Abstract
Artificial intelligence tools usually aim to maximize predictive accuracy, but personalized measures of uncertainty, using new techniques such as conformal prediction, are needed for clinical artificial intelligence to realize its potential and improve human health.
Citation information
Banerji C.R.S., Chakraborti T., Harbron C. et al. Clinical AI tools must convey predictive uncertainty for each individual patient, Nature Medicine, 11 October 2023
Turing affiliated authors
Dr Tapabrata (Rohan) Chakraborty
Theme Lead, Turing-Roche Partnership
Chris Harbron
Expert Statistical Scientist and Advanced Analytics Lead, Roche