Explainable and externally validated machine learning for neuropsychiatric diagnosis via electrocardiograms

2025-02-07

AI Summary

This study addresses the lack of non-invasive, generalizable auxiliary diagnostic tools for neuropsychiatric disorders—specifically Alzheimer’s disease (AD) and unspecified dementia. We propose an interpretable machine learning framework integrating electrocardiogram (ECG) signals with demographic features. The model employs XGBoost and random forests, with SHAP values ensuring clinical interpretability. It undergoes rigorous internal and external validation using two real-world, multi-center datasets: MIMIC-IV and ECG-View, while aligning predictions with ICD-10 clinical codes. To our knowledge, this is the first systematic, multi-center validation of ECG as a potential biomarker for neuropsychiatric disorders, revealing several novel ECG-based discriminative features. In external validation, the model achieves AUROC scores of 0.868 for AD and 0.862 for unspecified dementia, demonstrating strong generalizability and clinical discriminative performance.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Electrocardiogram (ECG) analysis has emerged as a promising tool for identifying physiological changes associated with neuropsychiatric conditions. The relationship between cardiovascular health and neuropsychiatric disorders suggests that ECG abnormalities could serve as valuable biomarkers for more efficient detection, therapy monitoring, and risk stratification. However, the potential of the ECG to accurately distinguish neuropsychiatric conditions, particularly among diverse patient populations, remains underexplored. This study utilized ECG markers and basic demographic data to predict neuropsychiatric conditions using machine learning models, with targets defined through ICD-10 codes. Both internal and external validation were performed using the MIMIC-IV and ECG-View datasets respectively. Performance was assessed using AUROC scores. To enhance model interpretability, Shapley values were applied to provide insights into the contributions of individual ECG features to the predictions. Significant predictive performance was observed for conditions within the neurological and psychiatric groups. For the neurological group, Alzheimer's disease (G30) achieved an internal AUROC of 0.813 (0.812-0.814) and an external AUROC of 0.868 (0.867-0.868). In the psychiatric group, unspecified dementia (F03) showed an internal AUROC of 0.849 (0.848-0.849) and an external AUROC of 0.862 (0.861-0.863). Discriminative features align with known ECG markers but also provide hints on potentially new markers. ECG offers significant promise for diagnosing and monitoring neuropsychiatric conditions, with robust predictive performance across internal and external cohorts. Future work should focus on addressing potential confounders, such as therapy-related cardiotoxicity, and expanding the scope of ECG applications, including personalized care and early intervention strategies.

Problem

• Predict neuropsychiatric conditions via ECG
• Enhance model interpretability using Shapley values
• Validate predictive performance across diverse datasets

Innovation

• Machine learning predicts neuropsychiatric conditions.
• ECG markers analyzed via Shapley values.
• Validated across diverse patient datasets.