Chatbot Performance Assessment on Multiple Sclerosis Questions Using DISCERN-AI

Meisam Dastani created a 5.5 KB Excel dataset evaluating chatbot responses to medical questions about multiple sclerosis. The assessment uses the DISCERN-AI criteria, a tool for judging the quality of AI-generated health information. The dataset was last updated on May 11, 2026.

Use Cases

• Benchmarking chatbot performance based on DISCERN-AI criteria scores mentioned in the description
• Analyzing the quality of AI-generated medical answers for specific MS-related topics
• Training or fine-tuning AI models to improve the reliability of health information responses

Strengths

• Dataset is small (5.5 KB), facilitating quick download and initial analysis
• Uses the DISCERN-AI criteria, a recognized framework for evaluating AI health information
• Released under a permissive CC-BY-4.0 license, allowing for broad reuse

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

figshare

Collection Method

Assessment of chatbot performance using DISCERN-AI criteria.

Freshness

Last updated 2026-05-11 17:38:22; freshness should be verified