TY - JOUR
T1 - Machine Learning for Clinical Outcome Prediction
AU - Shamout, Farah
AU - Zhu, Tingting
AU - Clifton, David A.
N1 - Funding Information:
Manuscript received January 4, 2020; accepted June 20, 2020. Date of publication July 7, 2020; date of current version January 22, 2021. (Corresponding author: Farah Shamout.) This research was supported by a Health Innovation Challenge Fund (HICF-R9-524; WT-103703/Z/14/Z), a parallel funding partnership between the Department of Health and Wellcome Trust, and in part by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC). The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health. David A. Clifton is supported by an EPSRC Grand Challenge Award.
Publisher Copyright:
© 2008-2011 IEEE.
PY - 2021
Y1 - 2021
N2 - Clinical decision-making in healthcare is already being influenced by predictions or recommendations made by data-driven machines. Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury and arrhythmia. In this review article, we summarize the state-of-the-art in related works covering data processing, inference, and model evaluation, in the context of outcome prediction models developed using data extracted from electronic health records. We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.
AB - Clinical decision-making in healthcare is already being influenced by predictions or recommendations made by data-driven machines. Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury and arrhythmia. In this review article, we summarize the state-of-the-art in related works covering data processing, inference, and model evaluation, in the context of outcome prediction models developed using data extracted from electronic health records. We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.
KW - Learning (artificial intelligence)
KW - big data applications
KW - decision support systems
KW - electronic medical records
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85091287381&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091287381&partnerID=8YFLogxK
U2 - 10.1109/RBME.2020.3007816
DO - 10.1109/RBME.2020.3007816
M3 - Article
C2 - 32746368
AN - SCOPUS:85091287381
SN - 1937-3333
VL - 14
SP - 116
EP - 126
JO - IEEE Reviews in Biomedical Engineering
JF - IEEE Reviews in Biomedical Engineering
M1 - 9134853
ER -