{"id":"W3044073468","doi":"10.1038/s41598-020-69106-8","title":"$$\\text {DRTOP}$$: deep learning-based radiomics for the time-to-event outcome prediction in lung cancer","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; Toronto General Hospital; Concordia University","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Canada; Sunnybrook Research Institute","keywords":"Concordance correlation coefficient; Concordance; Artificial intelligence; Radiomics; Computer science; Hazard ratio; Algorithm; Machine learning; Lung cancer; Event (particle physics); Positron emission tomography; Proportional hazards model; Medicine; Nuclear medicine; Mathematics; Statistics; Internal medicine; Confidence interval; Physics","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":[0.002010702,0.000157961,0.000313312,0.0001539995,0.0002971351,0.0001328118,0.0001371608,0.00006769198,0.000507181],"category_scores_gemma":[0.002047114,0.0001141548,0.0001637323,0.0006096311,0.0001368826,0.00006011302,0.00004975768,0.0004623446,0.0000355689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001777484,"about_ca_system_score_gemma":0.0002312098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000043886,"about_ca_topic_score_gemma":0.000007371665,"domain_scores_codex":[0.9977522,0.00005252549,0.0006366959,0.0006639005,0.000521163,0.0003735139],"domain_scores_gemma":[0.9987977,0.0001541321,0.0002091558,0.0003948275,0.0001225992,0.0003215519],"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":[0.0002618941,0.0001608081,0.3704627,0.0004776466,0.0001161791,0.0005116175,0.00202973,0.4571681,0.01475676,0.00001598778,0.09841495,0.05562363],"study_design_scores_gemma":[0.0006032452,0.0000668017,0.007882864,0.00008697889,0.00009095768,0.00004742352,0.00004104138,0.7910806,0.0004116055,0.00002564841,0.1995577,0.0001051469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6487914,0.002410983,0.2064214,0.1229257,0.01242636,0.005394103,0.00001372856,0.0004847712,0.001131614],"genre_scores_gemma":[0.9868904,0.000008508312,0.001342785,0.003332983,0.0005104152,0.0002182838,0.00008386169,0.00005147522,0.007561306],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3625798,"threshold_uncertainty_score":0.5553276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01351538231969917,"score_gpt":0.3053651834387694,"score_spread":0.2918498011190702,"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."}}