Prediction on critically ill patients: The role of “big data”

• Published in: Journal of critical care Vol. 60; pp. 64 - 68
• Main Authors: Bulgarelli, Lucas, Deliberato, Rodrigo Octávio, Johnson, Alistair E.W.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2020; Elsevier Limited
• Subjects: Algorithms; Archives & records; Big Data; Critical Care; Critical Care - methods; Critical Illness; Data collection; Deep learning; Delivery of Health Care - methods; Electronic Health Records; Hospital Mortality; Humans; Information systems; Intensive Care Units; Length of Stay; Machine Learning; Medical equipment; Mortality; Neural networks; Outcome prediction; Patients; Prognosis; Researchers; Severity of Illness Index; Outcome prediction; Critical Care; Machine learning
• ISSN: 0883-9441; 1557-8615
• DOI: 10.1016/j.jcrc.2020.07.017

Accurate outcome prediction in Intensive Care Units (ICUs) would allow for better treatment planning, risk adjustment of study populations, and overall improvements in patient care. In the past, prognostic models have focused on mortality using simple ordinal severity of illness scores which could be tabulated manually by a human. With the improvements in computing power and proliferation of electronic medical records, entirely new approaches have become possible. Here we review the latest advances in outcome prediction, paying close attention to methods which are widely applicable and provide a high-level overview of the challenges the field currently faces. •The high volume of data generated by electronic health records has shown to be promising in the creation of prediction models.•There is a lack of robust and well-established evaluation methods for machine learning in healthcare.•Generalizability in prediction models is a problem, especially in low-and-middle income countries.