Topic Modeling on Triage Notes With Semiorthogonal Nonnegative Matrix Factorization

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)1609-1624
Number of pages16
Journal / PublicationJournal of the American Statistical Association
Volume116
Issue number536
Online published11 Dec 2020
Publication statusPublished - 2021

Abstract

Emergency Department (ED) crowding is a universal health issue that affects the efficiency of hospital management and patient care quality. ED crowding frequently occurs when a request for a ward-bed for a patient is delayed until a doctor makes an admission decision. In this case study, we build a classifier to predict the disposition of patients using manually typed nurse notes collected during triage as provided by the Alberta Medical Center. These predictions can potentially be incorporated to early bed coordination and fast track streaming strategies to alleviate overcrowding and waiting times in the ED. However, these triage notes involve high dimensional, noisy, and sparse text data, which make model-fitting and interpretation difficult. To address this issue, we propose a novel semi-orthogonal non-negative matrix factorization (SONMF) for both continuous and binary predictors to reduce the dimensionality and derive word topics. The triage notes can then be interpreted as a non-subtractive linear combination of orthogonal basis topic vectors. Our real data analysis shows that the triage notes contain strong predictive information towards classifying the disposition of patients for certain medical complaints, such as altered consciousness or stroke. Additionally, we show that the document-topic vectors generated by our method can be used as features to further improve classification accuracy by up to 1% across different medical complaints, i.e. 74.3% to 75.3% accuracy for patients with stroke symptoms. This improvement could be clinically impactful for certain patients, especially when the scale of hospital patients is large. Furthermore, the generated word-topic vectors provide a bi-clustering interpretation under each topic due to the orthogonal formulation, which can be beneficial for hospitals in better understanding the symptoms and reasons behind patients’ visits.

Research Area(s)

  • Emergency Department Crowding, Text Mining, Matrix Factorization, Dimension Reduction, Topic Modeling

Citation Format(s)

Topic Modeling on Triage Notes With Semiorthogonal Nonnegative Matrix Factorization. / Li, Yutong; Zhu, Ruoqing; Qu, Annie et al.
In: Journal of the American Statistical Association, Vol. 116, No. 536, 2021, p. 1609-1624.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review