Classifying Unstructured Clinical Notes via Automatic Weak Supervision

Chufan Gao, Mononito Goswami, Jieshi Chen, Artur Dubrawski
Proceedings of the 7th Machine Learning for Healthcare Conference, PMLR 182:673-690, 2022.

Abstract

Healthcare providers usually record detailed notes of the clinical care delivered to each patient for clinical, research, and billing purposes. Due to the unstructured nature of these narratives, providers employ dedicated staff to assign diagnostic codes to patients’ diagnoses using the International Classification of Diseases (ICD) coding system. This manual process is not only time-consuming but also costly and error-prone. Prior work demonstrated potential utility of Machine Learning (ML) methodology in automating this process, but it has relied on large quantities of manually labeled data to train the models. Additionally, diagnostic coding systems evolve with time, which makes traditional supervised learning strategies unable to generalize beyond local applications. In this work, we introduce a general weakly-supervised text classification framework that learns from class-label descriptions only, without the need to use any human-labeled documents. It leverages the linguistic domain knowledge stored within pre-trained language models and the data programming framework to assign code labels to individual texts. We demonstrate the efficacy and flexibility of our method by comparing it to state-of-the-art weak text classifiers across four real-world text classification datasets, in addition to assigning ICD codes to medical notes in the publicly available MIMIC-III database.

Cite this Paper

BibTeX
@InProceedings{pmlr-v182-gao22a, title = {Classifying Unstructured Clinical Notes via Automatic Weak Supervision}, author = {Gao, Chufan and Goswami, Mononito and Chen, Jieshi and Dubrawski, Artur}, booktitle = {Proceedings of the 7th Machine Learning for Healthcare Conference}, pages = {673--690}, year = {2022}, editor = {Lipton, Zachary and Ranganath, Rajesh and Sendak, Mark and Sjoding, Michael and Yeung, Serena}, volume = {182}, series = {Proceedings of Machine Learning Research}, month = {05--06 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v182/gao22a/gao22a.pdf}, url = {https://proceedings.mlr.press/v182/gao22a.html}, abstract = {Healthcare providers usually record detailed notes of the clinical care delivered to each patient for clinical, research, and billing purposes. Due to the unstructured nature of these narratives, providers employ dedicated staff to assign diagnostic codes to patients’ diagnoses using the International Classification of Diseases (ICD) coding system. This manual process is not only time-consuming but also costly and error-prone. Prior work demonstrated potential utility of Machine Learning (ML) methodology in automating this process, but it has relied on large quantities of manually labeled data to train the models. Additionally, diagnostic coding systems evolve with time, which makes traditional supervised learning strategies unable to generalize beyond local applications. In this work, we introduce a general weakly-supervised text classification framework that learns from class-label descriptions only, without the need to use any human-labeled documents. It leverages the linguistic domain knowledge stored within pre-trained language models and the data programming framework to assign code labels to individual texts. We demonstrate the efficacy and flexibility of our method by comparing it to state-of-the-art weak text classifiers across four real-world text classification datasets, in addition to assigning ICD codes to medical notes in the publicly available MIMIC-III database.} }
Endnote
%0 Conference Paper %T Classifying Unstructured Clinical Notes via Automatic Weak Supervision %A Chufan Gao %A Mononito Goswami %A Jieshi Chen %A Artur Dubrawski %B Proceedings of the 7th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2022 %E Zachary Lipton %E Rajesh Ranganath %E Mark Sendak %E Michael Sjoding %E Serena Yeung %F pmlr-v182-gao22a %I PMLR %P 673--690 %U https://proceedings.mlr.press/v182/gao22a.html %V 182 %X Healthcare providers usually record detailed notes of the clinical care delivered to each patient for clinical, research, and billing purposes. Due to the unstructured nature of these narratives, providers employ dedicated staff to assign diagnostic codes to patients’ diagnoses using the International Classification of Diseases (ICD) coding system. This manual process is not only time-consuming but also costly and error-prone. Prior work demonstrated potential utility of Machine Learning (ML) methodology in automating this process, but it has relied on large quantities of manually labeled data to train the models. Additionally, diagnostic coding systems evolve with time, which makes traditional supervised learning strategies unable to generalize beyond local applications. In this work, we introduce a general weakly-supervised text classification framework that learns from class-label descriptions only, without the need to use any human-labeled documents. It leverages the linguistic domain knowledge stored within pre-trained language models and the data programming framework to assign code labels to individual texts. We demonstrate the efficacy and flexibility of our method by comparing it to state-of-the-art weak text classifiers across four real-world text classification datasets, in addition to assigning ICD codes to medical notes in the publicly available MIMIC-III database.
APA
Gao, C., Goswami, M., Chen, J. & Dubrawski, A.. (2022). Classifying Unstructured Clinical Notes via Automatic Weak Supervision. Proceedings of the 7th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 182:673-690 Available from https://proceedings.mlr.press/v182/gao22a.html.

Related Material