# ChatGPT-4’s Level of Dermatological Knowledge Based on Board Examination Review Questions and Bloom’s Taxonomy

**Authors:** Hansen Tai, Carrie Kovarik

PMC · DOI: 10.2196/74085 · JMIR Dermatology · 2025-08-07

## TL;DR

ChatGPT-4 correctly answers most dermatology board questions, but struggles with higher-order thinking and needs better visual diagnostic skills.

## Contribution

This study evaluates ChatGPT-4's dermatological knowledge using board questions and Bloom’s Taxonomy.

## Key findings

- ChatGPT-4 answered 77.5% of dermatology board review questions correctly.
- Performance decreased with higher-order thinking requirements.
- Visual diagnostic capabilities need improvement for clinical use.

## Abstract

Our study demonstrated the ability of ChatGPT-4 to answer 77.5% of all sampled text-based board review type questions correctly. Questions requiring the recall of factual information were answered correctly most often, with slight decreases in correctness as higher-order thinking requirements increased. Improvements to ChatGPT’s visual diagnostics capabilities will be required before it can be used reliably for clinical decision-making and visual diagnostics.

## Full-text entities

- **Genes:** CMPK1 (cytidine/uridine monophosphate kinase 1) [NCBI Gene 51727] {aka CK, CMK, CMPK, UMK, UMP-CMPK, UMPK}

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12331215/full.md

## References

5 references — full list in the complete paper: https://tomesphere.com/paper/PMC12331215/full.md

---
Source: https://tomesphere.com/paper/PMC12331215