{"id":"W4405248120","doi":"10.1002/ana.27154","title":"Automated Neuroprognostication Via Machine Learning in Neonates with Hypoxic‐Ischemic Encephalopathy","year":2024,"lang":"en","type":"article","venue":"Annals of Neurology","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; University of Toronto; Mental Health Research Canada; Hospital for Sick Children","funders":"TD Bank","keywords":"Bayley Scales of Infant Development; Hypoxic Ischemic Encephalopathy; Toddler; Magnetic resonance imaging; Neuroimaging; Medicine; Encephalopathy; Neonatal encephalopathy; Pediatrics; Psychology; Cognition; Developmental psychology; Psychiatry; Radiology; Psychomotor learning","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":[0.001375663,0.0006488931,0.0004366752,0.0007978125,0.0002449282,0.0004813082,0.0005700135,0.0005442312,0.0008451729],"category_scores_gemma":[0.00510251,0.0002129769,0.0003939423,0.0003886085,0.0002098789,0.0005220387,0.000592501,0.0006728711,0.000341122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006165457,"about_ca_system_score_gemma":0.0007558243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0058812,"about_ca_topic_score_gemma":0.004608616,"domain_scores_codex":[0.9996722,0.0001392388,0.00002977,0.00007832983,0.00004550692,0.00003497015],"domain_scores_gemma":[0.9985375,0.0008857808,0.0002152057,0.0000655848,0.0002414787,0.00005437472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003963106,0.0003419207,0.1558932,0.00008980614,0.0001593957,0.0004277608,0.0001322831,0.5766547,0.003161318,0.0005115641,0.001647538,0.2605843],"study_design_scores_gemma":[0.000004893795,0.00004594348,0.006826122,0.00001443159,0.00001027945,0.0000612566,0.00002541209,0.9911328,0.00110355,0.0006261081,0.0001425355,0.000006755054],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8223473,0.0008742032,0.1726668,0.000733171,0.00006183379,0.0001103484,0.0005388889,0.001227252,0.001440063],"genre_scores_gemma":[0.9748531,0.0001405085,0.02373821,0.00006884059,0.0000266296,0.00005713761,0.000574099,0.00002180637,0.0005196859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0058812,"threshold_uncertainty_score":0.01169389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02124728514937856,"score_gpt":0.2856529708088187,"score_spread":0.2644056856594401,"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."}}