{"id":"W4412798192","doi":"10.2196/70621","title":"Optimizing Feature Selection and Machine Learning Algorithms for Early Detection of Prediabetes Risk: Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Prediabetes; Feature selection; Computer science; Selection (genetic algorithm); Artificial intelligence; Machine learning; Feature (linguistics); Pattern recognition (psychology); Medicine; Diabetes mellitus","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004310729,0.0001288034,0.0003055189,0.00031655,0.0008333253,0.00001124907,0.0000735923,0.000497516,0.000002049785],"category_scores_gemma":[0.0001883112,0.0001073543,0.00002410032,0.0003553488,0.000107578,0.00010076,0.0001143265,0.0008545755,0.000001515389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004574348,"about_ca_system_score_gemma":0.00004530818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003709005,"about_ca_topic_score_gemma":0.001136917,"domain_scores_codex":[0.9989091,0.0001121168,0.0004965737,0.0001549361,0.00006685927,0.0002604816],"domain_scores_gemma":[0.9989154,0.0003731691,0.000380724,0.0001068947,0.0001902993,0.00003353419],"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":[0.0004343733,0.0002043916,0.5471268,0.00217416,0.00025686,3.485702e-7,0.05674243,0.000144731,0.005367429,0.001544689,0.0001206366,0.3858832],"study_design_scores_gemma":[0.0009199831,0.003263564,0.02090793,0.000271958,0.00008514493,0.000001587215,0.07580084,0.8609986,0.03398797,0.001147246,0.00238575,0.0002294711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760046,0.0003038818,0.02041095,0.0004467399,0.0001668297,0.002444549,0.00003308721,0.0001313876,0.00005797948],"genre_scores_gemma":[0.9903874,0.0001934137,0.009015336,0.00002677652,0.00002459393,0.0002510555,0.000007107656,0.000006468206,0.00008788922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8608539,"threshold_uncertainty_score":0.6409349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289600529600652,"score_gpt":0.4114418252403894,"score_spread":0.3485458199443829,"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."}}