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

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 augmen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NPJ digital medicine Jg. 6; H. 1; S. 6 - 7
Hauptverfasser: Joyce, Dan W., Kormilitzin, Andrey, Smith, Katharine A., Cipriani, Andrea
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 18.01.2023
Nature Publishing Group
Nature Portfolio
Schlagworte:
631/114
692/700
Artificial intelligence
Behavior
Biomedicine
Biotechnology
Medical research
Medicine
Medicine & Public Health
Mental health
Review
Review Article
Transparency
ISSN:2398-6352, 2398-6352
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
ISSN:2398-6352
2398-6352
DOI:10.1038/s41746-023-00751-9