Mixed methods assessment of the influence of demographics on medical advice of ChatGPT.

OBJECTIVES: To evaluate demographic biases in diagnostic accuracy and health advice between generative artificial intelligence (AI) (ChatGPT GPT-4) and traditional symptom checkers like WebMD. MATERIALS AND METHODS: Combination symptom and demographic vignettes were developed for 27 most common symptom complaints. Standardized prompts, written from a patient perspective, with varying demographic permutations of age, sex, and race/ethnicity were entered into ChatGPT (GPT-4) between July and August 2023. In total, 3 runs of 540 ChatGPT prompts were compared to the corresponding WebMD Symptom Checker output using a mixed-methods approach. In addition to diagnostic correctness, the associated text generated by ChatGPT was analyzed for readability (using Flesch-Kincaid Grade Level) and qualitative aspects like disclaimers and demographic tailoring. RESULTS: ChatGPT matched WebMD in 91% of diagnoses, with a 24% top diagnosis match rate. Diagnostic accuracy was not significantly different across demographic groups, including age, race/ethnicity, and sex. ChatGPT's urgent care recommendations and demographic tailoring were presented significantly more to 75-year-olds versus 25-year-olds (P < .01) but were not statistically different among race/ethnicity and sex groups. The GPT text was suitable for college students, with no significant demographic variability. DISCUSSION: The use of non-health-tailored generative AI, like ChatGPT, for simple symptom-checking functions provides comparable diagnostic accuracy to commercially available symptom checkers and does not demonstrate significant demographic bias in this setting. The text accompanying differential diagnoses, however, suggests demographic tailoring that could potentially introduce bias. CONCLUSION: These results highlight the need for continued rigorous evaluation of AI-driven medical platforms, focusing on demographic biases to ensure equitable care.

Residual limbs of amputees are significantly cooler than contralateral intact limbs.

OBJECTIVE: To test the hypothesis that distal residual limbs (DRLs) have significant vasomotor abnormalities. DESIGN: Comparative surface temperature studies of DRLs using paired samples (DRL vs. similar site on intact contralateral limb). SUBJECTS/PATIENTS: Thirty-six volunteer subjects with unilateral, upper or lower limb amputations were recruited and evaluated at a pain research center in an urban academic rehabilitation facility. METHODS: Our main outcomes were subjects' residual limb temperature as measured by quantitative infrared telethermography (qIRT), temperature strips, and examiner's palpation, compared with the contralateral limb. RESULTS: The qIRT showed that the DRLs were significantly cooler than the corresponding area of the contralateral intact limbs (P < 0.01). The difference using temperature strips supported this finding (P < 0.05); while on physical examination, 39% of the residual limbs were perceived by the examiner as cooler than the corresponding unaffected limbs. CONCLUSIONS: DRLs as measured by qIRT were significantly cooler than the corresponding area of the contralateral intact limbs. A better understanding of these findings may be important in elucidating the pathophysiology of relevant clinical features such as a potential sympathetic component of postamputation pain.