Painting the Black Box White: Experimental Findings from Applying XAI to an ECG Reading Setting

Author:

Cabitza Federico12ORCID,Campagner Andrea2,Natali Chiara1ORCID,Parimbelli Enea34ORCID,Ronzio Luca5ORCID,Cameli Matteo6ORCID

Affiliation:

1. Department of Computer Science, Systems and Communication, University of Milano-Bicocca, 20126 Milan, Italy

2. IRCCS Istituto Ortopedico Galeazzi, 20161 Milan, Italy

3. Department of Electric, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy

4. Telfer School of Management, University of Ottawa, Ottawa, ON K1N 6N5, Canada

5. Department of Medicine and Surgery, University of Milano-Bicocca, 20126 Milan, Italy

6. Department of Medicine, Surgery and Neuroscience, University of Siena, 53100 Siena, Italy

Abstract

The emergence of black-box, subsymbolic, and statistical AI systems has motivated a rapid increase in the interest regarding explainable AI (XAI), which encompasses both inherently explainable techniques, as well as approaches to make black-box AI systems explainable to human decision makers. Rather than always making black boxes transparent, these approaches are at risk of painting the black boxes white, thus failing to provide a level of transparency that would increase the system’s usability and comprehensibility, or even at risk of generating new errors (i.e., white-box paradox). To address these usability-related issues, in this work we focus on the cognitive dimension of users’ perception of explanations and XAI systems. We investigated these perceptions in light of their relationship with users’ characteristics (e.g., expertise) through a questionnaire-based user study involved 44 cardiology residents and specialists in an AI-supported ECG reading task. Our results point to the relevance and correlation of the dimensions of trust, perceived quality of explanations, and tendency to defer the decision process to automation (i.e., technology dominance). This contribution calls for the evaluation of AI-based support systems from a human–AI interaction-oriented perspective, laying the ground for further investigation of XAI and its effects on decision making and user experience.

Funder

Italian Ministry of Health

Publisher

MDPI AG

Subject

General Economics, Econometrics and Finance

Reference80 articles.

1. On the integration of symbolic and sub-symbolic techniques for XAI: A survey;Calegari;Intell. Artif.,2020

2. Springer, A., Hollis, V., and Whittaker, S. (2017, January 27–29). Dice in the black box: User experiences with an inscrutable algorithm. Proceedings of the 2017 AAAI Spring Symposium Series, Stanford, CA, USA.

3. Cinà, G., Röber, T., Goedhart, R., and Birbil, I. (2022). Why we do need Explainable AI for Healthcare. arXiv.

4. Gerlings, J., Shollo, A., and Constantiou, I. (2020). Reviewing the need for explainable artificial intelligence (xAI). arXiv.

5. Goebel, R., Chander, A., Holzinger, K., Lecue, F., Akata, Z., Stumpf, S., Kieseberg, P., and Holzinger, A. (2018, January 27). Explainable AI: The new 42?. Proceedings of the International Cross-Domain Conference for Machine Learning and Knowledge Extraction, Hamburg, Germany.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3