Journal of Medical Internet Research (Aug 2020)

Is Artificial Intelligence Better Than Human Clinicians in Predicting Patient Outcomes?

  • Lee, Joon

DOI
https://doi.org/10.2196/19918
Journal volume & issue
Vol. 22, no. 8
p. e19918

Abstract

Read online

In contrast with medical imaging diagnostics powered by artificial intelligence (AI), in which deep learning has led to breakthroughs in recent years, patient outcome prediction poses an inherently challenging problem because it focuses on events that have not yet occurred. Interestingly, the performance of machine learning–based patient outcome prediction models has rarely been compared with that of human clinicians in the literature. Human intuition and insight may be sources of underused predictive information that AI will not be able to identify in electronic data. Both human and AI predictions should be investigated together with the aim of achieving a human-AI symbiosis that synergistically and complementarily combines AI with the predictive abilities of clinicians.