{"id":"W2530808190","doi":"10.1016/j.compbiomed.2016.10.007","title":"Influence of feature set reduction on breast cancer malignancy classification of fine needle aspiration biopsies","year":2016,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Grading (engineering); Malignancy; Feature selection; Pattern recognition (psychology); Artificial intelligence; Computer science; Breast cancer; Feature (linguistics); Support vector machine; Biopsy; Cancer; Radiology; Medicine; Pathology; Internal medicine; Biology","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":[0.0002035787,0.00008769376,0.0001827964,0.0001975879,0.00002769624,0.000001736177,0.0001732233,0.0001089864,0.000003045972],"category_scores_gemma":[0.00002787802,0.00005603622,0.0000127548,0.0003036421,0.0002994265,0.0001478259,0.00004325763,0.00007105311,4.987249e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005269936,"about_ca_system_score_gemma":0.00003161579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000785197,"about_ca_topic_score_gemma":0.00001587228,"domain_scores_codex":[0.9992843,0.00006770209,0.0002238732,0.0002492861,0.00007386864,0.0001010041],"domain_scores_gemma":[0.9993538,0.00009123642,0.0002071613,0.0002195199,0.0001023633,0.0000259682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001219229,0.00003562435,0.0307012,0.00006752826,0.00001976712,8.289421e-7,0.0008393365,0.0004002856,0.4506908,0.01956285,0.0008156119,0.4967442],"study_design_scores_gemma":[0.001216669,0.001014993,0.9665865,0.001182247,0.000009867791,0.00005216363,0.00003709163,0.002943857,0.02132838,0.005202238,0.0002969251,0.0001290754],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9343165,0.0003900069,0.05428553,0.01013617,0.000664059,0.0001300671,0.000009399444,0.0000261664,0.00004216001],"genre_scores_gemma":[0.9979978,0.0002860841,0.001461932,0.00009891186,0.0001204563,0.00001235651,0.000003059381,0.000002730601,0.00001663047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9358853,"threshold_uncertainty_score":0.2285091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02139307801496854,"score_gpt":0.3048476643038641,"score_spread":0.2834545862888955,"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."}}