{"id":"W4388765424","doi":"10.1089/end.2023.0446","title":"Predictive Modeling of Urinary Stone Composition Using Machine Learning and Clinical Data: Implications for Treatment Strategies and Pathophysiological Insights","year":2023,"lang":"en","type":"article","venue":"Journal of Endourology","topic":"Kidney Stones and Urolithiasis Treatments","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Science Centre for Human and Animal Health; Western University","funders":"","keywords":"Medicine; Uric acid; Calcium oxalate; Calcium; Kidney stones; Kappa; Creatinine; Logistic regression; Urology; Internal medicine","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":[0.0001932824,0.00009533106,0.0004434764,0.0001148811,0.00008864694,0.000007483071,0.00004108394,0.00008815467,0.000001163625],"category_scores_gemma":[0.00007842387,0.00006357231,0.00006937472,0.00006046212,0.00009383509,0.0001298236,0.00006310698,0.0001219333,1.283051e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002062387,"about_ca_system_score_gemma":0.00009099638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001360399,"about_ca_topic_score_gemma":8.437435e-7,"domain_scores_codex":[0.999127,0.0001066342,0.0004273915,0.000168285,0.00005676352,0.0001139604],"domain_scores_gemma":[0.999121,0.0002942653,0.0002625768,0.0001050675,0.0001133421,0.0001037804],"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":[0.01838964,0.004804298,0.7748609,0.0002475645,0.003703155,0.0004240675,0.001386042,0.0216243,0.1588314,0.001645039,0.00003882758,0.01404476],"study_design_scores_gemma":[0.00862317,0.02288344,0.3771997,0.0000644682,0.001433309,0.00196818,0.0005417701,0.5845565,0.00009209866,0.002360106,0.0001763951,0.0001008868],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995045,0.001365663,0.0026985,0.0005582907,0.00005959542,0.0001973861,0.00005430743,0.0000109436,0.00001029335],"genre_scores_gemma":[0.9941845,0.002645537,0.002881701,0.00003781654,0.0001372604,0.000003564147,0.00009687556,0.000008779277,0.000004001139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5629321,"threshold_uncertainty_score":0.2592404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1578934993190497,"score_gpt":0.4249408200097626,"score_spread":0.2670473206907129,"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."}}