The use of a ChatGPT‐4‐based chatbot in teledermatology: A retrospective exploratory study
Bibliographic record
Abstract
BACKGROUND AND OBJECTIVES: Integration of artificial intelligence in healthcare, particularly ChatGPT, is transforming medical diagnostics and may benefit teledermatology. This exploratory study compared image description and differential diagnosis generation by a ChatGPT-4 based chatbot with human teledermatologists. PATIENTS AND METHODS: This retrospective study compared 154 teledermatology consultations (December 2023-February 2024) with ChatGPT-4's performance in image descriptions and diagnoses. Diagnostic concordance was classified as "Top1" (exact match with the teledermatologist's diagnoses), "Top3" (correct diagnosis within one the top three diagnoses), and "Partial" (similar but not identical diagnoses). Image descriptions were rated and compared for quality parameters (location, color, size, morphology, and surrounding area), and accuracy (Yes, No, and Partial). RESULTS: Out of 154 cases, ChatGPT-4 achieved a Top1 diagnostic concordance in 108 (70.8%), Top3 concordance in 137 (87.7%), partial concordance in four (2.6%), and was discordant in 15 (9.7%) cases. The quality of ChatGPT-4's image descriptions significantly surpassed teledermatologists in all five parameters. ChatGPT-4's descriptions were accurate in 130 (84.4%), partially accurate in 22 (14.3%), and inaccurate in two (1.3%) cases. CONCLUSIONS: The preliminary findings of this study indicate that ChatGPT-4 demonstrates potential in generating accurate image descriptions and differential diagnoses. These results highlight the promise of integrating artificial intelligence into asynchronous teledermatology workflows.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".