model for assessing health status in patients with comorbid coronary heart disease and
Jiqing Li1, Shuo Wu1, Jianhua Gu1
1Department of Emergency Medicine Qilu Hospital of Shandong University Jinan China; Shandong Provincial Clinical Research Center for Emergency and Critical Care Medicine Institute of Emergency and Critical Care Medicine of Shandong University Chest Pain Center Qilu Hospital of Shandong University Jinan China; Key Laboratory of Emergency and Critical Care Medicine of Shandong Province Key Laboratory of Cardiopulmonary-Cerebral Resuscitation Research of Shandong Province Shandong Provincial Engineering Laboratory for Emergency and Critical Care Medicine Shandong Key Laboratory: Magnetic Field-free Medicine & Functional Imaging Qilu Hospital of Shandong University Jinan China.
Insights
A new explainable machine learning model accurately assesses overall health in patients with coronary heart disease and depression. Key predictors include employment, physical activity, income, and age, aiding personalized care.
Area of Science:
- Health Informatics
- Machine Learning in Healthcare
- Cardiovascular Disease Research
Background:
- Coronary heart disease (CHD) and depression frequently co-occur, negatively impacting patient outcomes.
- A lack of comprehensive health status assessment tools exists for patients with comorbid CHD and depression.
- This study addresses the need for improved health status evaluation in this population.
Purpose of the Study:
- To develop and validate an explainable machine learning model for assessing overall health status.
- To identify key predictors of poor health in patients with comorbid CHD and depression.
- To provide a tool for personalized management strategies.
Main Methods:
- Utilized 2021-2022 Behavioral Risk Factor Surveillance System data.
- Developed and externally validated eleven machine learning models, including XGBoost.
- Employed SHapley Additive exPlanations (SHAP) for model interpretability.
- Assessed model performance using discrimination, calibration, and decision curve analysis.
Main Results:
- An optimized XGBoost model with eight features demonstrated balanced performance in derivation and validation cohorts.
- SHAP analysis identified employment status, physical activity, income, and age as significant predictors.
- The model achieved good discrimination (AUC ~0.71) and calibration.
Conclusions:
- An explainable machine learning model offers a novel approach to assessing health status in comorbid CHD and depression.
- The model provides valuable insights for personalized patient management.
- This tool can enhance clinical decision-making for this complex patient group.
Background:
Coronary heart disease (CHD) and depression frequently co-occur, significantly impacting patient outcomes. However, comprehensive health status assessment tools for this complex population are lacking. This study aimed to develop and validate an explainable machine learning model to evaluate overall health status in patients with comorbid CHD and depression.
Methods:
Utilizing data from the 2021-2022 Behavioral Risk Factor Surveillance System, we developed and externally validated machine learning models to predict overall health status, defined as having both poor physical and mental health for ≥ 14 days in the past 30 days. Eleven machine learning algorithms were evaluated, including artificial neural networks, support vector machines, and ensemble methods. The SHapley Additive exPlanations (SHAP) method was employed to enhance model interpretability. Model performance was assessed using discrimination, calibration, and decision curve analysis.
Results:
The study included 9,747 participants in the derivation cohort and 8,394 in the external validation cohort. Among the eleven algorithms evaluated, an optimized XGBoost model with eight key features demonstrated balanced performance. SHAP analysis revealed that employment status, physical activity, income, and age were the most influential predictors. The model maintained good discrimination (AUC 0.712, 95% CI 0.703-0.721 in derivation; AUC 0.711, 95% CI 0.701-0.721 in validation), calibration and clinical utility across both cohorts.
Conclusion:
Our explainable machine learning model provides a novel, comprehensive approach to assessing health status in patients with comorbid CHD and depression, offering valuable insights for personalized management strategies.
More Related Videos
06:55An Unpredictable Chronic Mild Stress Protocol for Instigating Depressive Symptoms, Behavioral Changes and Negative Health Outcomes in Rodents
Published on: December 2, 2015
05:19Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
Related Concept Videos
01:27Depressive Disorders: Etiology
Biological Factors in Depression
Biological predispositions significantly influence the risk of developing depressive disorders. Genetic studies highlight the role of variations in the serotonin transporter...
01:18Models of Health Promotion and Illness Prevention II
The agent-host-environment model states that disease results...
01:18Depression: Overview
01:25Models of Health Promotion and Illness Prevention I
The health belief model (HBM) attempts to predict health-related behavior in specific belief patterns. According to the HBM, a person's...
01:29Concepts of Health and Illness
01:28Human Genetics
The complex relationship between genetics and psychology is observable through common biological components such...