[论文解读] Designing Explainable AI for Healthcare Reviews: Guidance on Adoption and Trust

Eman Alamoudi, Ellis Solaiman|arXiv (Cornell University)|Feb 11, 2026

Explainable Artificial Intelligence (XAI)被引用 0

一句话总结

论文评估了一个可解释的AI系统，用于分析医疗保健评价，发现当解释透明时，感知有用性和信任度较高，并给出分层次、面向受众的解释设计指南。

ABSTRACT

Patients increasingly rely on online reviews when choosing healthcare providers, yet the sheer volume of these reviews can hinder effective decision-making. This paper summarises a mixed-methods study aimed at evaluating a proposed explainable AI system that analyses patient reviews and provides transparent explanations for its outputs. The survey (N=60) indicated broad optimism regarding usefulness (82% agreed it saves time; 78% that it highlights essentials), alongside strong demand for explainability (84% considered it important to understand why a review is classified; 82% said explanations would increase trust). Around 45% preferred combined text-and-visual explanations. Thematic analysis of open-ended survey responses revealed core requirements such as accuracy, clarity and simplicity, responsiveness, data credibility, and unbiased processing. In addition, interviews with AI experts provided deeper qualitative insights, highlighting technical considerations and potential challenges for different explanation methods. Drawing on TAM and trust in automation, the findings suggest that high perceived usefulness and transparent explanations promote adoption, whereas complexity and inaccuracy hinder it. This paper contributes actionable design guidance for layered, audience-aware explanations in healthcare review systems.

研究动机与目标

• Motivate the need to help patients navigate large volumes of online healthcare reviews.
• Assess user demand for explainability and transparency in AI-assisted review analysis.
• Identify design requirements for accuracy, clarity, simplicity, responsiveness, data credibility, and unbiased processing.
• Provide actionable design guidance for layered explanations tailored to different audiences.

提出的方法

• Conduct a mixed-methods study with a patient-facing AI review analyst prototype.
• Run a survey (N=60) to assess perceived usefulness and demand for explanations.
• Perform thematic analysis of open-ended survey responses to extract core requirements.
• Conduct expert interviews to gain qualitative insights into explanation methods and challenges.
• Ground findings in Technology Acceptance Model (TAM) and trust in automation to link usefulness and explanations to adoption.

实验结果

研究问题

• RQ1 Do patients find an explainable AI system for healthcare reviews useful and time-saving?
• RQ2 Do users value explanations and trust signals accompanying AI classifications of reviews?
• RQ3 What are the core design requirements for accurate, clear, responsive, and unbiased explanations?
• RQ4 What technical and practical challenges do experts identify for different explanation methods?

主要发现

• 82% of respondents agreed the system saves time.
• 78% believed the system highlights essential information in reviews.
• 84% considered it important to understand why a review is classified by the AI.
• 82% said explanations would increase trust in the AI output.
• Around 45% preferred a combined text-and-visual explanation format.