CardioLab: Laboratory Values Estimation from Electrocardiogram Features - An Exploratory Study

TL;DR

The paper addresses non-invasive estimation of laboratory-value abnormalities from ECG features and demographics. It uses per-lab-value binary classification with XGBoost on MIMIC-IV-ECG, aligning ECG with nearby vital signs (within 30 minutes) and laboratory results (within 60 minutes) and evaluating with AUROC and bootstrap CIs. Results demonstrate high discriminative performance across a broad set of labs (e.g., Albumin, Hemoglobin, NTproBNP), suggesting ECG-based estimation is feasible across organ systems. This exploratory study lays groundwork for faster, lower-cost patient monitoring and motivates external validation, waveform-based extensions, and explainable analyses.

Abstract

Laboratory value represents a cornerstone of medical diagnostics, but suffers from slow turnaround times, and high costs and only provides information about a single point in time. The continuous estimation of laboratory values from non-invasive data such as electrocardiogram (ECG) would therefore mark a significant frontier in healthcare monitoring. Despite its potential, this domain remains relatively underexplored. In this preliminary study, we used a publicly available dataset (MIMIC-IV-ECG) to investigate the feasibility of inferring laboratory values from ECG features and patient demographics using tree-based models (XGBoost). We define the prediction task as a binary problem of whether the lab value falls into low or high abnormalities. We assessed model performance with AUROC. Our findings demonstrate promising results in the estimation of laboratory values related to different organ systems. While further research and validation are warranted to fully assess the clinical utility and generalizability of the approach, our findings lay the groundwork for future investigations for laboratory value estimation using ECG data. Such advancements hold promise for revolutionizing predictive healthcare applications, offering faster, non-invasive, and more affordable means of patient monitoring.