Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals
This work addresses biases in AI for healthcare, which can impact equity, compliance, and patient trust, but it is incremental as it focuses on auditing existing models rather than proposing new solutions.
The study tackled the problem of demographic biases in vision-language models (VLMs) like CLIP and OpenCLIP, specifically in healthcare settings, by developing an evaluation protocol that quantifies these biases and finds consistent demographic skew across multiple roles and models.
Vision language models (VLMs), such as CLIP and OpenCLIP, can encode and reflect stereotypical associations between medical professions and demographic attributes learned from web-scale data. We present an evaluation protocol for healthcare settings that quantifies associated biases and assesses their operational risk. Our methodology (i) defines a taxonomy spanning clinicians and allied healthcare roles (e.g., surgeon, cardiologist, dentist, nurse, pharmacist, technician), (ii) curates a profession-aware prompt suite to probe model behavior, and (iii) benchmarks demographic skew against a balanced face corpus. Empirically, we observe consistent demographic biases across multiple roles and vision models. Our work highlights the importance of bias identification in critical domains such as healthcare as AI-enabled hiring and workforce analytics can have downstream implications for equity, compliance, and patient trust.