Explainable artificial intelligence for mental health through transparency and interpretability for understandability

Joyce, Dan W ORCID: 0000-0002-9433-5340, Kormilitzin, Andrey, Smith, Katharine A and Cipriani, Andrea (2023) Explainable artificial intelligence for mental health through transparency and interpretability for understandability. NPJ DIGITAL MEDICINE, 6 (1). 6-.

Text Explainable artificial intelligence for mental health through transparency and interpretability for understandability.pdf - Open Access published version Download (701kB) | Preview

Abstract

The literature on artificial intelligence (AI) or machine learning (ML) in mental health and psychiatry lacks consensus on what "explainability" means. In the more general XAI (eXplainable AI) literature, there has been some convergence on explainability meaning model-agnostic techniques that augment a complex model (with internal mechanics intractable for human understanding) with a simpler model argued to deliver results that humans can comprehend. Given the differing usage and intended meaning of the term "explainability" in AI and ML, we propose instead to approximate model/algorithm explainability by understandability defined as a function of transparency and interpretability. These concepts are easier to articulate, to "ground" in our understanding of how algorithms and models operate and are used more consistently in the literature. We describe the TIFU (Transparency and Interpretability For Understandability) framework and examine how this applies to the landscape of AI/ML in mental health research. We argue that the need for understandablity is heightened in psychiatry because data describing the syndromes, outcomes, disorders and signs/symptoms possess probabilistic relationships to each other-as do the tentative aetiologies and multifactorial social- and psychological-determinants of disorders. If we develop and deploy AI/ML models, ensuring human understandability of the inputs, processes and outputs of these models is essential to develop trustworthy systems fit for deployment.

Item Type:	Article
Uncontrolled Keywords:	Bioengineering, Mental Health, Clinical Research, Mental health, 3 Good Health and Well Being
Divisions:	Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Population Health
Depositing User:	Symplectic Admin
Date Deposited:	13 Jun 2023 15:01
Last Modified:	17 Mar 2024 16:06
DOI:	10.1038/s41746-023-00751-9
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3170961