Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alcaraz, Juan Miguel Lopez, Strodthoff, Nils
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915626222616576
author Alcaraz, Juan Miguel Lopez
Strodthoff, Nils
author_facet Alcaraz, Juan Miguel Lopez
Strodthoff, Nils
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning
Alcaraz, Juan Miguel Lopez
Strodthoff, Nils
Signal Processing
Machine Learning
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.
title Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2411.14886