Medical AI, inductive risk and the communication of uncertainty: the case of disorders of consciousness

Birch, Jonathan ORCID: 0000-0001-7517-4759 (2023) Medical AI, inductive risk and the communication of uncertainty: the case of disorders of consciousness. Journal of Medical Ethics. ISSN 0306-6800

Text (Medical AI, Inductive Risk, and the Communication of Uncertainty The Case of Disorders of Consciousness) - Accepted Version Available under License Creative Commons Attribution Non-commercial. Download (607kB)

• Author
• Scopus publication

Abstract

Some patients, following brain injury, do not outwardly respond to spoken commands, yet show patterns of brain activity that indicate responsiveness. This is 'cognitive-motor dissociation' (CMD). Recent research has used machine learning to diagnose CMD from electroencephalogram recordings. These techniques have high false discovery rates, raising a serious problem of inductive risk. It is no solution to communicate the false discovery rates directly to the patient's family, because this information may confuse, alarm and mislead. Instead, we need a procedure for generating case-specific probabilistic assessments that can be communicated clearly. This article constructs a possible procedure with three key elements: (1) A shift from categorical 'responding or not' assessments to degrees of evidence; (2) The use of patient-centred priors to convert degrees of evidence to probabilistic assessments; and (3) The use of standardised probability yardsticks to convey those assessments as clearly as possible.

Item Type:	Article
Official URL:	https://jme.bmj.com/
Additional Information:	© 2023 The Author
Divisions:	Philosophy, Logic and Scientific Method
Subjects:	B Philosophy. Psychology. Religion > B Philosophy (General) R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
Date Deposited:	31 Oct 2023 10:33
Last Modified:	12 Dec 2024 03:55
URI:	http://eprints.lse.ac.uk/id/eprint/120570

Actions (login required)

View Item