QualitativeJMIR rehabilitation and assistive technologies2025

Use of ChatGPT for Urinary Symptom Management Among People With Spinal Cord Injury or Disease: Qualitative Study.

Bat-Zion Hose, Amanda K Rounds, Ishaan Nandwani and 5 others

PMID 40440564

WHAT IT FOUND

People with spinal cord injury used ChatGPT to interpret urinary symptoms and decide when to seek care.

They found advice clear but too generic, lacking personal health history. Most agreed with the AI but still relied on doctors for final decisions.

Key findings

01Participants used ChatGPT to evaluate specific urinary symptoms like cloudiness and odor, and to decide when to seek professional help.

02While most participants agreed with ChatGPT's advice, they found it too general because it lacked access to their personal medical records.

03ChatGPT was viewed as a complementary resource for verifying knowledge, not a replacement for professional medical care.

STILL TO COME

How it was doneWhat they found

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The sample was predominantly White (27 of 30) and technologically proficient (29 of 30), limiting generalizability to other demographic groups. Participants were experienced in managing their condition, so findings may not apply to newly diagnosed individuals. The study used remote scenario-based testing, which did not observe real-world contextual factors. The study did not assess clinical outcomes, only perceptions and self-reported decision-making.

Declared interests

The study was approved by the MedStar Health Research Institute Institutional Review Board. Participants received US $50 compensation. No specific commercial conflicts of interest were declared in the provided text.

The easy way to misread this

Do not assume ChatGPT is safe or accurate for clinical decision-making. The study reports user perceptions, not the AI's actual accuracy or error rate, and participants explicitly noted the advice lacked personalization.

Read it on PubMed →


The study

Participants
30
Certainty of evidence
Very low

Browse

    Cite

    Bat-Zion Hose, Amanda K Rounds, Ishaan Nandwani, et al. Use of ChatGPT for Urinary Symptom Management Among People With Spinal Cord Injury or Disease: Qualitative Study. JMIR rehabilitation and assistive technologies. 2025.

    Read the original