{"id":"W2921319512","doi":"10.12659/msm.913283","title":"Sociodemographic Indicators of Health Status Using a Machine Learning Approach and Data from the English Longitudinal Study of Aging (ELSA)","year":2019,"lang":"en","type":"article","venue":"Medical Science Monitor","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"Economic and Social Research Council; Medical Research Council; European Commission; Wellcome Trust; World Health Organization","keywords":"Longitudinal study; Random forest; Machine learning; Gerontology; Metric (unit); Artificial intelligence; Medicine; Psychology; Demography; Statistics; Computer science; Mathematics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00872492,0.00009355185,0.0003331699,0.0001170767,0.001078163,0.00006607567,0.00113267,0.00006221422,0.00007177284],"category_scores_gemma":[0.002236537,0.0000629721,0.00002498175,0.001125976,0.001720715,0.0003048219,0.0005350281,0.0003781265,3.836931e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007565818,"about_ca_system_score_gemma":0.001254632,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1194069,"about_ca_topic_score_gemma":0.002458848,"domain_scores_codex":[0.9959122,0.000612351,0.0004268929,0.0004196364,0.002015715,0.0006131906],"domain_scores_gemma":[0.9981583,0.0006930054,0.0003040483,0.0003533707,0.00007165651,0.0004196387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002685891,0.0001183915,0.9644518,0.00003526861,0.000008545405,3.204453e-7,0.02983217,0.000006875558,0.000001207741,0.0001378345,0.00001026203,0.005394637],"study_design_scores_gemma":[0.0004407938,0.00008251602,0.9081353,0.00009493645,0.00001252249,1.424873e-7,0.08517031,0.005394103,0.000001766356,0.00002200489,0.0005659066,0.00007970189],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99658,0.001356383,0.00008677926,0.0009804153,0.000453444,0.0003863678,0.00002229485,0.0000189048,0.0001154054],"genre_scores_gemma":[0.9989324,0.0003024156,0.0004227941,0.0001480239,0.0001740912,0.000002460276,0.000005000889,0.000005297946,0.000007472285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.116948,"threshold_uncertainty_score":0.8864571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09232749217418024,"score_gpt":0.4097772661140989,"score_spread":0.3174497739399186,"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."}}