Paper Type

ERF

Abstract

In developing countries, patients with limited medical knowledge often struggle with treatment plans due to numerous options. Explainable Artificial Intelligence (XAI) can help patients understand treatment options and engage in shared decision-making (SDM) for treatment decisions. However, current XAI systems typically provide one-size-fits-all explanations that fail to address user needs for building trust. This progress paper argues that interactive XAI offers dynamic functionality, enhancing patients' competence and empowering them to actively engage in SDM for optimal treatment choices. We aim to Investigate various interactive XAI designs for cancer treatment recommendations and examine their effects on building patients' trust. We plan to conduct two sequential studies in Africa, where qualitative results will inform the quantitative study by identifying user motivational factors (explanandum and explanans) for explanations. The identified user needs from Study 1 will enhance the existing XAI system by incorporating users' motivational factors into the design, thereby fostering trust.

Paper Number

2181

Author Connect URL

https://authorconnect.aisnet.org/conferences/AMCIS2025/papers/2181

Comments

SIGHEALTH

Author Connect Link

Share

COinS
 
Aug 15th, 12:00 AM

Interactive XAI for Shared Decision Making in Healthcare in Africa

In developing countries, patients with limited medical knowledge often struggle with treatment plans due to numerous options. Explainable Artificial Intelligence (XAI) can help patients understand treatment options and engage in shared decision-making (SDM) for treatment decisions. However, current XAI systems typically provide one-size-fits-all explanations that fail to address user needs for building trust. This progress paper argues that interactive XAI offers dynamic functionality, enhancing patients' competence and empowering them to actively engage in SDM for optimal treatment choices. We aim to Investigate various interactive XAI designs for cancer treatment recommendations and examine their effects on building patients' trust. We plan to conduct two sequential studies in Africa, where qualitative results will inform the quantitative study by identifying user motivational factors (explanandum and explanans) for explanations. The identified user needs from Study 1 will enhance the existing XAI system by incorporating users' motivational factors into the design, thereby fostering trust.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.