{"id":"W4378674477","doi":"10.1152/physiol.2023.38.s1.5695980","title":"A multimodal neural network that distinguishes between type 1 and type 2 diabetes in young persons using MRI and clinical data","year":2023,"lang":"en","type":"article","venue":"Physiology","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Support vector machine; Random forest; Artificial intelligence; Type 2 diabetes; Logistic regression; Artificial neural network; Computer science; Medicine; Type 1 diabetes; Diabetes mellitus; Decision tree; Kidney disease; Machine learning; Internal medicine; Endocrinology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001208699,0.00009954923,0.0003105639,0.00002995871,0.00005503371,0.000009789466,0.00005847282,0.00005911401,0.00001156085],"category_scores_gemma":[0.0001729358,0.0000780078,0.00002094457,0.0001629342,0.0001162896,0.00004432235,0.0002477721,0.0001039833,0.000007203389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001110082,"about_ca_system_score_gemma":0.0000283952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002173576,"about_ca_topic_score_gemma":0.00005265501,"domain_scores_codex":[0.9991668,0.00008002899,0.0001291298,0.0003381404,0.00004911433,0.0002367255],"domain_scores_gemma":[0.9992281,0.0003836159,0.00003755189,0.0002314652,0.00002209125,0.0000972038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005160024,0.00005787985,0.997582,0.00002701523,0.0001126134,0.00001876963,0.00006185007,0.00001279267,0.000080174,0.000003935915,0.0006701655,0.001321186],"study_design_scores_gemma":[0.0006994093,0.0001891666,0.9733277,0.00004946863,0.0002168969,0.000001464404,0.00005429236,0.02526118,0.000003740548,0.00006420389,0.00006264151,0.00006985175],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984594,0.0008053868,1.579964e-7,0.0002484612,0.0002211708,0.0001612345,0.00004545058,0.00003054719,0.0000282174],"genre_scores_gemma":[0.9984149,0.0003826658,0.0001626251,0.00008980535,0.000474495,0.000003458223,0.0004519173,0.0000122068,0.000007917695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02524839,"threshold_uncertainty_score":0.3181066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1470161953864138,"score_gpt":0.3898118050757689,"score_spread":0.2427956096893552,"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."}}