{"id":"W4408335193","doi":"10.21203/rs.3.rs-6195549/v1","title":"A Multilingual Predictive System for Type 2 Diabetes using the CATBoost Machine Learning Algorithm","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Type (biology); Algorithm","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":[0.001122706,0.0008601139,0.001079157,0.001737601,0.001175449,0.001160642,0.001124187,0.0009282531,0.005557531],"category_scores_gemma":[0.002368909,0.0003421662,0.0008310035,0.001379654,0.0002333972,0.001159607,0.001196775,0.001147785,0.00321649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008190302,"about_ca_system_score_gemma":0.001784655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02461998,"about_ca_topic_score_gemma":0.0238817,"domain_scores_codex":[0.9994513,0.00008392017,0.00004669454,0.0002153692,0.0001285739,0.00007414658],"domain_scores_gemma":[0.999104,0.0002848234,0.00003896416,0.00006713746,0.0004488001,0.00005627317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001509216,0.0009144594,0.007500598,0.0002404513,0.0002414965,0.0004257358,0.0001103613,0.0503177,0.01635269,0.001527231,0.02435667,0.8965034],"study_design_scores_gemma":[0.00008236769,0.0001129919,0.002026273,0.00002897254,0.0001432447,0.0001600003,0.00005688969,0.9808965,0.008813324,0.002342922,0.005295224,0.00004132546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1146137,0.002096715,0.8401456,0.000841136,0.001260867,0.0003166584,0.003016486,0.03011422,0.007594546],"genre_scores_gemma":[0.5829147,0.0006713739,0.39592,0.0004999286,0.0004270447,0.0004266674,0.006660237,0.0007519517,0.01172815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02461998,"threshold_uncertainty_score":0.04895335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3764831869094132,"score_gpt":0.5993380618965096,"score_spread":0.2228548749870964,"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."}}