{"id":"W4367459262","doi":"10.1177/1759720x231165560","title":"Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis","year":2023,"lang":"en","type":"review","venue":"Therapeutic Advances in Musculoskeletal Disease","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Magnetic resonance imaging; Medicine; Osteoarthritis; Deep learning; Machine learning; Artificial intelligence; Narrative review; Knee Joint; Modalities; Rheumatology; Radiology; Computer science; Pathology; Surgery; Intensive care medicine","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001770278,0.000443904,0.0009813723,0.0003821342,0.00006781871,0.00004312525,0.00006339839,0.00008700799,0.000006843375],"category_scores_gemma":[0.00005984947,0.00034916,0.0001499119,0.0003900896,0.0001624056,0.0005003652,0.00004741826,0.0002309378,0.000001162627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009212903,"about_ca_system_score_gemma":0.00009562807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002286387,"about_ca_topic_score_gemma":0.0001001301,"domain_scores_codex":[0.9981396,0.0002103734,0.0005259554,0.0005604036,0.0002474983,0.0003162033],"domain_scores_gemma":[0.9988983,0.0004475862,0.0002696107,0.0001764111,0.0000600798,0.0001480558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002875485,0.0002223733,0.08350591,0.00848267,0.00003222137,0.00003387136,0.0001668214,0.000001286918,0.000001509032,0.00005621396,9.418002e-8,0.9072095],"study_design_scores_gemma":[0.09605261,0.105377,0.3006539,0.3479809,0.01467287,0.0001065019,0.004477145,0.002428086,0.00004001889,0.009933987,0.1128077,0.005469212],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.06507824,0.9301124,0.00006760367,0.00001288589,0.00007512039,0.004466963,0.000122328,0.00005175125,0.00001275319],"genre_scores_gemma":[0.05654417,0.9387417,0.000355554,0.00001782079,0.00002460383,0.003700812,0.0004395019,0.0001005952,0.00007520163],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9017403,"threshold_uncertainty_score":0.999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01996517988596505,"score_gpt":0.3305705025647858,"score_spread":0.3106053226788207,"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."}}