{"id":"W4407386583","doi":"10.3389/fninf.2025.1544372","title":"Quantitative evaluation method of stroke association based on multidimensional gait parameters by using machine learning","year":2025,"lang":"en","type":"article","venue":"Frontiers in Neuroinformatics","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Capital Health","keywords":"Stroke (engine); Gait; Computer science; Support vector machine; Linear discriminant analysis; Artificial intelligence; Machine learning; Physical medicine and rehabilitation; AdaBoost; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.004074236,0.0007657807,0.0006691607,0.00539613,0.000335337,0.0009028921,0.0004427518,0.0005186875,0.001501884],"category_scores_gemma":[0.009284833,0.0001650481,0.0005790242,0.001922466,0.0004025548,0.0009414931,0.0006291266,0.000374355,0.0005050048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003784364,"about_ca_system_score_gemma":0.0004385505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009013317,"about_ca_topic_score_gemma":0.001124943,"domain_scores_codex":[0.996711,0.0008236329,0.000436528,0.0005108503,0.001407687,0.0001101824],"domain_scores_gemma":[0.9950429,0.001522906,0.0008920479,0.0003425024,0.002059721,0.0001399719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000917551,0.0004592687,0.4502501,0.000690292,0.0005805476,0.0002229743,0.0004434684,0.01557373,0.02026844,0.001473894,0.004262907,0.5048568],"study_design_scores_gemma":[0.0001533079,0.001422908,0.5454468,0.0002537967,0.0005730951,0.001723663,0.0009063656,0.4092789,0.02945716,0.004474373,0.006030133,0.0002796486],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5074174,0.001758152,0.4804811,0.000336359,0.0001875289,0.0005823505,0.001867522,0.001527442,0.005842219],"genre_scores_gemma":[0.9156799,0.0002903692,0.08186611,0.00005748141,0.00006907248,0.0002733835,0.0008287682,0.00003704133,0.0008977553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00539613,"threshold_uncertainty_score":0.02154684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03817694696463961,"score_gpt":0.3889550806533354,"score_spread":0.3507781336886958,"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."}}