{"id":"W2773114850","doi":"10.1109/jtehm.2017.2780836","title":"Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Translational Engineering in Health and Medicine","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Muscular Dystrophy Canada; University of Toronto; Toronto Rehabilitation Institute; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Toronto Rehabilitation Institute","keywords":"Rehabilitation; Stroke (engine); Trunk; Physical medicine and rehabilitation; Support vector machine; Artificial intelligence; Medicine; Computer science; Physical therapy; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004751644,0.0002957083,0.0003443642,0.000395434,0.0001288831,0.0002069597,0.0002375768,0.0003522468,0.0008776694],"category_scores_gemma":[0.001672858,0.0001452966,0.0001481686,0.0001681385,0.0001477655,0.0001757238,0.0002050438,0.0001314414,0.0003365501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001941841,"about_ca_system_score_gemma":0.0002617345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001767759,"about_ca_topic_score_gemma":0.00268897,"domain_scores_codex":[0.9996363,0.00008721459,0.00002370859,0.0001011977,0.0001080004,0.00004357551],"domain_scores_gemma":[0.9996524,0.0001205867,0.00006936814,0.00002391859,0.0001158316,0.0000179435],"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":[0.001244559,0.0002076459,0.0247549,0.0002322755,0.00007059584,0.0002294037,0.0003263086,0.009145366,0.4714152,0.0001666041,0.0009059765,0.4913012],"study_design_scores_gemma":[0.00007201363,0.001543644,0.4530708,0.00006014027,0.000127883,0.001676073,0.0002734801,0.2824509,0.2576635,0.0005060242,0.002460505,0.00009506824],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9077731,0.0004433859,0.08887948,0.00005974684,0.00003910588,0.0001188013,0.0001542887,0.0008990271,0.001633058],"genre_scores_gemma":[0.9834219,0.00009193479,0.01546341,0.00002938687,0.000008772759,0.00004649663,0.0001019593,0.00001504916,0.0008211163],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001767759,"threshold_uncertainty_score":0.003514946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02081435644003402,"score_gpt":0.3076615272276876,"score_spread":0.2868471707876536,"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."}}