Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning-Based Method to Predict Crucial Complication Phenotypes.

Journal: Journal of medical Internet research
Published Date:

Abstract

BACKGROUND: Acute diseases present severe complications that develop rapidly, exhibit distinct phenotypes, and have profound effects on patient outcomes. Predictive analytics can enhance physicians' care and management of patients with acute diseases by predicting crucial complication phenotypes for a timely diagnosis and treatment. However, effective phenotype predictions require several challenges to be overcome. First, patient data collected in the early stages of an acute disease (eg, clinical data and laboratory results) are less informative for predicting phenotypic outcomes. Second, patient data are temporal and heterogeneous; for example, patients receive laboratory tests at different time intervals and frequencies. Third, imbalanced distributions of patient outcomes create additional complexity for predicting complication phenotypes.

Authors

  • Jessica Qiuhua Sheng
    Department of Operations and Information Systems, David Eccles School of Business, University of Utah, Salt Lake City, UT, United States.
  • Paul Jen-Hwa Hu
    Department of Operations and Information Systems, David Eccles School of Business, University of Utah, USA. Electronic address: paul.hu@eccles.utah.edu.
  • Xiao Liu
  • Ting-Shuo Huang
    Department of General Surgery, Keelung Chang Gung Memorial Hospital, Department of Chinese Medicine, College of Medicine, Chang Gung University, Community Medicine Research Center, Keelung Chang Gung Memorial Hospital, Taiwan, ROC. Electronic address: huangts@cgmh.org.tw.
  • Yu Hsien Chen
    Department of Chinese Medicine, College of Medicine, Chang Gung University, Taoyuan, Chang Gung, Taiwan.