{"id":"W3116540513","doi":"10.1016/j.medengphy.2020.12.007","title":"Machine learning and wearable sensors at preoperative assessments: Functional recovery prediction to set realistic expectations for knee replacements","year":2020,"lang":"en","type":"article","venue":"Medical Engineering & Physics","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Arthritis Society; Canadian Institutes of Health Research; Government of Ontario","keywords":"Wearable computer; Set (abstract data type); Computer science; Machine learning; Wearable technology; Artificial intelligence; Human–computer interaction; Biomedical engineering; Physical medicine and rehabilitation; Simulation; Medicine; Embedded system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001067789,0.0001676433,0.0002599765,0.00003917328,0.0001286205,0.00001931106,0.00002866647,0.00006752597,0.0001506317],"category_scores_gemma":[0.001370612,0.0001611358,0.00005926268,0.0001762351,0.00002538101,0.0001123475,0.00006909788,0.0002581505,0.00003087707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322577,"about_ca_system_score_gemma":0.00006621968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009050143,"about_ca_topic_score_gemma":0.000002038539,"domain_scores_codex":[0.9987333,0.00002204061,0.0002489131,0.0003169828,0.0004550089,0.0002237849],"domain_scores_gemma":[0.9991408,0.000248619,0.00004223708,0.00009342613,0.00006896912,0.0004059635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004905085,0.0007894114,0.1064725,0.002861579,0.002719019,0.0001599695,0.01298588,0.7847882,0.03263661,0.002337258,0.02247212,0.02687234],"study_design_scores_gemma":[0.003710535,0.002492911,0.009561308,0.0003178846,0.0001808349,0.00004485425,0.0004222816,0.9674287,0.0008732023,0.00002455715,0.01465183,0.0002910441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5925623,0.0001804953,0.3998263,0.004370591,0.0006589249,0.001277408,0.0002343557,0.0004903954,0.0003992462],"genre_scores_gemma":[0.9913459,0.00002841113,0.004912769,0.0006313864,0.0005672477,0.0001619784,0.0004229158,0.00005703633,0.001872387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3987836,"threshold_uncertainty_score":0.6570927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02112606929461351,"score_gpt":0.2783862009466105,"score_spread":0.257260131651997,"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."}}