{"id":"W2752925099","doi":"10.6000/1927-5129.2017.13.77","title":"Analyzing Diabetes Datasets using Data Mining","year":2017,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Naive Bayes classifier; Computer science; Diabetes mellitus; Data mining; Domain (mathematical analysis); Random forest; Data set; Data science; Medicine; Artificial intelligence; Machine learning; Support vector machine; Mathematics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.007333509,0.0001404437,0.0003918928,0.0002146666,0.005577757,0.0001637582,0.003107322,0.0001087531,0.0001715028],"category_scores_gemma":[0.001656017,0.0001067512,0.00004481517,0.0002211558,0.0006483545,0.001242215,0.0008752457,0.0006342304,0.00004569176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009771912,"about_ca_system_score_gemma":0.001025049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002685161,"about_ca_topic_score_gemma":0.0004158024,"domain_scores_codex":[0.997124,0.0001889075,0.001073713,0.0003512042,0.0006196116,0.0006425736],"domain_scores_gemma":[0.9952759,0.0009174933,0.00228316,0.001110091,0.000189468,0.0002238445],"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":[0.00004140706,0.00005407758,0.9194055,0.00015987,0.0000481372,0.00002762807,0.002686136,0.0002572759,0.01241049,0.00125475,0.009034956,0.05461983],"study_design_scores_gemma":[0.002917844,0.001478857,0.2314828,0.01207989,0.001114999,0.0001083803,0.23508,0.3672614,0.02805626,0.03381555,0.08279912,0.003804917],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932731,0.0002980276,0.0006059509,0.001539955,0.001594674,0.0002093755,0.00008450286,0.00001245788,0.002381944],"genre_scores_gemma":[0.986491,0.00003786899,0.01196716,0.0003655986,0.001101033,0.000002342323,0.000007897209,0.00001149454,0.00001557001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6879227,"threshold_uncertainty_score":0.9957169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4432978032849009,"score_gpt":0.5419335777827297,"score_spread":0.09863577449782873,"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."}}