Derma Synth: GPT-4-Based Synthetic Text Generation for Dermatology via Meta-Prompting and Few-Shot Conditioning
Natural Resources for Human Health · 23.10.2026 · 6 (19s) · 160-175
DOI: 10.53365/nrfhh.3925 ↗Kurz gefasst
Fachartikel in der Zeitschrift Natural Resources for Human Health, online erschienen am 23.10.2026. Verfasst von Divya Mishra.
Abstract (Originalsprache)
Automated classification of dermatological conditions from free text is limited by the scarcity of labelled clinical and patient-narrative corpora. We present DermaSynth, a meta-prompting framework that uses GPT-4 to expand a seed set of 67 real dermatology texts into a synthetic dataset of 653 labelled texts covering seven conditions (acne, contact dermatitis, eczema, folliculitis, psoriasis, scabies and vitiligo; 82–100 texts per class). Generation combines a dermatologist-persona context prompt, a diversity prompt, and in-context exemplars drawn from the seed set (k ∈ {2, 4, 6, 8}). We evaluate the dataset with Random Forest (RF) and Multinomial Naïve Bayes (MNB) classifiers under repeated stratified cross-validation, and through ratings by three board-certified dermatologists. RF reaches 94.55 ± 0.55% accuracy (macro-F1 0.944) and MNB 91.58 ± 0.45% (macro-F1 0.915) in 5×5 cross-validation, and the RF advantage is statistically significant on paired predictions (McNemar p = 0.003). However, 58.7% of the texts name their own disease, and masking the names lowers accuracy to 84.6% (RF) and 83.5% (MNB), so about 8–10 points of accuracy come from keyword cues. Texts also have a low length (mean 21.7 words), while contact dermatitis is very templated. Data was evaluated 4.53/5 by dermatologists on four different dimensions (realism 4.3/5). All classification results are on synthetic text; transfer to real patient text remains to be tested.
Zitieren
APA
Mishra, D. (2026). Derma Synth: GPT-4-Based Synthetic Text Generation for Dermatology via Meta-Prompting and Few-Shot Conditioning. Natural Resources for Human Health, 6(19s), 160-175. https://doi.org/10.53365/nrfhh.3925
Vancouver
Mishra D. Derma Synth: GPT-4-Based Synthetic Text Generation for Dermatology via Meta-Prompting and Few-Shot Conditioning. Natural Resources for Human Health. 2026;6(19s):160-175. doi:10.53365/nrfhh.3925
BibTeX
@article{Mishra2026,
author = {Mishra, Divya},
title = {Derma Synth: GPT-4-Based Synthetic Text Generation for Dermatology via Meta-Prompting and Few-Shot Conditioning},
journal = {Natural Resources for Human Health},
year = {2026},
volume = {6},
number = {19s},
pages = {160--175},
doi = {10.53365/nrfhh.3925}
}
EUVIMED