{"id":"W2964427053","doi":"10.1101/713800","title":"Automating Three-dimensional Osteoarthritis Histopathological Grading of Human Osteochondral Tissue using Machine Learning on Contrast-Enhanced Micro-Computed Tomography","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"Oulun Yliopisto; Academy of Finland; European Commission","keywords":"Receiver operating characteristic; Osteoarthritis; Grading (engineering); Nuclear medicine; Tomography; Computed tomography; Medicine; Mathematics; Radiology; Pathology; Statistics; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184524,0.0004539482,0.0003724748,0.001059354,0.0001539383,0.0008258483,0.0005639567,0.0005240426,0.000479725],"category_scores_gemma":[0.003203713,0.0002554108,0.0004662595,0.0003070192,0.0002470743,0.0003543725,0.0004887506,0.0003216355,0.0005273442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003155665,"about_ca_system_score_gemma":0.0004300439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001636856,"about_ca_topic_score_gemma":0.003245462,"domain_scores_codex":[0.9993991,0.0001873896,0.00004543248,0.0001675746,0.0001594612,0.00004120751],"domain_scores_gemma":[0.9986676,0.0005185833,0.0002066496,0.0001701148,0.000406424,0.00003061448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004570097,0.0002366133,0.0574888,0.0002721616,0.0001537882,0.0001648645,0.0001878639,0.09360263,0.3037263,0.0004103945,0.0009556974,0.5423439],"study_design_scores_gemma":[0.00001079173,0.0001269723,0.0381074,0.00002615094,0.00003857472,0.0002528539,0.00006024495,0.9101309,0.05018655,0.0003985189,0.0006351395,0.00002592908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3914904,0.0004791791,0.6051426,0.0001039932,0.00001960971,0.0001207887,0.0001976501,0.001768797,0.0006768996],"genre_scores_gemma":[0.7747166,0.0001796338,0.2239946,0.00005200417,0.00001344866,0.00009335119,0.0003133798,0.00005365014,0.0005832775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00184524,"threshold_uncertainty_score":0.009758711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01600566664340468,"score_gpt":0.2396222676425002,"score_spread":0.2236166009990955,"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."}}