FemHealth adds equity-aware metadata to medical research results — participant balance, exclusion patterns, and bias signals that standard databases bury in abstracts or omit entirely.
FemHealth searches PubMed (NCBI E-utilities), Europe PMC (EMBL-EBI), and OpenAlex simultaneously. Each database returns 20–25 results per search; results are deduplicated and ranked by relevance.
For each result, FemHealth analyses the abstract to extract participant counts by sex, detects exclusion language (e.g. "pregnant women excluded", "male participants only"), and calculates a gender balance score from 0–100. Studies with fewer than 40% female participants are flagged with moderate or critical gender bias.
Sample sizes are extracted from abstracts using pattern matching on common reporting formats. When participant sex breakdown is explicitly reported (e.g. "n=120 women, n=80 men"), FemHealth surfaces this in the result card — before the user opens the paper.
Research quality is assessed using a multi-factor model considering: study type (systematic review > RCT > cohort > case study), peer review status, citation count, publication recency, and open access availability.
FemHealth scans abstracts and methods sections for common exclusion patterns: pregnancy exclusion, breastfeeding exclusion, age-range restrictions, and hormonal contraceptive exclusion — flagging them in every result card.
Gender data extraction is only as good as what is reported in the abstract. Many studies do not report sex breakdowns in the abstract, leading to "data unavailable" indicators. This is itself a signal: non-reporting is common in older studies and certain journals.