{"id":"W4381309868","doi":"10.2196/45352","title":"Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches","year":2023,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Transplantation: Methods and Outcomes","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health; Florida State University","keywords":"Gradient boosting; AdaBoost; Machine learning; Random forest; Artificial intelligence; Medicine; Receiver operating characteristic; Softmax function; Transplantation; Multilayer perceptron; Logistic regression; Stochastic gradient descent; Heart transplantation; Support vector machine; Computer science; Internal medicine; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0200127,0.001054549,0.0009986222,0.002061073,0.0003334796,0.00113229,0.001180979,0.0008729896,0.0006918088],"category_scores_gemma":[0.03256844,0.0003104424,0.001468904,0.001331326,0.0003500708,0.001408917,0.001238669,0.001650496,0.0002770546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008477572,"about_ca_system_score_gemma":0.00143996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005615085,"about_ca_topic_score_gemma":0.004519396,"domain_scores_codex":[0.992577,0.005269681,0.0004411089,0.0008210984,0.0006669151,0.0002241956],"domain_scores_gemma":[0.9704451,0.02155362,0.003238908,0.001517688,0.002441785,0.0008029883],"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":[0.0008778187,0.0004941819,0.8696281,0.000169333,0.001104732,0.00006550251,0.0001037252,0.07006829,0.0001433454,0.0003251288,0.001689392,0.0553303],"study_design_scores_gemma":[0.0001216141,0.001025155,0.156461,0.0001752981,0.0003515097,0.0001620119,0.0002284335,0.839034,0.0006384603,0.0008111301,0.0009508138,0.00004050683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714345,0.002751059,0.0200518,0.001544931,0.0001270702,0.0001864863,0.00251342,0.0002484046,0.001142351],"genre_scores_gemma":[0.983135,0.000728882,0.01325306,0.0001065589,0.00009160765,0.000090986,0.002439783,0.00002145328,0.0001327211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0200127,"threshold_uncertainty_score":0.1058386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2190373009914043,"score_gpt":0.3846664664344567,"score_spread":0.1656291654430523,"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."}}