Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR Dermatology

Date Submitted: Nov 2, 2026
Open Peer Review Period: Nov 17, 2026 - Jan 12, 2027
(currently open for review)

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Expert Evaluation of AI-Generated Responses to Hair Loss Questions Across Two Models: Comparative Evaluation Study

  • Frieda Anastopulos; 
  • Elika D. Javaheri; 
  • Jasmine Monge; 
  • Rewan M. Abdelwahab; 
  • Reese Imhof; 
  • Julio C. Sartori-Valinotti; 
  • Carilyn Wieland; 
  • Sindhuja Sominidi-Damodaran

ABSTRACT

Background:

Hair loss is a common dermatologic concern, of which androgenetic alopecia (AGA) and telogen effluvium (TE) are two common etiologies. Accurate diagnosis requires dermatologic examination and histopathology. With barriers to access care, patients are increasingly turning to artificial intelligence (AI). The clinical accuracy of AI remains uncertain.

Objective:

Assess AI responses on TE, AGA, and alopecia by board-certified dermatologists.

Methods:

Two AI foundation models were queried for 43 questions regarding TE, AGA, and hair loss broadly. Four board-certified dermatologists evaluated each response in a blinded manner for accuracy, relevance, appropriateness, word length, and readability (Flesch Kincaid Reading Ease).

Results:

For appropriateness, AI achieved a perfect 5/5 score on the majority of questions. For accuracy and relevance, AI achieved this threshold on the minority of questions. ChatGPT responses were significantly more relevant than Copilot responses overall, and particularly with the general alopecia subset of responses. ChatGPT generated significantly longer responses than Copilot. ChatGPT generated a significant difference in readability and wordcount across the three question topics.

Conclusions:

AI can generate appropriate responses to hair loss questions, which often lack individualized, evidence-based guidance. AI-generated content should not serve as a substitute for professional dermatologic evaluation. Ongoing clinical oversight of AI-generated medical content is essential to ensure safe and context-appropriate use.


 Citation

Please cite as:

Anastopulos F, Javaheri ED, Monge J, Abdelwahab RM, Imhof R, Sartori-Valinotti JC, Wieland C, Sominidi-Damodaran S

Expert Evaluation of AI-Generated Responses to Hair Loss Questions Across Two Models: Comparative Evaluation Study

JMIR Preprints. 02/11/2026:116007

DOI: 10.2196/preprints.116007

URL: https://preprints.jmir.org/preprint/116007

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.