Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Designing Medical Chatbots where Accuracy and Acceptability are in Conflict: An Exploratory, Vignette-based Study in Urban India

Ananditha Raghunath, William Thies, Mohit Jain

Abstract

When medical chatbots provide advice that conflicts with users' lived care experiences, users are left to interpret, negotiate, and evaluate the legitimacy of that guidance. In India, the widespread overuse of antibiotics, antidiarrheals, and injections has shifted patient expectations away from the guideline-aligned advice that chatbots are trained to provide. We present a mixed-methods, vignette-based study with 200 urban Indian adults examining preferences for and against guideline-aligned, norm-divergent advice in chatbot transcripts. We find that a majority of users reject such advice, drawing on diverse rationales grounded in their lived expectations. Through the design and introduction of context-aware nudges, we support expectation alignment that shifts preferences towards transcripts containing guideline-aligned advice. In doing so, we surface key tensions in the equitable design of medical chatbots in the Global South.

Designing Medical Chatbots where Accuracy and Acceptability are in Conflict: An Exploratory, Vignette-based Study in Urban India

Abstract

When medical chatbots provide advice that conflicts with users' lived care experiences, users are left to interpret, negotiate, and evaluate the legitimacy of that guidance. In India, the widespread overuse of antibiotics, antidiarrheals, and injections has shifted patient expectations away from the guideline-aligned advice that chatbots are trained to provide. We present a mixed-methods, vignette-based study with 200 urban Indian adults examining preferences for and against guideline-aligned, norm-divergent advice in chatbot transcripts. We find that a majority of users reject such advice, drawing on diverse rationales grounded in their lived expectations. Through the design and introduction of context-aware nudges, we support expectation alignment that shifts preferences towards transcripts containing guideline-aligned advice. In doing so, we surface key tensions in the equitable design of medical chatbots in the Global South.
Paper Structure (25 sections, 1 figure, 3 tables)

This paper contains 25 sections, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methods
  4. Study Context and Participants
  5. Vignette Design
  6. Study Procedure
  7. Analysis
  8. Ethical Considerations & Threats to Validity
  9. Results
  10. Phase 1: Verity vs Max
  11. Quantitative Results
  12. Qualitative Results
  13. Tangible Outcomes as a Basis for Legitimacy
  14. Alignment with Perceived Impact of Treatment as a Basis for Legitimacy
  15. Cues of Medical Authority as a Basis for Legitimacy
  16. ...and 10 more sections

Figures (1)

  • Figure 1: Pane A depicts a common message that was shown to participants across bots for the Cold scenario. On the right, pane B shows Verity's treatment, pane C shows Max's treatment message, and pane D shows Clarity's treatment message. Each participant was shown two full side-by-side screenshots, this figure is compressed for reader reference.