{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008045404,0.0003962192,0.00070546,0.0005152502,0.005256377,0.00007767877,0.001009925,0.001085748,0.00009169061],"category_scores_gemma":[0.008139333,0.0002986912,0.000223892,0.0007469222,0.0003130588,0.00006377637,0.002537664,0.008904945,0.00009941708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002358798,"about_ca_system_score_gemma":0.005208765,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434504,"about_ca_topic_score_gemma":0.001856811,"domain_scores_codex":[0.9890847,0.005863455,0.001099554,0.000983788,0.001140115,0.001828416],"domain_scores_gemma":[0.9819625,0.01091657,0.0004076493,0.001043916,0.005396939,0.0002724463],"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":[0.002039044,0.0004883794,0.4263315,0.1534854,0.001419788,0.00009081536,0.1533529,0.04304494,0.0005153966,0.002945337,0.006739417,0.2095471],"study_design_scores_gemma":[0.0001779978,0.0003040019,0.0002989817,0.01157675,0.0000594556,5.364811e-7,0.06287502,0.9138064,0.0007738954,0.000693391,0.009153715,0.0002798431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7970839,0.03687326,0.02568163,0.006523372,0.02616396,0.08028053,0.01864368,0.002542712,0.006206992],"genre_scores_gemma":[0.9835433,0.0003745772,0.003073099,0.0001139797,0.003539823,0.004084585,0.000793284,0.0001546595,0.004322703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8707615,"threshold_uncertainty_score":0.9999465,"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."}}