{"id":"W3216069892","doi":"10.1111/biom.13611","title":"Supervised Two-Dimensional Functional Principal Component Analysis with Time-to-Event Outcomes and Mammogram Imaging Data","year":2021,"lang":"en","type":"article","venue":"Biometrics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Actua; Simon Fraser University","funders":"National Cancer Institute; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Principal component analysis; Breast cancer; Mammography; Censoring (clinical trials); Computer science; Artificial intelligence; Population; Data set; Medicine; Event (particle physics); Pattern recognition (psychology); Data mining; Machine learning; Statistics; Cancer; Mathematics; Pathology; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004695674,0.000173391,0.0002645381,0.001648629,0.0001623638,0.0002604435,0.000560251,0.00003167456,0.0001105021],"category_scores_gemma":[0.00009266285,0.0001496544,0.00006680948,0.01090633,0.00004669391,0.0003808736,0.001348209,0.0001066424,0.00007008226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462472,"about_ca_system_score_gemma":0.0001506672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005876692,"about_ca_topic_score_gemma":0.00002345131,"domain_scores_codex":[0.9977223,0.00007061693,0.0002525212,0.0008278781,0.0008493338,0.0002773798],"domain_scores_gemma":[0.9981346,0.0002203942,0.00008471104,0.001102106,0.0002523497,0.0002058376],"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":[0.0001120782,0.0008526732,0.548186,0.00005688825,0.002449897,0.0003337135,0.0001699898,0.02842569,0.007391555,0.0005748289,0.005397693,0.406049],"study_design_scores_gemma":[0.0008877977,0.00006873774,0.4075528,0.000009785799,0.0002249309,0.00007804562,0.00001051647,0.5803978,0.0006979465,0.00003320822,0.009690989,0.000347437],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.163152,0.0004584392,0.8330002,0.002425216,0.0004204194,0.0001792704,0.00007531931,0.0001758366,0.0001132727],"genre_scores_gemma":[0.7658154,0.000008147907,0.232133,0.0009894454,0.0001091788,0.00001818475,0.0003118591,0.00002235459,0.0005924305],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6026634,"threshold_uncertainty_score":0.6102728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03557363428132682,"score_gpt":0.2781117748046347,"score_spread":0.2425381405233079,"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."}}