{"id":"W4401160603","doi":"10.3390/app14156700","title":"Machine Learning-Based Stroke Patient Rehabilitation Stage Classification Using Kinect Data","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rehabilitation; Computer science; Artificial intelligence; Hyperparameter; Physical medicine and rehabilitation; Stroke (engine); Gesture; Machine learning; Physical therapy; Medicine; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000657949,0.001227326,0.00103105,0.001782687,0.0003123551,0.0007206255,0.0007754571,0.0008312153,0.001739764],"category_scores_gemma":[0.001349491,0.0002008543,0.0009695718,0.0010095,0.0002122072,0.0004074321,0.0005158085,0.0006737444,0.001061193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006561077,"about_ca_system_score_gemma":0.0008567807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0144405,"about_ca_topic_score_gemma":0.01544651,"domain_scores_codex":[0.9995527,0.00005083115,0.00005722533,0.0001324793,0.00009828909,0.0001085054],"domain_scores_gemma":[0.9996769,0.00007253844,0.00004244491,0.00003132606,0.0001369484,0.0000398119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002504376,0.001073336,0.08986699,0.0004216504,0.0003705769,0.0007638226,0.0001800121,0.1771331,0.01774867,0.0009246487,0.0199976,0.6890152],"study_design_scores_gemma":[0.000037637,0.0002898464,0.036378,0.00007042536,0.00006541312,0.0001729408,0.0001509835,0.9488581,0.01115947,0.0007027974,0.002062082,0.00005219254],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8114691,0.002854096,0.1592984,0.0007197459,0.0005046573,0.0007870883,0.01387678,0.00483088,0.005659164],"genre_scores_gemma":[0.9373184,0.0005407718,0.04581791,0.00011746,0.00006632664,0.0003073541,0.01109699,0.00006443525,0.00467031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0144405,"threshold_uncertainty_score":0.02871293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07001903823092659,"score_gpt":0.3421118112104393,"score_spread":0.2720927729795127,"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."}}