Introduction: Artificial intelligence (AI) has developed into an increasingly important tool in dermatology. While new technologies integrated within laser devices are emerging, there is a lack of data on the applicability of publicly available AI models. Methods: The prospective study used an online questionnaire where participants evaluated diagnosis and treatment for 25 dermatological cases shown as pictures. The same questions were given to AI models: ChatGPT-4o, Claude Sonnet 4, Gemini 2.5 Flash, and Grok-3. Results: Dermatologists outperformed AI in diagnostic accuracy (suspected primary diagnosis-SD 75.6%) in pooled dermatologists vs. pooled AI (SD 57.0%), with laser specialists achieving the highest accuracy (SD 82.0%) and residents the lowest (SD 66.0%). There was a high heterogeneity across AI models. Gemini approached dermatologist performance (SD 72.0%), while Claude showed a low accuracy (SD 40.0%). While AI models reached near 100% accuracy in some classic/common diagnoses (e.g., acne, rosacea, spider angioma, infantile hemangioma), their accuracy dropped to near 0% on rare or context-dependent cases (e.g., blue rubber bleb nevus syndrome, angiosarcoma, hirsutism, cutaneous siderosis). Inter-rater agreement was high among laser experts in terms of diagnostic accuracy and treatment choice. Agreement between residents and AI models was highest for diagnostic accuracy and treatment choice, while it was lowest between experts and AI models. Conclusions: Before AI-based tools can be integrated into daily practice, particularly regarding diagnosis and appropriate laser treatment recommendations, specific supervised medical training of the AI model is necessary, as open-source platforms currently lack the ability to contextualize presented data.
Background/Objectives: Trichoscopy is an important diagnostic tool for hair and scalp disorders, but it requires significant expertise. Publicly available large language models (LLMs) are becoming more popular among both physicians and patients, yet their usefulness in trichology is unknown. We aimed to evaluate the diagnostic accuracy of four publicly available LLMs when interpreting trichoscopic images, as well as to compare their performance with that of dermatology residents, board-certified dermatologists, and trichology experts. Method: In this prospective comparative study, a preprocessed set of trichoscopic images was assessed in an online image-based survey. To reduced recognition bias from public image repositories, all images were structurally transformed while preserving diagnostic features. Fifteen dermatologists (five residents, four board-certified dermatologists, six trichology experts) provided a suspected diagnosis (SD), and up to three the differential diagnoses (DD). Four LLMs (ChatGPT-4o, Claude Sonnet 4, Gemini 2.5 Flash, and Grok-3) evaluated the images under the same conditions. Results: The overall diagnostic accuracy among 15 dermatologists was 58.1% (95% CI, 53.0–63.0) for SD and 68.3% (95% CI, 63.4–72.8) for SD + DD. Experts significantly outperformed residents and board-certified dermatologists. AI models achieved an accuracy of 18.2% (95% CI, 11.8–26.9) for SD and 44.4% (95% CI, 35.0–54.3) for SD + DD. Gemini 2.5 Flash performed best, with an accuracy of 62.5% for SD + DD. Agreement among dermatologists increased with experience (AC1 up to 0.65 for experts), while agreement among AI models was moderate to good (AC1 up to 0.70). Agreement between AI models and dermatologists was only slight to fair (AC1 = 0.06 for SD and 0.21 for SD + DD). All human-AI differences were statistically significant (p < 0.001). Conclusions: In trichology, publicly available LLMs currently underperform compared to human experts, especially in providing a single correct diagnosis. These models require further development and specialized training before they can reliably assist with trichological diagnoses in routine care.
Artificial intelligence (AI) shows promise in analyzing patterns of nail disease. This prospective, comparative study compared the diagnostic performance of dermatologists with that of large language models (LLMs). We evaluated the diagnostic accuracy of dermatologists and four freely available multimodal LLMs (GPT-4o, Grok 3, Claude Sonnet 4, and Gemini 2.5 Flash) using clinical images of nail diseases. Seventeen dermatologists correctly diagnosed the primary suspected diagnosis (SD) in 70.6% (95% CI: 65.5–75.2) of cases, and in 80.3% (95% CI: 75.7–84.2) of cases when considering both the SD and the differential diagnosis (SD + DD). Accuracy increased across dermatologist groups, ranging from residents (68.3% for SD + DD) to nail disease experts (96.0%). In comparison, AI models were correct in 25.0% (95% CI: 16.8–35.5) and 35.0% (95% CI: 25.5–45.9) of cases, respectively ( p < 0.001). The AI algorithms correctly classified 13.9% of tumors and 52.3% of non-tumors (SD + DD, p < 0.001). Current freely available general-purpose AI models demonstrated limited reliability for standalone nail disease diagnosis in this exploratory setting and should not be used without clinical supervision. While these systems may assist in suggesting differential diagnoses, their performance remains variable and requires further validation in larger, clinically representative datasets.