Guardado en:
Detalles Bibliográficos
Autores principales: Kite, Thomas, Siam, Uzair Tahamid, Ayers, Brian, Houstis, Nicholas, Aguirre, Aaron D
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.16915
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913403091550208
author Kite, Thomas
Siam, Uzair Tahamid
Ayers, Brian
Houstis, Nicholas
Aguirre, Aaron D
author_facet Kite, Thomas
Siam, Uzair Tahamid
Ayers, Brian
Houstis, Nicholas
Aguirre, Aaron D
contents Machine learning (ML) applied to routine patient monitoring within intensive care units (ICUs) has the potential to improve care by providing clinicians with novel insights into each patient's health and expected response to interventions. This paper applies deep learning to a large volume of unlabeled electrocardiogram (ECG) telemetry signals, which are commonly used for continuous patient monitoring in hospitals but have important differences from the standard, single time-point 12-lead ECG used in many prior machine learning studies. We applied self-supervised learning to pretrain a spectrum of deep networks on approximately 147,000 hours of ECG telemetry data. Our approach leverages this dataset to train models that significantly improve performance on four distinct downstream tasks compared with direct supervised learning using labeled data. These pretrained models enable medically useful predictions and estimates in smaller patient cohorts that are typically limited by the scarcity of labels. Notably, we demonstrate that our pretrained networks can continuously annotate ECG telemetry signals, thereby providing monitoring capabilities that are often unavailable due to the requirement for specialized expertise and time-consuming professional annotations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unlocking Telemetry Potential: Self-Supervised Learning for Continuous Clinical Electrocardiogram Monitoring
Kite, Thomas
Siam, Uzair Tahamid
Ayers, Brian
Houstis, Nicholas
Aguirre, Aaron D
Signal Processing
Artificial Intelligence
Computers and Society
Machine Learning
Machine learning (ML) applied to routine patient monitoring within intensive care units (ICUs) has the potential to improve care by providing clinicians with novel insights into each patient's health and expected response to interventions. This paper applies deep learning to a large volume of unlabeled electrocardiogram (ECG) telemetry signals, which are commonly used for continuous patient monitoring in hospitals but have important differences from the standard, single time-point 12-lead ECG used in many prior machine learning studies. We applied self-supervised learning to pretrain a spectrum of deep networks on approximately 147,000 hours of ECG telemetry data. Our approach leverages this dataset to train models that significantly improve performance on four distinct downstream tasks compared with direct supervised learning using labeled data. These pretrained models enable medically useful predictions and estimates in smaller patient cohorts that are typically limited by the scarcity of labels. Notably, we demonstrate that our pretrained networks can continuously annotate ECG telemetry signals, thereby providing monitoring capabilities that are often unavailable due to the requirement for specialized expertise and time-consuming professional annotations.
title Unlocking Telemetry Potential: Self-Supervised Learning for Continuous Clinical Electrocardiogram Monitoring
topic Signal Processing
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2406.16915