{"id":"W3096190465","doi":"10.1158/1538-7445.tumhet2020-po-080","title":"Abstract PO-080: Predicting relapse in patients with triple negative breast cancer (TNBC) using a deep-learning approach","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Cohort; Triple-negative breast cancer; Breast cancer; Medicine; Tumor-infiltrating lymphocytes; Oncology; Internal medicine; Cancer; Artificial intelligence; Machine learning; Computer science; Immunotherapy","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":[0.0003623328,0.000436685,0.0003528197,0.0006718183,0.0001389005,0.0003585964,0.0004381454,0.0005368551,0.00103391],"category_scores_gemma":[0.0008094342,0.0001276114,0.0002766465,0.0002393108,0.0001192101,0.0002056745,0.0003484924,0.0003123909,0.000255424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003744597,"about_ca_system_score_gemma":0.0003647281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005428838,"about_ca_topic_score_gemma":0.005055739,"domain_scores_codex":[0.999907,0.0000241941,0.000006435361,0.00002323353,0.00001440813,0.00002469016],"domain_scores_gemma":[0.9998161,0.00005933471,0.00002450379,0.00001043157,0.00004562089,0.0000438849],"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":[0.002586071,0.001217281,0.5443026,0.0001281407,0.0002002838,0.0008954168,0.00009646433,0.10671,0.02167649,0.0003077831,0.007586763,0.3142927],"study_design_scores_gemma":[0.0000452575,0.0003786357,0.0754598,0.00001499573,0.00005324191,0.000251559,0.00005782254,0.9192854,0.003581668,0.0004198054,0.0004388079,0.00001302347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890576,0.0003035517,0.008706815,0.0003085361,0.00002544695,0.00003826978,0.0004377888,0.0002731128,0.0008488696],"genre_scores_gemma":[0.9940234,0.00006207945,0.004615222,0.00005442737,0.00001656844,0.0000208595,0.0006881797,0.000006503635,0.0005127083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005428838,"threshold_uncertainty_score":0.01079452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0651865803646133,"score_gpt":0.3564657935200026,"score_spread":0.2912792131553893,"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."}}