{"id":"W4415484344","doi":"10.1101/2025.10.22.25338548","title":"A Scoping Review of Algorithmic Equity, Data Diversity, and Inclusive Design in the Transformer Era of Clinical NLP","year":2025,"lang":"","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Canadian Institutes of Health Research; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Comparability; Audit; Health equity; Equity (law); Accountability; Health care; Health informatics; Citizen journalism","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.1158446,0.001696896,0.004493964,0.02571328,0.002442692,0.01024782,0.003995951,0.004343555,0.005203586],"category_scores_gemma":[0.3929832,0.001929565,0.006062715,0.02399498,0.006943348,0.009376623,0.007588717,0.004251853,0.0008718336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01077893,"about_ca_system_score_gemma":0.04305054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009324872,"about_ca_topic_score_gemma":0.01298007,"domain_scores_codex":[0.8989307,0.05392712,0.0292218,0.003907956,0.01278633,0.001226156],"domain_scores_gemma":[0.4969588,0.4270285,0.02448878,0.01352943,0.03675919,0.001235319],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001936231,0.00005873465,0.001435547,0.480109,0.002813025,0.0001839657,0.004250115,0.001345673,0.0003267457,0.03018462,0.01145533,0.4676436],"study_design_scores_gemma":[0.00003097352,0.00008370464,0.0008314046,0.886622,0.002886866,0.0001513419,0.001353564,0.0002993523,0.0003560157,0.01195133,0.0953921,0.00004146285],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001238283,0.9792262,0.006547308,0.007656055,0.0008495012,0.0006593115,0.0003309155,0.00005039292,0.003441975],"genre_scores_gemma":[0.02506897,0.9577022,0.01031754,0.003390074,0.0003932491,0.002167588,0.0004790461,0.00006749426,0.0004139074],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.996004,"threshold_uncertainty_score":0.6126519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5553745600691103,"score_gpt":0.5782441597974315,"score_spread":0.02286959972832114,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}