# Abnormality prediction and forecasting of laboratory values from electrocardiogram signals using multimodal deep learning

## TL;DR

This study shows that combining ECG data with patient metadata can predict and forecast lab abnormalities, offering a non-invasive alternative to traditional testing.

## Contribution

A novel multimodal deep learning model for predicting and forecasting lab abnormalities using ECG and clinical data.

## Key findings

- The model achieved AUROCs above 0.70 for 24 lab values in abnormality prediction and forecasting.
- NTproBNP was best predicted with an AUROC > 0.90, while Hemoglobin, Albumin, and Hematocrit showed AUROCs > 0.85.
- ECG combined with clinical data can enable non-invasive monitoring of lab abnormalities.

## Abstract

This study investigates the feasibility of using electrocardiogram (ECG) data combined with basic patient metadata to estimate and monitor prompt laboratory abnormalities. We use the MIMIC-IV dataset to train multimodal deep learning models on ECG waveforms, demographics, biometrics, and vital signs. Our model is a structured state space classifier with late fusion for metadata. We frame the task as individual binary classifications per abnormality and evaluate performance using AUROC. The models achieve strong performance, with AUROCs above 0.70 for 24 lab values in abnormality prediction and up to 24 in abnormality forecasting, across cardiac, renal, hematological, metabolic, immunological, and coagulation categories. NTproBNP (≥ 353 pg/mL) is best predicted (AUROC > 0.90). Other values with AUROC > 0.85 include Hemoglobin (≥ 17.5 g/dL), Albumin (≥ 5.2 g/dL), and Hematocrit (≥ 51%). Our findings show ECG combined with clinical data enables prompt abnormality prediction and forecasting of lab abnormalities, offering a non-invasive, cost-effective alternative to traditional testing. This can support early intervention and enhanced patient monitoring. ECG and clinical data can help estimate and monitor abnormal lab values, potentially improving care while reducing reliance on invasive and costly procedures.