Appl Clin Inform 2019; 10(05): 952-963
DOI: 10.1055/s-0039-3401814
AMIA CIC 2019
Georg Thieme Verlag KG Stuttgart · New York

Unsupervised Machine Learning of Topics Documented by Nurses about Hospitalized Patients Prior to a Rapid-Response Event

Zfania Tom Korach
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Kenrick D. Cato
2  School of Nursing, Columbia University, New York, New York, United States
,
Sarah A. Collins
2  School of Nursing, Columbia University, New York, New York, United States
3  Department of Biomedical Informatics, Columbia University, New York, New York, United States
,
Min Jeoung Kang
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Christopher Knaplund
2  School of Nursing, Columbia University, New York, New York, United States
,
Patricia C. Dykes
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Liqin Wang
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Kumiko O. Schnock
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Jose P. Garcia
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Haomiao Jia
2  School of Nursing, Columbia University, New York, New York, United States
,
Frank Chang
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
,
Jessica M. Schwartz
2  School of Nursing, Columbia University, New York, New York, United States
,
Li Zhou
1  Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, United States
› Author Affiliations
Funding This work was funded by the National Institute of Nursing Research (NINR) award number 1R01NR016941. Jessica Schwartz is a pre-doctoral fellow funded by the National Institute of Nursing Research Reducing Health Disparities Through Informatics (RHeaDI) T32NR007969 and was funded by a grant from CRICO titled “2017-2019: Resilience in Clinical Deterioration Survival: Learning from Different Outcomes in Critical and Acute Care.”
Further Information

Publication History

13 August 2019

06 November 2019

Publication Date:
18 December 2019 (online)

Abstract

Background In the hospital setting, it is crucial to identify patients at risk for deterioration before it fully develops, so providers can respond rapidly to reverse the deterioration. Rapid response (RR) activation criteria include a subjective component (“worried about the patient”) that is often documented in nurses' notes and is hard to capture and quantify, hindering active screening for deteriorating patients.

Objectives We used unsupervised machine learning to automatically discover RR event risk/protective factors from unstructured nursing notes.

Methods In this retrospective cohort study, we obtained nursing notes of hospitalized, nonintensive care unit patients, documented from 2015 through 2018 from Partners HealthCare databases. We applied topic modeling to those notes to reveal topics (clusters of associated words) documented by nurses. Two nursing experts named each topic with a representative Systematized Nomenclature of Medicine–Clinical Terms (SNOMED CT) concept. We used the concepts along with vital signs and demographics in a time-dependent covariates extended Cox model to identify risk/protective factors for RR event risk.

Results From a total of 776,849 notes of 45,299 patients, we generated 95 stable topics, of which 80 were mapped to 72 distinct SNOMED CT concepts. Compared with a model containing only demographics and vital signs, the latent topics improved the model's predictive ability from a concordance index of 0.657 to 0.720. Thirty topics were found significantly associated with RR event risk at a 0.05 level, and 11 remained significant after Bonferroni correction of the significance level to 6.94E-04, including physical examination (hazard ratio [HR] = 1.07, 95% confidence interval [CI], 1.03–1.12), informing doctor (HR = 1.05, 95% CI, 1.03–1.08), and seizure precautions (HR = 1.08, 95% CI, 1.04–1.12).

Conclusion Unsupervised machine learning methods can automatically reveal interpretable and informative signals from free-text and may support early identification of patients at risk for RR events.

Protection of Human and Animal Subjects

The study was approved by the institutional review board of Partners HealthCare System.