{"id":"W3018269092","doi":"10.1016/j.compmedimag.2020.101718","title":"Early detection of ankylosing spondylitis using texture features and statistical machine learning, and deep learning, with some patient age analysis","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Spondyloarthritis Studies and Treatments","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Artificial intelligence; Random forest; Receiver operating characteristic; Cross-validation; Deep learning; Computer science; Machine learning; Classifier (UML); Pattern recognition (psychology); Cross entropy; Binary classification; Ankylosing spondylitis; Recall; Support vector machine; Medicine; Surgery","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001022195,0.0002010905,0.0005566606,0.0001631237,0.0002280597,0.00005131333,0.00002594582,0.00007747873,0.0000156635],"category_scores_gemma":[0.0001546677,0.0001542498,0.00005681954,0.0003545777,0.0004796049,0.00006343045,0.0001024251,0.0004799016,8.695297e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000947944,"about_ca_system_score_gemma":0.00001670483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002411905,"about_ca_topic_score_gemma":0.00002595493,"domain_scores_codex":[0.9987058,0.0001055277,0.0002353829,0.0003724422,0.00036018,0.0002206818],"domain_scores_gemma":[0.9992302,0.0001317565,0.0001063823,0.00006651541,0.00006390637,0.0004012257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001365345,0.0001747817,0.6246608,0.0004642999,0.001843667,0.002729885,0.003800689,0.00001258111,0.002053867,0.0003385938,0.000009947497,0.3625455],"study_design_scores_gemma":[0.01210271,0.003762444,0.6969162,0.0007265884,0.003714165,0.001667614,0.000682643,0.2759299,0.0001791303,0.0002106568,0.003530998,0.0005769992],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9595624,0.01191948,0.02775551,0.0004921199,0.00003375073,0.0001461082,0.00002643953,0.00005374949,0.00001050809],"genre_scores_gemma":[0.9938226,0.002212401,0.003427493,0.0003756872,0.00006083267,0.000002734321,0.00007581349,0.00001846404,0.000003970773],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3619686,"threshold_uncertainty_score":0.6290123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007484875278572186,"score_gpt":0.2478185041883662,"score_spread":0.240333628909794,"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."}}