{"id":"W3154072984","doi":"10.1097/01.hjh.0000745088.97388.2a","title":"MACHINE LEARNING CLUSTERING FOR BLOOD PRESSURE VARIABILITY: VALIDATION FROM THE SPRINT TO THE HONG KONG COMMUNITY COHORT","year":2021,"lang":"en","type":"article","venue":"Journal of Hypertension","topic":"Blood Pressure and Hypertension Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Medicine; Cohort; Sprint; k-medians clustering; Quantile; Quantile regression; Silhouette; Artificial intelligence; Statistics; Machine learning; Physical therapy; Internal medicine; Correlation clustering; Computer science; Mathematics; CURE data clustering algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01087201,0.0007872634,0.0006548548,0.0009273691,0.001066035,0.0007311169,0.001113986,0.0006051758,0.0009413869],"category_scores_gemma":[0.01523042,0.0002740766,0.001115904,0.0006881826,0.0006944904,0.0003301678,0.001143072,0.0008651827,0.0004809526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127294,"about_ca_system_score_gemma":0.001929683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07808775,"about_ca_topic_score_gemma":0.04069521,"domain_scores_codex":[0.9977355,0.001243014,0.0001243796,0.0004455472,0.0002578178,0.0001936248],"domain_scores_gemma":[0.9906396,0.002655904,0.001068093,0.002368947,0.002473949,0.0007936195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002490934,0.0005928013,0.9608961,0.00008857551,0.0007558392,0.0002502654,0.0007739561,0.01085688,0.0009417064,0.0001580691,0.002833813,0.01936107],"study_design_scores_gemma":[0.0001828559,0.0009541247,0.9324276,0.00004041469,0.0001657353,0.0002855278,0.000906249,0.06316011,0.0006816052,0.0001866993,0.0009692406,0.00003986625],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971307,0.00008294188,0.001553437,0.00005538626,0.00001543755,0.000110653,0.0008694862,0.00003168371,0.0001503996],"genre_scores_gemma":[0.9933907,0.00007394561,0.002347404,0.00003842491,0.0000156531,0.0001468761,0.003523958,0.00001816875,0.0004449627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07808775,"threshold_uncertainty_score":0.1552665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05612765431382641,"score_gpt":0.2721815558907651,"score_spread":0.2160539015769387,"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."}}