{"id":"W2810043513","doi":"10.1126/science.aar5045","title":"Predictive modeling of U.S. health care spending in late life","year":2018,"lang":"en","type":"article","venue":"Science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; National Institute for Health Care Management Foundation","keywords":"Quarter (Canadian coin); Ex-ante; Demography; Interpretation (philosophy); Economics; Demographic economics; Health care; Health spending; Actuarial science; Gerontology; Medicine; Geography; Economic growth; Sociology; Computer science; Macroeconomics; Health insurance","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002088818,0.0004830113,0.0005044061,0.0009791898,0.0003596636,0.00108876,0.000653443,0.0006421608,0.002260059],"category_scores_gemma":[0.008100789,0.0002645719,0.0007135515,0.001144951,0.0005127398,0.0006860763,0.0005178786,0.001212292,0.0003989831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001623411,"about_ca_system_score_gemma":0.0008797676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05496217,"about_ca_topic_score_gemma":0.04785819,"domain_scores_codex":[0.9996846,0.0001511325,0.00001258968,0.00006237088,0.00002656013,0.00006272735],"domain_scores_gemma":[0.9968527,0.00224534,0.0003435873,0.0001580406,0.0002710295,0.0001292774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003013262,0.00013871,0.1464884,0.00003054545,0.0001188395,0.0001343603,0.0001413251,0.8288646,0.000180993,0.00802595,0.004285559,0.0112894],"study_design_scores_gemma":[0.00001273711,0.00002221468,0.01770802,0.00001408456,0.00001353452,0.00002245055,0.0000551858,0.9766915,0.0000568673,0.005039606,0.0003566012,0.000007197079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9850589,0.0004725676,0.008441136,0.00206251,0.00004043891,0.00002038604,0.002012272,0.00009970534,0.001792032],"genre_scores_gemma":[0.9959336,0.000240916,0.001074847,0.0001020693,0.00002410503,0.00001909196,0.001624202,0.00001337784,0.0009678252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05496217,"threshold_uncertainty_score":0.1092845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0359687558452922,"score_gpt":0.3474196464919873,"score_spread":0.3114508906466951,"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."}}