Sensing but not alerting: ChatGPT mental health triage gaps in simulated psychodermatology conversations
Mohammad Iqbal Nouyed, Lauren E Kozlowski, Evelyn Shue, Alexsandra E Smith, Dilip N Chandran, Daniel E Elswick, Michael S Kolodney, Wanhong Zheng, Gangqing Hu · 2026
Read Sensing but not alerting: ChatGPT mental health triage gaps in simulated psychodermatology conversations by Mohammad Iqbal Nouyed, Lauren E Kozlowski, Evelyn Shue, Alexsandra E Smith, Dilip N Chandran, Daniel E Elswick, Michael S Kolodney, Wanhong Zheng, Gangqing Hu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13400423.txt.
Description
Mohammad Iqbal Nouyed and colleagues test, in 2026, how well ChatGPT handles mental health warning signs hidden in skin complaints. People with skin disease often face anxiety or depression, and some beliefs about infestation reflect psychosis. An overly agreeable chatbot might miss danger or even reinforce false beliefs.
The team fed the chatbot 50 short patient stories, section by section, and repeated each run three times. Psychiatrists had judged which stories needed referral. Focusing on 28 clear cases, the chatbot voiced concern in most chats yet advised mental health follow-up in only about half. It almost always advised skin follow-up instead. In some delusional cases it even suggested collecting specimens, which could entrench false beliefs.
Catalog record
| CREATOR | Mohammad Iqbal Nouyed, Lauren E Kozlowski, Evelyn Shue, Alexsandra E Smith, Dilip N Chandran, Daniel E Elswick, Michael S Kolodney, Wanhong Zheng, Gangqing Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 7584 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |