{"id":"W4392962925","doi":"10.1186/s12938-024-01228-w","title":"Enhancing automated lower limb rehabilitation exercise task recognition through multi-sensor data fusion in tele-rehabilitation","year":2024,"lang":"en","type":"article","venue":"BioMedical Engineering OnLine","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Mitacs","keywords":"Rehabilitation; Computer science; Artificial intelligence; Task (project management); Recall; Machine learning; Deep learning; Precision and recall; Physical medicine and rehabilitation; Medicine; Physical therapy; Psychology; 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":[0.0005624678,0.0007822437,0.0006433704,0.0006391756,0.0001590505,0.000549513,0.0005712373,0.0008801164,0.001125078],"category_scores_gemma":[0.001325364,0.0002340593,0.0007052735,0.0004507532,0.0002349937,0.0006582572,0.0006775144,0.0006934805,0.0004486771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000389756,"about_ca_system_score_gemma":0.0005031773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003242597,"about_ca_topic_score_gemma":0.004048837,"domain_scores_codex":[0.9996883,0.00004871607,0.00002040001,0.0001066536,0.00007987283,0.00005619326],"domain_scores_gemma":[0.9996915,0.0001301704,0.00004558698,0.00002663616,0.0000849874,0.00002108527],"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":[0.0008011033,0.0008568547,0.01794294,0.000506443,0.0002527601,0.0004156103,0.0002263383,0.2359961,0.0562804,0.0006467832,0.004327013,0.6817476],"study_design_scores_gemma":[0.00001730182,0.0002322474,0.01473356,0.00006223196,0.00006946411,0.0001674068,0.00006009187,0.9687408,0.01366545,0.001053034,0.001171292,0.00002719953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3017537,0.002880007,0.6871541,0.000707784,0.0002837971,0.000164338,0.00110149,0.002536057,0.003418664],"genre_scores_gemma":[0.9497475,0.0005412269,0.04727608,0.0002409815,0.00006444908,0.000126973,0.0005463806,0.00002917188,0.001427219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003242597,"threshold_uncertainty_score":0.006447494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02417251343247035,"score_gpt":0.3153314319790333,"score_spread":0.291158918546563,"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."}}