{"id":"W3006953361","doi":"10.1200/jco.2020.38.6_suppl.294","title":"Deep learning-based approach for automated assessment of PTEN status.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"PTEN; Prostate cancer; Medicine; Artificial intelligence; Biomarker; Machine learning; Cancer; Computer science; Internal medicine; Biology","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":[0.001190923,0.001032645,0.0006275887,0.001137695,0.0003610701,0.0008108033,0.00128256,0.001129313,0.002576097],"category_scores_gemma":[0.001759025,0.0004171497,0.0008176979,0.0007441796,0.000296901,0.0006216822,0.001011599,0.001201633,0.001531042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234594,"about_ca_system_score_gemma":0.00125114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009625212,"about_ca_topic_score_gemma":0.01144821,"domain_scores_codex":[0.9994944,0.00009294799,0.00003597338,0.0001471726,0.0001420302,0.00008736487],"domain_scores_gemma":[0.9994916,0.0001653225,0.00005139208,0.00005157015,0.0002110035,0.00002909252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003393632,0.0004206165,0.005117672,0.0001422277,0.0001871407,0.0001757461,0.00008346518,0.2202374,0.02055056,0.002560676,0.01174551,0.7384396],"study_design_scores_gemma":[0.000008312182,0.00004216253,0.0007668234,0.000008125015,0.0000142155,0.00003458337,0.000009359312,0.9927129,0.004118266,0.001374781,0.0009030106,0.000007358141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09814536,0.001694791,0.8811381,0.000798412,0.0001744365,0.0003245495,0.001567997,0.010297,0.005859354],"genre_scores_gemma":[0.6840565,0.0004660437,0.3025806,0.0005827647,0.00006232575,0.0003791099,0.00282368,0.0002014323,0.008847567],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009625212,"threshold_uncertainty_score":0.0191384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09316328120341431,"score_gpt":0.4797399913955277,"score_spread":0.3865767101921134,"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."}}