Explanatory pragmatism: a context-sensitive framework for explainable medical AI.
View / Open Files
Publication Date
2022Journal Title
Ethics Inf Technol
ISSN
1388-1957
Publisher
Springer
Type
Article
This Version
AM
Metadata
Show full item recordCitation
Nyrup, R., & Robinson, D. (2022). Explanatory pragmatism: a context-sensitive framework for explainable medical AI.. Ethics Inf Technol https://doi.org/10.1007/s10676-022-09632-3
Abstract
Explainable artificial intelligence (XAI) is an emerging, multidisciplinary field of research that seeks to develop methods and tools for making AI systems more explainable or interpretable. XAI researchers increasingly recognise explainability as a context-, audience- and purpose-sensitive phenomenon, rather than a single well-defined property that can be directly measured and optimised. However, since there is currently no overarching definition of explainability, this poses a risk of miscommunication between the many different researchers within this multidisciplinary space. This is the problem we seek to address in this paper. We outline a framework, called Explanatory Pragmatism, which we argue has two attractive features. First, it allows us to conceptualise explainability in explicitly context-, audience- and purpose-relative terms, while retaining a unified underlying definition of explainability. Second, it makes visible any normative disagreements that may underpin conflicting claims about explainability regarding the purposes for which explanations are sought. Third, it allows us to distinguish several dimensions of AI explainability. We illustrate this framework by applying it to a case study involving a machine learning model for predicting whether patients suffering disorders of consciousness were likely to recover consciousness.
Sponsorship
Leverhulme Trust (through Leverhulme Centre for the Future of Intelligence)
Funder references
Wellcome Trust (213660/Z/18/Z)
Leverhulme Trust (RC-2015-067)
Leverhulme Trust (RC-2015-067)
Embargo Lift Date
2023-12-31
Identifiers
External DOI: https://doi.org/10.1007/s10676-022-09632-3
This record's URL: https://www.repository.cam.ac.uk/handle/1810/332764
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.