Machine learning for clinical outcome prediction

Journal article

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.

Authors: Shamout, F; Zhu, T; Clifton, DA

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Journal: IEEE Reviews in Biomedical Engineering
• Volume: 14
• Pages: 116-126
• Publication date: 2020-07-07
• Acceptance date: 2020-06-20
• DOI: 10.1109/rbme.2020.3007816
• ISSN: 1937-3333
• Pmid: 32746368
• Language: English
• Keywords: electronic medical records; decision support systems; learning (artificial intelligence); big data applications; machine learning; FFR