Effects of explainable artificial intelligence in neurology decision support
Annals of Clinical and Translational Neurology · 2024
DOI: 10.1002/acn3.52036 ↗Kurz gefasst
Randomisierte kontrollierte Studie in der Zeitschrift Annals of Clinical and Translational Neurology, 2024. Verfasst von Grace Y Gombolay und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Division of Neurology, Children's Healthcare of Atlanta, Emory University School of Medicine, Atlanta, GA, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Decision Support Systems, Clinical, Neurology. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NCATS NIH HHS, NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Objective
Artificial intelligence (AI)‐based decision support systems (DSS) are utilized in medicine but underlying decision‐making processes are usually unknown. Explainable AI (xAI) techniques provide insight into DSS, but little is known on how to design xAI for clinicians. Here we investigate the impact of various xAI techniques on a clinician's interaction with an AI‐based DSS in decision‐making tasks as compared to a general population.
Methods
We conducted a randomized, blinded study in which members of the Child Neurology Society and American Academy of Neurology were compared to a general population. Participants received recommendations from a DSS via a random assignment of an xAI intervention (decision tree, crowd sourced agreement, case‐based reasoning, probability scores, counterfactual reasoning, feature importance, templated language, and no explanations). Primary outcomes included test performance and perceived explainability, trust, and social competence of the DSS. Secondary outcomes included compliance, understandability, and agreement per question.
Results
We had 81 neurology participants with 284 in the general population. Decision trees were perceived as the more explainable by the medical versus general population ( P < 0.01) and as more explainable than probability scores within the medical population ( P < 0.001). Increasing neurology experience and perceived explainability degraded performance ( P = 0.0214). Performance was not predicted by xAI method but by perceived explainability. Interpretation xAI methods have different impacts on a medical versus general population; thus, xAI is not uniformly beneficial, and there is no one‐size‐fits‐all approach. Further user‐centered xAI research targeting clinicians and to develop personalized DSS for clinicians is needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Pediatrics, Division of Neurology, Children's Healthcare of Atlanta, Emory University School of Medicine, Atlanta, GA, USA.
- Georgia Institute of Technology, Atlanta, GA, USA.
- Arizona State University, Tempe, AZ, USA.
ORCID-Profile: Grace Y Gombolay
Förderung
- NCATS NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Gombolay, G. Y., Silva, A., Schrum, M., Gopalan, N., Hallman-Cooper, J., Dutt, M., & Gombolay, M. (2024). Effects of explainable artificial intelligence in neurology decision support. Annals of Clinical and Translational Neurology. https://doi.org/10.1002/acn3.52036
Vancouver
Gombolay GY, Silva A, Schrum M, Gopalan N, Hallman-Cooper J, Dutt M, et al. Effects of explainable artificial intelligence in neurology decision support. Annals of Clinical and Translational Neurology. 2024. doi:10.1002/acn3.52036
BibTeX
@article{Gombolay2024,
author = {Gombolay, Grace Y and Silva, Andrew and Schrum, Mariah and Gopalan, Nakul and Hallman-Cooper, Jamika and Dutt, Monideep and Gombolay, Matthew},
title = {Effects of explainable artificial intelligence in neurology decision support},
journal = {Annals of Clinical and Translational Neurology},
year = {2024},
doi = {10.1002/acn3.52036}
}
EUVIMED