Explainable artificial intelligence for mental health through transparency and interpretability for understandability
University of Liverpool · Warneford Hospital · +3 more institutions
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…
Citation impact
- FWCI
- 34.96
- Percentile
- 100%
- References
- 44
Authors
4- DWDan W. JoyceCorresponding
University of Liverpool, Warneford Hospital, University of Oxford
- AKAndrey Kormilitzin
Warneford Hospital, University of Oxford
- KSKatharine Smith
Oxford Health NHS Foundation Trust, Warneford Hospital, University of Oxford, Oxford BioMedica (United Kingdom)
- ACAndrea Cipriani
Oxford Health NHS Foundation Trust, Warneford Hospital, University of Oxford, Oxford BioMedica (United Kingdom)
Topics & keywords
- Interpretability
- Transparency (behavior)
- Computer science
- Artificial intelligence
- Meaning (existential)
- Trustworthiness
- Probabilistic logic
- Machine learning