{"id":"W4286539427","doi":"10.2139/ssrn.4163705","title":"A Deep Learning Framework for Personalized Dynamic Diagnosis of Graft Fibrosis after Liver Transplantation Using Longitudinal Data","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Transplantation; Deep learning; Liver transplantation; Medicine; Personalized medicine; Longitudinal data; Fibrosis; Computer science; Artificial intelligence; Pathology; Bioinformatics; Surgery; Data mining; 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":[0.001431178,0.000845121,0.0011972,0.001019372,0.0004607471,0.000904402,0.001605656,0.001464218,0.00168814],"category_scores_gemma":[0.002393434,0.0005414666,0.0009085325,0.0007307676,0.0003042435,0.0008667595,0.001331683,0.001883349,0.0005183304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009971685,"about_ca_system_score_gemma":0.001902449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02533464,"about_ca_topic_score_gemma":0.03763699,"domain_scores_codex":[0.9995968,0.00009626163,0.00002544152,0.0001313322,0.00006172564,0.00008839885],"domain_scores_gemma":[0.9993427,0.0003513133,0.00005255409,0.00004689339,0.0001382649,0.00006824471],"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":[0.0005906745,0.0006816745,0.01881958,0.0001448808,0.0004067932,0.0003900835,0.000121247,0.5320925,0.002881342,0.005766246,0.01490298,0.423202],"study_design_scores_gemma":[0.000009556232,0.00002330185,0.0003601985,0.000008083852,0.00001563886,0.00001662393,0.000005441836,0.9969369,0.0001919402,0.002126135,0.0003017715,0.000004450605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1036796,0.004329183,0.8809432,0.003014434,0.0002634069,0.0001480026,0.002820218,0.002808905,0.001993065],"genre_scores_gemma":[0.8221067,0.001228949,0.1660558,0.0007878937,0.0002987534,0.0002201442,0.00420824,0.0001063322,0.004987122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02533464,"threshold_uncertainty_score":0.05037433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337582002220639,"score_gpt":0.3017769643827251,"score_spread":0.2784011443605187,"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."}}