{"id":"W3168184531","doi":"10.1109/tim.2021.3085956","title":"A Diagnostic Biomarker for Breast Cancer Screening <i>via</i> Hilbert Embedded Deep Low-Rank Matrix Approximation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Breast cancer; Rank (graph theory); Computer science; Mathematics; Cancer; Medicine; Combinatorics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003351629,0.0002264187,0.0002756402,0.0002299687,0.0002524332,0.00003632945,0.00004071024,0.00009906349,0.0003918956],"category_scores_gemma":[0.00002684214,0.0002148916,0.0001529531,0.0003567727,0.00007101065,0.0001517047,9.728928e-7,0.0001623245,0.000004971336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002013495,"about_ca_system_score_gemma":0.0001226262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004332398,"about_ca_topic_score_gemma":0.00007098725,"domain_scores_codex":[0.9982145,0.00006840814,0.0004147533,0.0003630881,0.0006715542,0.0002677345],"domain_scores_gemma":[0.9988829,0.0001010196,0.0001124299,0.0002151004,0.0005055912,0.0001829843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00138061,0.000777256,0.001008084,0.0007276568,0.0008390133,0.00001605211,0.00132276,0.0006739521,0.1792224,0.00004730869,0.0002731874,0.8137118],"study_design_scores_gemma":[0.04799764,0.001227992,0.08834049,0.004951268,0.004476412,0.001171912,0.005694514,0.0405081,0.8022915,0.000403334,0.001447282,0.001489536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1043688,0.0003639093,0.8897456,0.002863487,0.0008218993,0.001431585,0.0001234215,0.00009867947,0.0001826486],"genre_scores_gemma":[0.99029,0.0003330627,0.007057751,0.001280945,0.00009674513,0.000747406,0.0000528315,0.00003853361,0.0001027619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8859212,"threshold_uncertainty_score":0.8763025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02782245041002921,"score_gpt":0.290972111596892,"score_spread":0.2631496611868627,"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."}}