{"id":"W4411135751","doi":"10.1093/rheumatology/keaf323","title":"Automated detection of spinal bone marrow oedema in axial spondyloarthritis: training and validation using two large phase 3 trial datasets","year":2025,"lang":"en","type":"article","venue":"Lara D. Veeken","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"Medac; Celgene; Gilead Sciences; Sanofi; Regeneron Pharmaceuticals; Novartis; Amgen; Pfizer; Eli Lilly and Company","keywords":"Axial spondyloarthritis; Medicine; Bone marrow; Physical therapy; Radiology; Magnetic resonance imaging; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004658918,0.000100775,0.0002607989,0.0002494719,0.00004427279,0.00003217567,0.00005074477,0.00006118741,0.00001997765],"category_scores_gemma":[0.0001299874,0.0001129245,0.00003870542,0.0003857389,0.00002721508,0.0001241173,0.0000214705,0.0001301224,0.000001205132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003188877,"about_ca_system_score_gemma":0.00002245837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009015388,"about_ca_topic_score_gemma":0.00004886369,"domain_scores_codex":[0.9991202,0.00006390626,0.0003385293,0.0001559198,0.0001319637,0.0001894931],"domain_scores_gemma":[0.9997417,0.00003108057,0.00004340403,0.0001212179,0.00001446938,0.00004810715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003062161,0.0005160514,0.001257507,0.0007326227,0.0003475455,0.0002543906,0.001113486,0.01024125,0.7009908,0.0002213906,0.0003964385,0.2808663],"study_design_scores_gemma":[0.02955696,0.00007434108,0.000282535,0.0003271585,0.0001047967,0.00001196391,0.0001274168,0.9567384,0.01185586,0.00009869528,0.0006706378,0.0001513049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859751,0.000423453,0.0128619,0.00002530592,0.0002377955,0.0001212061,0.0001091568,0.0001724578,0.00007364857],"genre_scores_gemma":[0.9991276,0.00002130796,0.0005473368,0.00001719938,0.00008989553,0.00000719787,0.0001749043,0.000009865298,0.000004649562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9464971,"threshold_uncertainty_score":0.4604928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02217252064252179,"score_gpt":0.315961232719277,"score_spread":0.2937887120767552,"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."}}