{"id":"W4390837850","doi":"10.1038/s41598-024-51723-2","title":"AI improves accuracy, agreement and efficiency of pathologists for Ki67 assessments in breast cancer","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; St. Michael's Hospital; Princess Margaret Cancer Centre; University Health Network; Toronto Metropolitan University; University of Toronto","funders":"Mitacs","keywords":"Medicine; Breast cancer; Kappa; Concordance; Turnaround time; Reproducibility; Consistency (knowledge bases); Diagnostic accuracy; Cohen's kappa; Cancer; Medical physics; Internal medicine; Artificial intelligence; Machine learning; Computer science; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.09913851,0.0006555998,0.001008007,0.004650067,0.001029032,0.002928308,0.001066933,0.0009623716,0.001233078],"category_scores_gemma":[0.2045149,0.0005481939,0.001104428,0.002453295,0.001128236,0.00292486,0.003610139,0.001013451,0.0009286773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001263756,"about_ca_system_score_gemma":0.001395702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002236514,"about_ca_topic_score_gemma":0.003149626,"domain_scores_codex":[0.9055753,0.06164389,0.008889367,0.006774736,0.01524726,0.001869337],"domain_scores_gemma":[0.7266542,0.1824863,0.02724615,0.01833913,0.04269551,0.002578694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002787575,0.000302346,0.6425567,0.0008017528,0.0006891415,0.0001934298,0.01129747,0.00260766,0.008019329,0.0009053721,0.002479196,0.3273601],"study_design_scores_gemma":[0.00008626778,0.001940367,0.9435512,0.0004156275,0.000545187,0.000973931,0.004931504,0.02049246,0.01400661,0.004097612,0.008689201,0.0002700697],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9248179,0.003562988,0.05406262,0.001181255,0.0003162629,0.0004992592,0.0003063117,0.0007450773,0.01450827],"genre_scores_gemma":[0.9644983,0.0006197494,0.0328487,0.0002331748,0.000140827,0.0001289727,0.0002221226,0.0001047546,0.0012033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09913851,"threshold_uncertainty_score":0.5243008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01751447108590855,"score_gpt":0.3350775172729329,"score_spread":0.3175630461870244,"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."}}