AI and Preeclampsia — Learning from Black Women's Clinical Narratives for Equitable Models
OVERVIEWBoston Medical Center has published work examining what AI systems can learn from Black women's lived experiences and clinical stories of preeclampsia — a serious pregnancy complication for which Black women face disproportionately high rates of morbidity and mortality. The initiative highlights a methodological gap in AI model development: training datasets often underrepresent the clinical presentations and risk factors most common in marginalized populations. The approach emphasizes narrative data — patient stories and qualitative accounts — as a source of signal that structured clinical data may miss. Black women's experiences of preeclampsia frequently involve delayed diagnosis, dismissed symptoms, and care patterns that differ from those of white patients, meaning AI models trained predominantly on majority-population data may perpetuate or amplify these disparities. This work contributes to a broader movement in health AI equity research that argues technical accuracy on aggregate benchmarks is insufficient if performance varies systematically across racial and ethnic groups. Incorporating community narratives into model development is proposed as one mechanism to build more representative and equitable clinical AI. ---
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.