Mining heterogeneous clinical notes by multi-modal latent topic model
Open Access
- 8 April 2021
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (4) , e0249622
Abstract
Latent knowledge can be extracted from the electronic notes that are recorded during patient encounters with the health system. Using these clinical notes to decipher a patient’s underlying comorbidites, symptom burdens, and treatment courses is an ongoing challenge. Latent topic model as an efficient Bayesian method can be used to model each patient’s clinical notes as “documents” and the words in the notes as “tokens”. However, standard latent topic models assume that all of the notes follow the same topic distribution, regardless of the type of note or the domain expertise of the author (such as doctors or nurses). We propose a novel application of latent topic modeling, using multi-note topic model (MNTM) to jointly infer distinct topic distributions of notes of different types. We applied our model to clinical notes from the MIMIC-III dataset to infer distinct topic distributions over the physician and nursing note types. Based on manual assessments made by clinicians, we observed a significant improvement in topic interpretability using MNTM modeling over the baseline single-note topic models that ignore the note types. Moreover, our MNTM model led to a significantly higher prediction accuracy for prolonged mechanical ventilation and mortality using only the first 48 hours of patient data. By correlating the patients’ topic mixture with hospital mortality and prolonged mechanical ventilation, we identified several diagnostic topics that are associated with poor outcomes. Because of its elegant and intuitive formation, we envision a broad application of our approach in mining multi-modality text-based healthcare information that goes beyond clinical notes. Code available at https://github.com/li-lab-mcgill/heterogeneous_ehr.Keywords
Funding Information
- Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada (RGPIN-2019-0621)
- Fonds de Recherche du Québec - Nature et Technologies (NC-268592)
- Microsoft Research
This publication has 11 references indexed in Scilit:
- Publicly Available Clinical2019
- Readmission prediction via deep contextual embedding of clinical conceptsPLOS ONE, 2018
- MIMIC-III, a freely accessible critical care databaseScientific Data, 2016
- Learning probabilistic phenotypes from heterogeneous EHR dataJournal of Biomedical Informatics, 2015
- Building bridges across electronic health record systems through inferred phenotypic topicsJournal of Biomedical Informatics, 2015
- Clinical review: Scoring systems in the critically illCritical Care, 2010
- A Collapsed Variational Bayesian Inference Algorithm for Latent Dirichlet Allocation2007
- Weaning from mechanical ventilationEuropean Respiratory Journal, 2007
- Systematic review and meta-analysis of studies of the timing of tracheostomy in adult patients undergoing artificial ventilationBMJ, 2005
- Long-term outcome and quality of life of patients requiring prolonged mechanical ventilation after cardiac surgeryEuropean Journal of Cardio-Thoracic Surgery, 2004