{"id":"W4413986381","doi":"10.1080/10408363.2025.2549309","title":"Large scale implementation of DP for clinical diagnoses: experience, challenges, and lessons learned","year":2025,"lang":"en","type":"review","venue":"Critical Reviews in Clinical Laboratory Sciences","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Scale (ratio); Medical diagnosis; Data science; Computer science; Medical physics; Medicine; Geography; Cartography; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02070366,0.0004737402,0.003511285,0.0003355861,0.0002492486,0.0001567135,0.002124443,0.0006121664,0.00002324233],"category_scores_gemma":[0.0207946,0.0003728613,0.0007273511,0.001827122,0.001933636,0.0007723699,0.0007592273,0.0008042826,0.00001323889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008598782,"about_ca_system_score_gemma":0.001926762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004052976,"about_ca_topic_score_gemma":0.0001355935,"domain_scores_codex":[0.9888924,0.003125874,0.004666175,0.002081544,0.0005331032,0.0007008607],"domain_scores_gemma":[0.9767265,0.02063021,0.0009535102,0.001050819,0.0003344126,0.0003045104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002037481,0.0001631756,0.0001420721,0.009070165,0.000009069214,0.000001826132,0.0001323609,2.279497e-8,2.126152e-8,0.04298767,0.00050813,0.9469835],"study_design_scores_gemma":[0.0003308939,0.0005101726,0.0001991879,0.01356204,0.0001300437,0.000001467951,0.0003282487,0.00005003698,9.633519e-7,0.004563554,0.9799527,0.0003707087],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001310893,0.9863232,0.007962902,0.001125984,0.002341904,0.001857186,0.0001331152,0.0000494675,0.0001931534],"genre_scores_gemma":[0.00004330951,0.982153,0.01601729,0.0004273934,0.0002757241,0.001049194,0.000005043857,0.00001540313,0.0000136321],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9794446,"threshold_uncertainty_score":0.9998723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4443458344913378,"score_gpt":0.6195860533763532,"score_spread":0.1752402188850154,"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."}}