{"id":"W3034428823","doi":"10.2196/17289","title":"Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers","year":2020,"lang":"en","type":"article","venue":"JMIR Rehabilitation and Assistive Technologies","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Regional Development Fund; Imperial College London","keywords":"Dynamic time warping; Hidden Markov model; Rehabilitation; Motion capture; Physical medicine and rehabilitation; Computer science; Motion (physics); Functional movement; Physical therapy; Artificial intelligence; Machine learning; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.000298598,0.0001340608,0.0002855325,0.0003270062,0.0001113324,0.00007341174,0.0001108486,0.00007977749,9.482314e-7],"category_scores_gemma":[0.00204531,0.0001240559,0.00003843196,0.0009405099,0.0001825745,0.0005928127,0.0001857505,0.0001835853,0.000001408459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004480951,"about_ca_system_score_gemma":0.0000143003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009580922,"about_ca_topic_score_gemma":0.00003874184,"domain_scores_codex":[0.9987983,0.00007522558,0.0003782914,0.0004339291,0.0001501545,0.0001641474],"domain_scores_gemma":[0.9989862,0.0005130091,0.0001507578,0.0001692962,0.0001335264,0.00004721823],"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":[0.0001595244,0.00003988697,0.2478404,0.0003186207,0.000006906193,8.312193e-7,0.008542721,0.001911923,0.001251864,0.001732129,0.00001719866,0.738178],"study_design_scores_gemma":[0.0003048768,0.001745875,0.5470586,0.0002667671,0.000006268581,0.000001204655,0.009476542,0.4399557,0.0002577228,0.0001963173,0.0005524118,0.0001776924],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9457423,0.0001888044,0.04322957,0.01013883,0.00001770232,0.0003999409,0.000002694929,0.0002708054,0.000009322115],"genre_scores_gemma":[0.8863916,0.00006566624,0.1134716,0.00003505355,0.000002628853,0.00001973794,0.000002627878,0.000006144905,0.0000048608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7380003,"threshold_uncertainty_score":0.5058853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02686718766707355,"score_gpt":0.2627801883127804,"score_spread":0.2359130006457069,"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."}}