Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features

TL;DR

This study demonstrates that ECG features, combined with demographic data, can reliably predict a wide range of both cardiac and non-cardiac diagnoses, expanding the diagnostic utility of ECG analysis beyond traditional cardiac conditions.

Contribution

The paper introduces a novel approach using machine learning to infer multiple non-cardiac diagnoses from ECG data, a previously underexplored area.

Findings

Achieved above 0.7 AUROC for 23 cardiac conditions

Achieved above 0.7 AUROC for 21 non-cardiac conditions

First systematic expansion of ECG-based diagnosis to non-cardiac conditions

Abstract

Ensuring timely and accurate diagnosis of medical conditions is paramount for effective patient care. Electrocardiogram (ECG) signals are fundamental for evaluating a patient's cardiac health and are readily available. Despite this, little attention has been given to the remarkable potential of ECG data in detecting non-cardiac conditions. In our study, we used publicly available datasets (MIMIC-IV-ECG-ICD and ECG-VIEW II) to investigate the feasibility of inferring general diagnostic conditions from ECG features. To this end, we trained a tree-based model (XGBoost) based on ECG features and basic demographic features to estimate a wide range of diagnoses, encompassing both cardiac and non-cardiac conditions. Our results demonstrate the reliability of estimating 23 cardiac as well as 21 non-cardiac conditions above 0.7 AUROC in a statistically significant manner across a wide range of physiological categories. Our findings underscore the predictive potential of ECG data in identifying well-known cardiac conditions. However, even more striking, this research represents a pioneering effort in systematically expanding the scope of ECG-based diagnosis to conditions not traditionally associated with the cardiac system.