{"id":"W4385951900","doi":"10.2196/42756","title":"Identification of Risk Groups for and Factors Affecting Metabolic Syndrome in South Korean Single-Person Households Using Latent Class Analysis and Machine Learning Techniques: Secondary Analysis Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Korean Urban and Social Studies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Metabolic syndrome; Latent class model; Obesity; Binge drinking; Logistic regression; Abdominal obesity; Medicine; Categorization; Environmental health; Gerontology; Demography; Psychology; Artificial intelligence; Computer science; Machine learning; Internal medicine; Poison control","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":[0.00301644,0.0001405895,0.0004711625,0.0009772761,0.0005813187,0.00007692057,0.0001152637,0.00006221099,0.00001386569],"category_scores_gemma":[0.0001725768,0.0001195313,0.0001288989,0.004727497,0.0002737883,0.0003006303,0.0002357808,0.0003414967,0.000001595448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001669477,"about_ca_system_score_gemma":0.000005429739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002284406,"about_ca_topic_score_gemma":0.001945398,"domain_scores_codex":[0.9979472,0.0005565215,0.000339483,0.0003276113,0.000480765,0.0003484299],"domain_scores_gemma":[0.9991247,0.0004227848,0.0002181888,0.0001332376,0.00003428559,0.00006681214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001546905,0.00008862286,0.8854471,0.00002494208,0.0005847264,0.000001721792,0.1104734,0.0002964015,0.001042892,0.000004220403,0.000001558488,0.002018924],"study_design_scores_gemma":[0.0002329949,0.000177912,0.9278917,0.000007268095,0.0003521889,2.720221e-7,0.05345587,0.01672073,0.001007307,0.00004383747,0.000002146116,0.0001077137],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998498,0.00007845635,0.0005633539,0.000007430572,0.000008119002,0.0006826232,0.00007872065,0.00004421783,0.00003910941],"genre_scores_gemma":[0.999757,0.00005658648,0.00006414676,8.829265e-7,0.000005070574,0.00004913638,0.00002835591,0.00001384168,0.00002499872],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05701757,"threshold_uncertainty_score":0.4874344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07627253472305726,"score_gpt":0.3410596871733324,"score_spread":0.2647871524502752,"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."}}