Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels

Brian Chen, Golara Javadi, Amoon Jamzad, Alexander Hamilton, Stephanie Sibley, Purang Abolmaesumi, David Maslove, Parvin Mousavi
Proceedings of the 6th Machine Learning for Healthcare Conference, PMLR 149:176-195, 2021.

Abstract

State of the art techniques for creating ML models in healthcare often require large quantities of clean, labelled data. However, many healthcare organizations lack the capacity to generate the large-scale annotations required to create and validate reliable labels. In this paper, we demonstrate how raw data from an information-rich area of care can be exploited without the need for mass manual annotation via the use of weak labels. We evaluate the AF Detection with Weak Labels proposed framework on telemetry data from the intensive care unit for application of atrial fibrillation (AF) detection. We generate an in-house dataset of over 60,000 ECG segments with weak labels, derived from a model trained on publicly available data. We then show that building a deep learning model based on these weakly generated labels can significantly improve (more than 30%) the performance of AF detection in comparison with only using limited expert-annotated ground truth labels. We further demonstrate how weakly supervised learning techniques can be used to augment and control the level of noise in these weak labels. Lastly, we explore how supervised fine-tuning effects the performance of these models and discuss the viability of leveraging weak labels for large-scale atrial fibrillation detection and identification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v149-chen21b, title = {Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels}, author = {Chen, Brian and Javadi, Golara and Jamzad, Amoon and Hamilton, Alexander and Sibley, Stephanie and Abolmaesumi, Purang and Maslove, David and Mousavi, Parvin}, booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference}, pages = {176--195}, year = {2021}, editor = {Jung, Ken and Yeung, Serena and Sendak, Mark and Sjoding, Michael and Ranganath, Rajesh}, volume = {149}, series = {Proceedings of Machine Learning Research}, month = {06--07 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v149/chen21b/chen21b.pdf}, url = {https://proceedings.mlr.press/v149/chen21b.html}, abstract = {State of the art techniques for creating ML models in healthcare often require large quantities of clean, labelled data. However, many healthcare organizations lack the capacity to generate the large-scale annotations required to create and validate reliable labels. In this paper, we demonstrate how raw data from an information-rich area of care can be exploited without the need for mass manual annotation via the use of weak labels. We evaluate the AF Detection with Weak Labels proposed framework on telemetry data from the intensive care unit for application of atrial fibrillation (AF) detection. We generate an in-house dataset of over 60,000 ECG segments with weak labels, derived from a model trained on publicly available data. We then show that building a deep learning model based on these weakly generated labels can significantly improve (more than 30%) the performance of AF detection in comparison with only using limited expert-annotated ground truth labels. We further demonstrate how weakly supervised learning techniques can be used to augment and control the level of noise in these weak labels. Lastly, we explore how supervised fine-tuning effects the performance of these models and discuss the viability of leveraging weak labels for large-scale atrial fibrillation detection and identification.} }
Endnote
%0 Conference Paper %T Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels %A Brian Chen %A Golara Javadi %A Amoon Jamzad %A Alexander Hamilton %A Stephanie Sibley %A Purang Abolmaesumi %A David Maslove %A Parvin Mousavi %B Proceedings of the 6th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2021 %E Ken Jung %E Serena Yeung %E Mark Sendak %E Michael Sjoding %E Rajesh Ranganath %F pmlr-v149-chen21b %I PMLR %P 176--195 %U https://proceedings.mlr.press/v149/chen21b.html %V 149 %X State of the art techniques for creating ML models in healthcare often require large quantities of clean, labelled data. However, many healthcare organizations lack the capacity to generate the large-scale annotations required to create and validate reliable labels. In this paper, we demonstrate how raw data from an information-rich area of care can be exploited without the need for mass manual annotation via the use of weak labels. We evaluate the AF Detection with Weak Labels proposed framework on telemetry data from the intensive care unit for application of atrial fibrillation (AF) detection. We generate an in-house dataset of over 60,000 ECG segments with weak labels, derived from a model trained on publicly available data. We then show that building a deep learning model based on these weakly generated labels can significantly improve (more than 30%) the performance of AF detection in comparison with only using limited expert-annotated ground truth labels. We further demonstrate how weakly supervised learning techniques can be used to augment and control the level of noise in these weak labels. Lastly, we explore how supervised fine-tuning effects the performance of these models and discuss the viability of leveraging weak labels for large-scale atrial fibrillation detection and identification.
APA
Chen, B., Javadi, G., Jamzad, A., Hamilton, A., Sibley, S., Abolmaesumi, P., Maslove, D. & Mousavi, P.. (2021). Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels. Proceedings of the 6th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 149:176-195 Available from https://proceedings.mlr.press/v149/chen21b.html.

Related Material