{"id":"W4318206245","doi":"10.1186/s12984-023-01140-9","title":"The use of machine learning and deep learning techniques to assess proprioceptive impairments of the upper limb after stroke","year":2023,"lang":"en","type":"article","venue":"Journal of NeuroEngineering and Rehabilitation","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Calgary","funders":"Canadian Institutes of Health Research; Ontario Research Foundation; Heart and Stroke Foundation of Canada","keywords":"Kinematics; Physical medicine and rehabilitation; Random forest; Artificial intelligence; Machine learning; Task (project management); Support vector machine; Proprioception; Computer science; Stroke (engine); Artificial neural network; Convolutional neural network; Decision tree; Psychology; Medicine; 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":[0.002059315,0.000709094,0.0005092536,0.001857881,0.0001514387,0.0008867207,0.0004015966,0.0006731857,0.0008860683],"category_scores_gemma":[0.006136524,0.0001696083,0.0004355914,0.001038026,0.0003963481,0.0007225499,0.0005860617,0.0007142649,0.000261623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003998724,"about_ca_system_score_gemma":0.0005204764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079888,"about_ca_topic_score_gemma":0.001922824,"domain_scores_codex":[0.9992843,0.0002464035,0.00009094491,0.0001215571,0.0002063586,0.00005052909],"domain_scores_gemma":[0.9970521,0.001652409,0.0006294631,0.0001615393,0.0004202732,0.00008417135],"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":[0.0006113187,0.0006387729,0.1286333,0.0006702243,0.000503495,0.0001583819,0.0001714115,0.04635211,0.03246499,0.001316619,0.001980842,0.7864985],"study_design_scores_gemma":[0.00009803144,0.002597438,0.2608085,0.0005746302,0.000310271,0.001103076,0.0002336387,0.6815191,0.03635404,0.01239231,0.003850961,0.0001580154],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5795125,0.00701157,0.4035299,0.001686683,0.0002175124,0.0003723495,0.001533307,0.001160836,0.004975291],"genre_scores_gemma":[0.9004639,0.001854308,0.0958909,0.0003101755,0.0001177582,0.0002156445,0.000412132,0.00003170096,0.0007035611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002059315,"threshold_uncertainty_score":0.01089078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307102630398969,"score_gpt":0.2654101785095376,"score_spread":0.2523391522055479,"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."}}