{"id":"W2579386518","doi":"10.1002/jor.23519","title":"Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative","year":2017,"lang":"en","type":"article","venue":"Journal of Orthopaedic Research®","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; National Institutes of Health","keywords":"Osteoarthritis; WOMAC; Magnetic resonance imaging; Artificial intelligence; Machine learning; Medicine; Cartilage; Knee Joint; Articular cartilage; Algorithm; Computer science; Radiology; Pathology; Surgery; Anatomy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00399993,0.0002076321,0.0005291469,0.0003096821,0.00103739,0.0002339154,0.0005874487,0.0001260598,0.0000876003],"category_scores_gemma":[0.002623929,0.000131469,0.0002411425,0.0002971309,0.0006774867,0.0005331357,0.0001532183,0.001547707,0.00000685342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001060961,"about_ca_system_score_gemma":0.0002665471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005633616,"about_ca_topic_score_gemma":0.0005357032,"domain_scores_codex":[0.9954902,0.001184468,0.0009793756,0.000253933,0.001625111,0.000466943],"domain_scores_gemma":[0.9964771,0.001097768,0.0009526146,0.0006776903,0.0006570551,0.0001377304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003514729,0.0001742117,0.7776197,0.00004702458,0.00003133133,0.0008203331,0.004075211,0.000002059509,0.03425615,0.0001373198,0.00003323549,0.182452],"study_design_scores_gemma":[0.01044793,0.01137729,0.9635547,0.0044988,0.0001631927,0.0004760124,0.004812263,0.0002715773,0.002619325,0.001096113,0.0005279298,0.0001548042],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800825,0.01639842,0.00001112121,0.001172495,0.0001630895,0.0008112441,0.00004155602,0.00001039814,0.001309186],"genre_scores_gemma":[0.9981135,0.0006618634,0.0004609966,0.00004427562,0.0005066947,0.0000299634,0.00001434248,0.00003550348,0.0001329005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1859351,"threshold_uncertainty_score":0.7978867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07704470724319394,"score_gpt":0.3520994994982187,"score_spread":0.2750547922550247,"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."}}