{"id":"W4387046392","doi":"10.1016/j.arth.2023.09.027","title":"Using Unsupervised Machine Learning to Predict Quality of Life After Total Knee Arthroplasty","year":2023,"lang":"en","type":"article","venue":"The Journal of Arthroplasty","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Patient-reported outcome; Physical therapy; Demographics; Body mass index; Comorbidity; Quality of life (healthcare); Arthroplasty; Metric (unit); Total knee arthroplasty; Orthopedic surgery; Internal medicine; Surgery","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":[0.001711864,0.0003158793,0.000467658,0.00074053,0.0002290358,0.0007796814,0.0004962549,0.000571664,0.0007715369],"category_scores_gemma":[0.0105943,0.0001282889,0.0006244861,0.0005160199,0.0003029333,0.0006257124,0.0005468563,0.0009829557,0.0002274015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005000762,"about_ca_system_score_gemma":0.0006124655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002650302,"about_ca_topic_score_gemma":0.004902053,"domain_scores_codex":[0.9992705,0.0003192607,0.00008462858,0.00009730866,0.0001327048,0.00009564137],"domain_scores_gemma":[0.9944301,0.003200444,0.001246313,0.0002938443,0.0005289324,0.0003003388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005439181,0.0007741764,0.9420088,0.00005267771,0.0003378103,0.00005209862,0.00008209515,0.0153567,0.0003527844,0.0002936144,0.001079052,0.03906632],"study_design_scores_gemma":[0.00004040293,0.0007280622,0.7250389,0.00004370981,0.0001104846,0.0001401824,0.0002072803,0.2696112,0.0005893031,0.002891616,0.0005607628,0.00003813936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920637,0.0002682685,0.005896641,0.0002554405,0.00006204635,0.00002940802,0.0007071655,0.00004324113,0.0006739845],"genre_scores_gemma":[0.9977912,0.00005744045,0.00116565,0.0000301517,0.00002687734,0.00002009328,0.000705794,0.000004249017,0.0001985158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002650302,"threshold_uncertainty_score":0.00905329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03803486805388942,"score_gpt":0.3020819342030079,"score_spread":0.2640470661491184,"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."}}