Journal article
Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care
Journal of biomedical informatics, Vol.128, pp.104039-104039
04/2022
DOI: 10.1016/j.jbi.2022.104039
PMCID: PMC9825202
PMID: 35231649
Abstract
[Display omitted]
•Early identification of HHC patients at risk can prevent hospitalizations/ED visits.•Valid indicators for hospitalizations/ER visits were generated by NLP approaches.•Combining clinical notes with structured data improves risk prediction.
Between 10 and 25% patients are hospitalized or visit emergency department (ED) during home healthcare (HHC). Given that up to 40% of these negative clinical outcomes are preventable, early and accurate prediction of hospitalization risk can be one strategy to prevent them. In recent years, machine learning-based predictive modeling has become widely used for building risk models. This study aimed to compare the predictive performance of four risk models built with various data sources for hospitalization and ED visits in HHC.
Four risk models were built using different variables from two data sources: structured data (i.e., Outcome and Assessment Information Set (OASIS) and other assessment items from the electronic health record (EHR)) and unstructured narrative-free text clinical notes for patients who received HHC services from the largest non-profit HHC organization in New York between 2015 and 2017. Then, five machine learning algorithms (logistic regression, Random Forest, Bayesian network, support vector machine (SVM), and Naïve Bayes) were used on each risk model. Risk model performance was evaluated using the F-score and Precision-Recall Curve (PRC) area metrics.
During the study period, 8373/86,823 (9.6%) HHC episodes resulted in hospitalization or ED visits. Among five machine learning algorithms on each model, the SVM showed the highest F-score (0.82), while the Random Forest showed the highest PRC area (0.864). Adding information extracted from clinical notes significantly improved the risk prediction ability by up to 16.6% in F-score and 17.8% in PRC.
All models showed relatively good hospitalization or ED visit risk predictive performance in HHC. Information from clinical notes integrated with the structured data improved the ability to identify patients at risk for these emergent care events.
Details
- Title: Subtitle
- Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care
- Creators
- Jiyoun Song - Visiting Nurse Service of New YorkMollie Hobensack - Columbia UniversityKathryn H. Bowles - Visiting Nurse Service of New YorkMargaret V. McDonald - Visiting Nurse Service of New YorkKenrick Cato - Columbia University Irving Medical CenterSarah Collins Rossetti - Columbia UniversitySena Chae - University of IowaErin Kennedy - University of PennsylvaniaYolanda Barrón - Visiting Nurse Service of New YorkSridevi Sridharan - Visiting Nurse Service of New YorkMaxim Topaz - Visiting Nurse Service of New York
- Resource Type
- Journal article
- Publication Details
- Journal of biomedical informatics, Vol.128, pp.104039-104039
- Publisher
- Elsevier Inc
- DOI
- 10.1016/j.jbi.2022.104039
- PMID
- 35231649
- PMCID
- PMC9825202
- ISSN
- 1532-0464
- eISSN
- 1532-0480
- Grant note
- DOI: 10.13039/100000133, name: Agency for Healthcare Research and Quality
- Language
- English
- Date published
- 04/2022
- Academic Unit
- Nursing
- Record Identifier
- 9984368087102771
Metrics
9 Record Views