{"id":"W4206955470","doi":"10.2196/32508","title":"Machine Learning Models for Predicting Influential Factors of Early Outcomes in Acute Ischemic Stroke: Registry-Based Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chang Gung Medical Foundation","keywords":"Machine learning; Random forest; Medicine; Artificial intelligence; Artificial neural network; Stroke (engine); Gradient boosting; Receiver operating characteristic; Modified Rankin Scale; Support vector machine; Resampling; Computer science; Ischemic stroke; Internal medicine; Engineering; Ischemia","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007723187,0.0002578998,0.0006902581,0.0003350098,0.0001221311,0.00001700192,0.0004147054,0.000120655,0.0001766024],"category_scores_gemma":[0.0003694482,0.0002211396,0.0001945929,0.0002995099,0.00007559245,0.0001971056,0.0004791894,0.001056553,0.000001559852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002025054,"about_ca_system_score_gemma":0.0002553467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008312056,"about_ca_topic_score_gemma":0.000005209168,"domain_scores_codex":[0.9963057,0.00005277028,0.001306023,0.000176997,0.001741095,0.0004174172],"domain_scores_gemma":[0.9984994,0.000250945,0.000553779,0.0003988422,0.00007950083,0.0002175468],"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":[0.0006281175,0.001064372,0.9769491,0.0005346327,0.0006366251,0.00003683689,0.01304319,0.003382322,0.0001350626,0.00002079018,0.002159589,0.001409347],"study_design_scores_gemma":[0.02608765,0.004994849,0.03977127,0.0002655856,0.0008104832,0.00002145749,0.04124436,0.8758028,0.0009021495,0.00001057502,0.009485937,0.000602947],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908596,0.00001695893,0.004736949,0.0002101835,0.0001336489,0.002032991,0.0001401908,0.0001049428,0.001764577],"genre_scores_gemma":[0.9961072,0.000002700275,0.002083007,0.000369496,0.00003258957,0.0004590878,0.0002222474,0.00003299607,0.0006906845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9371778,"threshold_uncertainty_score":0.9017812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02308610744748438,"score_gpt":0.3038483226170726,"score_spread":0.2807622151695882,"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."}}