{"id":"W4309778459","doi":"10.1002/prm2.12089","title":"Using ensemble learning and genetic algorithm on magnetic resonance imaging radiomics to classify molecular subtypes of breast cancer","year":2022,"lang":"en","type":"article","venue":"Precision Medical Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Council; Ministry of Science and Technology, Taiwan; Ministry of Education","keywords":"Magnetic resonance imaging; Breast cancer; Triple-negative breast cancer; Ensemble learning; Progesterone receptor; Radiomics; Cancer; Estrogen receptor; Medicine; Artificial intelligence; Algorithm; Oncology; Machine learning; Internal medicine; Computer science; Radiology","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":[0.001758946,0.001013741,0.001171056,0.001621649,0.0004428546,0.0007247218,0.0007258204,0.0008139334,0.0004970642],"category_scores_gemma":[0.003176926,0.0002571797,0.001131412,0.0008646317,0.0002184378,0.0006146793,0.0005112289,0.0008568673,0.0002073591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006515438,"about_ca_system_score_gemma":0.0007510773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008603004,"about_ca_topic_score_gemma":0.006167916,"domain_scores_codex":[0.999376,0.0002316536,0.00004795945,0.0001629538,0.00009587413,0.00008552974],"domain_scores_gemma":[0.9986672,0.0007379671,0.00009198493,0.0001166947,0.0003224776,0.00006355037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002331887,0.0003708274,0.02946568,0.00004013142,0.000375765,0.0001190917,0.00005667268,0.7091644,0.002233231,0.0004725659,0.002694729,0.2547738],"study_design_scores_gemma":[0.000005203987,0.00005135892,0.001384592,0.000005840096,0.00003748336,0.00001912293,0.000008151868,0.9974844,0.0004962693,0.0003696446,0.0001323876,0.000005527841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6708504,0.002282155,0.3212664,0.0007408627,0.0002411212,0.0001282865,0.0005704297,0.001531762,0.002388571],"genre_scores_gemma":[0.9663244,0.0002549699,0.0314119,0.0001210739,0.00005625725,0.00006287415,0.0008399066,0.00002732269,0.0009013921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008603004,"threshold_uncertainty_score":0.01710588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01754007560777322,"score_gpt":0.3318394478027785,"score_spread":0.3142993721950053,"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."}}