{"id":"W4401174226","doi":"10.2196/56980","title":"Classifying Residual Stroke Severity Using Robotics-Assisted Stroke Rehabilitation: Machine Learning Approach","year":2024,"lang":"en","type":"article","venue":"JMIR Biomedical Engineering","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Civil, Mechanical and Manufacturing Innovation; National Science Foundation","keywords":"Artificial intelligence; Rehabilitation; Machine learning; Stroke (engine); Robotics; Physical medicine and rehabilitation; Deep learning; Motor learning; Residual; Computer science; Medicine; Physical therapy; Psychology; Robot; Engineering; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005658299,0.0003167618,0.0005025943,0.0006988312,0.0001244935,0.0001009187,0.0001152633,0.0003370417,0.0001191795],"category_scores_gemma":[0.0007246164,0.0002767043,0.0003213573,0.0007221192,0.0001734785,0.0001870677,0.00008767565,0.001128931,0.00002636676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004207004,"about_ca_system_score_gemma":0.0002114982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002083267,"about_ca_topic_score_gemma":6.918463e-7,"domain_scores_codex":[0.9975012,0.00008206262,0.0005935708,0.0005562378,0.000770244,0.0004966882],"domain_scores_gemma":[0.9985034,0.0006702006,0.0000551971,0.000277344,0.00008256439,0.0004112471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001050576,0.003304679,0.05471665,0.03506428,0.003310882,0.001173403,0.00741203,0.1513326,0.5902418,0.005313267,0.005816601,0.1412633],"study_design_scores_gemma":[0.00115653,0.0004664586,0.0261055,0.0009283379,0.0001431228,0.0003538867,0.000485813,0.9349729,0.0001467689,0.000007873381,0.03484437,0.000388467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8122114,0.003730782,0.1711338,0.004197931,0.003037822,0.001516082,0.0001245235,0.00233597,0.001711697],"genre_scores_gemma":[0.8761321,0.00003347993,0.1209326,0.00005874255,0.0009291709,0.00006390842,0.0001651785,0.00009574815,0.001589032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7836403,"threshold_uncertainty_score":0.9999685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02083183812538156,"score_gpt":0.2881970246824359,"score_spread":0.2673651865570543,"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."}}