{"id":"W4405796181","doi":"10.1136/rmdopen-2024-004628","title":"Anatomy-centred deep learning improves generalisability and progression prediction in radiographic sacroiliitis detection","year":2024,"lang":"en","type":"article","venue":"RMD Open","topic":"Spondyloarthritis Studies and Treatments","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Janssen Biotech; Berlin Institute of Health; Swedish Orphan Biovitrum; Technische Universität München; European Commission; Bundesministerium für Bildung und Forschung; Canon Medical Systems Corporation; Max Kade Foundation; Schering-Plough; AbbVie; Bayern Innovativ; Celgene; Pfizer; Australian Government; Wyeth; Wilhelm Sander-Stiftung; Amgen; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Medicine; Sacroiliitis; Deep learning; Radiography; Radiographic anatomy; Artificial intelligence; Anatomy; Medical physics; Radiology; Disease; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004236982,0.0008379643,0.0008970966,0.001280765,0.0002000091,0.001021901,0.0006741841,0.0008554184,0.0006194625],"category_scores_gemma":[0.01250183,0.0002695683,0.0007531611,0.0004927774,0.0004669562,0.000864548,0.001033686,0.0009981489,0.0002309467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005567208,"about_ca_system_score_gemma":0.0006778332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003892653,"about_ca_topic_score_gemma":0.006670056,"domain_scores_codex":[0.9987445,0.0005397899,0.00008821455,0.0003225318,0.0001910728,0.0001138346],"domain_scores_gemma":[0.9960848,0.001985845,0.0007842071,0.0004059576,0.000517613,0.0002216191],"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":[0.00157076,0.0004872076,0.6801475,0.0002986353,0.0007554916,0.0002500122,0.0001841185,0.1100575,0.00674371,0.0002260103,0.001155344,0.1981239],"study_design_scores_gemma":[0.00008334022,0.001367473,0.3682264,0.0001715892,0.0003485061,0.0006164231,0.0001212083,0.6219932,0.004207894,0.001892789,0.0009013929,0.00006961104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9739615,0.001318534,0.02246134,0.0003593062,0.00003712274,0.00006732126,0.0004736719,0.000306594,0.001014544],"genre_scores_gemma":[0.9941214,0.0001483126,0.005063574,0.00006007059,0.00002141777,0.00001331339,0.0003774068,0.000009258432,0.0001852596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004236982,"threshold_uncertainty_score":0.02240759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01419501059822151,"score_gpt":0.2989372230836289,"score_spread":0.2847422124854074,"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."}}