{"id":"W4238151591","doi":"10.2196/preprints.34554","title":"Machine Learning Support for Decision-Making in Kidney Transplantation: Step-by-step Development of a Technological Solution (Preprint)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Renal and Vascular Pathologies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Discriminative model; Transplantation; Proportional hazards model; Random forest; Medicine; Computer science; Calibration; Artificial neural network; Artificial intelligence; Recurrent neural network; Index (typography); Kidney transplantation; Machine learning; Statistics; Internal medicine; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001023175,0.0002761591,0.0007308722,0.000257961,0.00006656418,0.0000231282,0.0001889866,0.000534595,0.0002892351],"category_scores_gemma":[0.001187834,0.0002170981,0.0002725954,0.0001700281,0.00007310191,0.00003959071,0.0003443591,0.0007385762,0.000004935412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392794,"about_ca_system_score_gemma":0.0005120486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002184796,"about_ca_topic_score_gemma":0.00005807664,"domain_scores_codex":[0.9977578,0.00007486176,0.0008600073,0.0006556521,0.0003728355,0.0002788495],"domain_scores_gemma":[0.9989634,0.0002419036,0.0002231506,0.000328571,0.0001633521,0.00007958381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002711718,0.001541466,0.09970719,0.01037628,0.0007401743,0.0008378917,0.002573844,0.001789128,0.03460051,0.0005146552,0.0008043025,0.8438028],"study_design_scores_gemma":[0.03152927,0.003675751,0.3415542,0.09845796,0.002338067,0.003834753,0.0131828,0.1154849,0.3105025,0.002351484,0.07093544,0.006152933],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.180634,0.0004660396,0.8163909,0.000210295,0.00008623522,0.0010386,0.0000232685,0.0001381442,0.001012585],"genre_scores_gemma":[0.6407452,0.000438141,0.3578312,0.00006232451,0.00001119238,0.000196411,0.0005199237,0.00001642424,0.0001791635],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8376499,"threshold_uncertainty_score":0.8853002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02729465009479662,"score_gpt":0.3056843573478204,"score_spread":0.2783897072530238,"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."}}