{"id":"W2979740388","doi":"10.4103/ijabmr.ijabmr_370_18","title":"Use of machine learning algorithms for prediction of fetal risk using cardiotocographic data","year":2019,"lang":"en","type":"article","venue":"International Journal of Applied and Basic Medical Research","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Triage; Machine learning; Decision tree; Suspect; Random forest; Medicine; Artificial intelligence; Gold standard (test); Referral; Algorithm; Computer science; Pathological; Medical emergency; Internal medicine; Psychology","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":[0.003139782,0.00007426215,0.0003501183,0.0004074319,0.0000335653,0.0000107738,0.0003090613,0.0001143683,0.0001009923],"category_scores_gemma":[0.001647568,0.00005332947,0.00009491234,0.0001534784,0.0003119121,0.0001119875,0.000253345,0.0007202897,0.00000100559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002288643,"about_ca_system_score_gemma":0.0002442939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006840486,"about_ca_topic_score_gemma":0.000002051453,"domain_scores_codex":[0.9973355,0.0000857644,0.0005252093,0.0001808789,0.001716036,0.0001565978],"domain_scores_gemma":[0.9976727,0.0009931239,0.0002686749,0.0001559688,0.0007379352,0.0001716033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008559162,0.0005875044,0.09662784,0.000527284,0.001623133,0.0002128943,0.0003689347,0.00009529839,0.09857394,0.001770605,0.0003539501,0.7906995],"study_design_scores_gemma":[0.03797281,0.01027629,0.1359327,0.003847243,0.0008532106,0.005970675,0.001669133,0.6594651,0.03184327,0.00897363,0.1026616,0.0005342156],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906856,0.0004356786,0.006977655,0.0004161924,0.0003153064,0.0005160573,0.0003456964,0.000004045627,0.0003037513],"genre_scores_gemma":[0.9945823,0.0007926513,0.004046291,0.00004116464,0.0003791618,0.000003912656,0.00008786091,0.0000109951,0.00005567688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7901652,"threshold_uncertainty_score":0.312934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1388361580100567,"score_gpt":0.4064694831133985,"score_spread":0.2676333251033418,"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."}}