{"id":"W4392949341","doi":"10.21203/rs.3.rs-4004164/v1","title":"Validating Large Language Models for Identifying Pathologic Complete Responses After Neoadjuvant Chemotherapy for Breast Cancer Using a Population-Based Pathologic Report Data","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breast cancer; Chemotherapy; Medicine; Oncology; Neoadjuvant therapy; Population; Cancer; Pathology; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"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":[0.009143117,0.0009852387,0.0007310354,0.001844071,0.000465353,0.001374411,0.001282051,0.001305764,0.001495489],"category_scores_gemma":[0.0270523,0.0004516704,0.001863265,0.001099267,0.0005165935,0.001319085,0.001069883,0.00179157,0.001062144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033084,"about_ca_system_score_gemma":0.001752215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008391785,"about_ca_topic_score_gemma":0.01107802,"domain_scores_codex":[0.9966635,0.001815095,0.0002605257,0.0007787305,0.0003235833,0.0001584262],"domain_scores_gemma":[0.9557545,0.03980734,0.001122678,0.001755206,0.001203838,0.0003564317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00386214,0.002802168,0.4257001,0.0007095843,0.002875101,0.001389874,0.0008998092,0.2841563,0.01084655,0.002363856,0.0198868,0.2445077],"study_design_scores_gemma":[0.0002088024,0.0005497771,0.03448727,0.00006146303,0.0004709939,0.0004584685,0.0002731168,0.9533509,0.003064811,0.004918564,0.002103313,0.00005253828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.899721,0.001001645,0.07632035,0.001949442,0.0001810925,0.0002892984,0.01659128,0.002715933,0.001229995],"genre_scores_gemma":[0.9499948,0.0001897531,0.02836747,0.0002883891,0.00009500561,0.0002419457,0.02000908,0.00009123488,0.0007222582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009143117,"threshold_uncertainty_score":0.04835397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2879053930948052,"score_gpt":0.4922161359139098,"score_spread":0.2043107428191046,"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."}}