Enriching Unsupervised User Embedding via Medical Concepts

Xiaolei Huang, Franck Dernoncourt, Mark Dredze
Proceedings of the Conference on Health, Inference, and Learning, PMLR 174:63-78, 2022.

Abstract

Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection. Unsupervised user embedding aims to encode patients into fixed-length vectors without human supervisions. Medical concepts extracted from the clinical notes contain rich connections between patients and their clinical categories. However, existing \textit{unsupervised} approaches of user embeddings from clinical notes do not explicitly incorporate medical concepts. In this study, we propose a concept-aware unsupervised user embedding that jointly leverages text documents and medical concepts from two clinical corpora, MIMIC-III and Diabetes. We evaluate user embeddings on both extrinsic and intrinsic tasks, including phenotype classification, in-hospital mortality prediction, patient retrieval, and patient relatedness. Experiments on the two clinical corpora show our approach exceeds unsupervised baselines, and incorporating medical concepts can significantly improve the baseline performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v174-huang22a, title = {Enriching Unsupervised User Embedding via Medical Concepts}, author = {Huang, Xiaolei and Dernoncourt, Franck and Dredze, Mark}, booktitle = {Proceedings of the Conference on Health, Inference, and Learning}, pages = {63--78}, year = {2022}, editor = {Flores, Gerardo and Chen, George H and Pollard, Tom and Ho, Joyce C and Naumann, Tristan}, volume = {174}, series = {Proceedings of Machine Learning Research}, month = {07--08 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v174/huang22a/huang22a.pdf}, url = {https://proceedings.mlr.press/v174/huang22a.html}, abstract = {Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection. Unsupervised user embedding aims to encode patients into fixed-length vectors without human supervisions. Medical concepts extracted from the clinical notes contain rich connections between patients and their clinical categories. However, existing \textit{unsupervised} approaches of user embeddings from clinical notes do not explicitly incorporate medical concepts. In this study, we propose a concept-aware unsupervised user embedding that jointly leverages text documents and medical concepts from two clinical corpora, MIMIC-III and Diabetes. We evaluate user embeddings on both extrinsic and intrinsic tasks, including phenotype classification, in-hospital mortality prediction, patient retrieval, and patient relatedness. Experiments on the two clinical corpora show our approach exceeds unsupervised baselines, and incorporating medical concepts can significantly improve the baseline performance.} }
Endnote
%0 Conference Paper %T Enriching Unsupervised User Embedding via Medical Concepts %A Xiaolei Huang %A Franck Dernoncourt %A Mark Dredze %B Proceedings of the Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2022 %E Gerardo Flores %E George H Chen %E Tom Pollard %E Joyce C Ho %E Tristan Naumann %F pmlr-v174-huang22a %I PMLR %P 63--78 %U https://proceedings.mlr.press/v174/huang22a.html %V 174 %X Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection. Unsupervised user embedding aims to encode patients into fixed-length vectors without human supervisions. Medical concepts extracted from the clinical notes contain rich connections between patients and their clinical categories. However, existing \textit{unsupervised} approaches of user embeddings from clinical notes do not explicitly incorporate medical concepts. In this study, we propose a concept-aware unsupervised user embedding that jointly leverages text documents and medical concepts from two clinical corpora, MIMIC-III and Diabetes. We evaluate user embeddings on both extrinsic and intrinsic tasks, including phenotype classification, in-hospital mortality prediction, patient retrieval, and patient relatedness. Experiments on the two clinical corpora show our approach exceeds unsupervised baselines, and incorporating medical concepts can significantly improve the baseline performance.
APA
Huang, X., Dernoncourt, F. & Dredze, M.. (2022). Enriching Unsupervised User Embedding via Medical Concepts. Proceedings of the Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 174:63-78 Available from https://proceedings.mlr.press/v174/huang22a.html.

Related Material