{"id":"W4309688772","doi":"10.3389/fbioe.2022.1082794","title":"MRI-based machine learning model: A potential modality for predicting cognitive dysfunction in patients with type 2 diabetes mellitus","year":2022,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Health Commission of Shanxi Province","keywords":"Type 2 Diabetes Mellitus; Receiver operating characteristic; Cognition; Logistic regression; Artificial intelligence; Support vector machine; Montreal Cognitive Assessment; Medicine; Magnetic resonance imaging; Machine learning; Dementia; Internal medicine; Diabetes mellitus; Computer science; Disease; Radiology; Psychiatry","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":[0.0003124206,0.0001464667,0.0002955226,0.0004888457,0.0001094991,0.000009184554,0.00006087727,0.0001287706,0.000002739522],"category_scores_gemma":[0.0001928844,0.0001358196,0.00002903914,0.0003684035,0.00009128343,0.00003285307,0.00005635463,0.0008582299,6.634438e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001204496,"about_ca_system_score_gemma":0.00003565037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002665549,"about_ca_topic_score_gemma":0.000001559763,"domain_scores_codex":[0.9989898,0.00003192046,0.0001984338,0.0003185002,0.0001434891,0.0003178104],"domain_scores_gemma":[0.9997361,0.00003096135,0.00006035406,0.00008932708,0.00003260592,0.00005067738],"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":[0.0007945985,0.0001525597,0.689722,0.0001347602,0.000058174,0.00001002567,0.00006797256,0.2837865,0.0004904089,0.00002244609,0.00003070492,0.02472985],"study_design_scores_gemma":[0.00434477,0.000971602,0.0169013,0.00008606999,0.00004819842,0.000003028008,0.0001173016,0.9768583,0.0002537161,0.00007121019,0.0002024511,0.0001420812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7774484,0.0006882712,0.2201658,0.0009553333,0.0002470416,0.0003516888,0.00001559129,0.0001238489,0.000003966168],"genre_scores_gemma":[0.9792609,0.0000564578,0.02029684,0.00009819803,0.00001966811,0.00006087669,0.0001647126,0.0000291439,0.00001326901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6930717,"threshold_uncertainty_score":0.5538563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003582490669884927,"score_gpt":0.1981401080024058,"score_spread":0.1945576173325209,"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."}}