Utilizing timestamps of longitudinal electronic health record data to classify clinical deterioration events. (16th July 2021)

• Record Type: Journal Article
• Authors: Fu, Li-Heng; Knaplund, Chris; Cato, Kenrick; Perotte, Adler; Kang, Min-Jeoung; Dykes, Patricia C; Albers, David; Collins Rossetti, Sarah
• Is Part Of: Journal of the American Medical Informatics Association. Volume 28:Number 9(2021)
• Page Start: 1955
• Page End: 1963
• Publication Date: 2021-07-16
• Subjects: electronic health records -- predictive modeling -- clinical informatics -- early warning scores, machine learning; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocab111
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective: To propose an algorithm that utilizes only timestamps of longitudinal electronic health record data to classify clinical deterioration events. Materials and methods: This retrospective study explores the efficacy of machine learning algorithms in classifying clinical deterioration events among patients in intensive care units using sequences of timestamps of vital sign measurements, flowsheets comments, order entries, and nursing notes. We design a data pipeline to partition events into discrete, regular time bins that we refer to as timesteps. Logistic regressions, random forest classifiers, and recurrent neural networks are trained on datasets of different length of timesteps, respectively, against a composite outcome of death, cardiac arrest, and Rapid Response Team calls. Then these models are validated on a holdout dataset. Results: A total of 6720 intensive care unit encounters meet the criteria and the final dataset includes 830 578 timestamps. The gated recurrent unit model utilizes timestamps of vital signs, order entries, flowsheet comments, and nursing notes to achieve the best performance on the time-to-outcome dataset, with an area under the precision-recall curve of 0.101 (0.06, 0.137), a sensitivity of 0.443, and a positive predictive value of 0. 092 at the threshold of 0.6. Discussion and Conclusion: This study demonstrates that our recurrent neural network models using only timestamps of longitudinal electronic health record data that reflect healthcare processes achieve well-performing discriminative power.