Predicting hospital mortality for intensive care unit patients: Time-series analysis. (June 2020)

• Record Type: Journal Article
• Authors: Awad, Aya; Bader-El-Den, Mohamed; McNicholas, James; Briggs, Jim; El-Sonbaty, Yasser
• Other Names: Bian Jiang guest-editor.; Zhang Yaoyun guest-editor.; Tao Cui guest-editor.
• Is Part Of: Health informatics journal. Volume 26:Number 2(2020)
• Page Start: 1043
• Page End: 1059
• Publication Date: 2020-06
• Subjects: critically ill -- missing values -- mortality prediction -- patient mortality -- time-series analysis; Medical informatics -- Periodicals; 610.285
• DOI: 10.1177/1460458219850323
• Languages: English
• ISSNs: 1460-4582

Abstract

Current mortality prediction models and scoring systems for intensive care unit patients are generally usable only after at least 24 or 48 h of admission, as some parameters are unclear at admission. However, some of the most relevant measurements are available shortly following admission. It is hypothesized that outcome prediction may be made using information available in the earliest phase of intensive care unit admission. This study aims to investigate how early hospital mortality can be predicted for intensive care unit patients. We conducted a thorough time-series analysis on the performance of different data mining methods during the first 48 h of intensive care unit admission. The results showed that the discrimination power of the machine-learning classification methods after 6 h of admission outperformed the main scoring systems used in intensive care medicine (Acute Physiology and Chronic Health Evaluation, Simplified Acute Physiology Score and Sequential Organ Failure Assessment) after 48 h of admission.