{"id":"W7117450076","doi":"10.1017/s0266462325101487","title":"PD11 First Comprehensive Assessment Of Artificial Intelligence At Canada’s Drug Agency: Evidence Review Methods, Lessons Learned, And Next Steps","year":2025,"lang":"en","type":"article","venue":"International Journal of Technology Assessment in Health Care","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Health technology; Medical diagnosis; MEDLINE; Digital health; Agency (philosophy); Health information technology; Equity (law); Clinical decision support system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09091756,0.002539027,0.005350831,0.02072257,0.003331236,0.01531429,0.005999198,0.00662353,0.01812018],"category_scores_gemma":[0.2466723,0.001850261,0.007688069,0.01674803,0.002709214,0.005927483,0.006111698,0.00718449,0.003049635],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.07836022,"about_ca_system_score_gemma":0.297953,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4783387,"about_ca_topic_score_gemma":0.6457086,"domain_scores_codex":[0.923696,0.02531979,0.01060408,0.002817759,0.03425897,0.003303337],"domain_scores_gemma":[0.6358599,0.1327135,0.02248598,0.00765634,0.1924428,0.008841457],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0004775943,0.0001325268,0.001602651,0.3288728,0.002305999,0.0001395886,0.0006834317,0.0005990312,0.0002858782,0.008596256,0.2920311,0.364273],"study_design_scores_gemma":[0.0002299659,0.0001336808,0.003351273,0.6554728,0.002821587,0.00008078013,0.0003673446,0.0002461629,0.0002641001,0.001748852,0.3352004,0.00008312655],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0008172652,0.883472,0.002378709,0.07519981,0.005093954,0.00626225,0.009343788,0.0002385176,0.01719384],"genre_scores_gemma":[0.01957315,0.8857508,0.03031386,0.04005663,0.001674421,0.007980016,0.007910753,0.000153333,0.006586953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9216398,"threshold_uncertainty_score":0.9511089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2283317725034829,"score_gpt":0.5685770173104113,"score_spread":0.3402452448069284,"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."}}