{"id":"W4404673278","doi":"10.5220/0012998400004601","title":"Comparative Analysis of Machine Learning Models for Stroke Risk Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Stroke (engine); Engineering","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":[0.02640676,0.001642161,0.002006156,0.004574453,0.0006844547,0.002500932,0.001742869,0.001670622,0.003080257],"category_scores_gemma":[0.04967267,0.0004115259,0.00256694,0.002169464,0.0005074982,0.002398905,0.001013742,0.001832028,0.0008175211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002171148,"about_ca_system_score_gemma":0.001721353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01490387,"about_ca_topic_score_gemma":0.008487229,"domain_scores_codex":[0.9924806,0.005352019,0.0005698789,0.0005665796,0.0007612922,0.0002694697],"domain_scores_gemma":[0.8790907,0.1129799,0.001235078,0.001862115,0.004330982,0.0005011891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01319203,0.001850697,0.1201846,0.001065462,0.005985343,0.0002799984,0.0003481637,0.6071655,0.0008274456,0.005027946,0.01104501,0.2330278],"study_design_scores_gemma":[0.0002393753,0.001270265,0.02213631,0.0001257633,0.000999448,0.0001011401,0.0002005537,0.9699358,0.0005543015,0.003445379,0.0009341266,0.00005745505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8892818,0.02101914,0.07174543,0.003770134,0.0008418582,0.000276647,0.004696551,0.001343432,0.007024972],"genre_scores_gemma":[0.9774038,0.002081947,0.01412751,0.0002134445,0.0002265481,0.0001204966,0.004232388,0.0001430048,0.001450892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02640676,"threshold_uncertainty_score":0.1396539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03569589097841393,"score_gpt":0.3058390415361034,"score_spread":0.2701431505576894,"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."}}