{"id":"W2914462514","doi":"10.2196/13030","title":"Achieving Rapid Blood Pressure Control With Digital Therapeutics: Retrospective Cohort and Machine Learning Study","year":2019,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Retrospective cohort study; Control (management); Medicine; Cohort; Blood pressure; Computer science; Artificial intelligence; Internal medicine","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":[0.0007989359,0.0002360712,0.0006196275,0.00008040349,0.000801014,0.00003389986,0.0001310932,0.0001576963,0.0001356807],"category_scores_gemma":[0.00003969149,0.0001811942,0.00005993178,0.0001901863,0.00004850027,0.0001660697,0.00007283986,0.001199656,0.0001224521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005639335,"about_ca_system_score_gemma":0.0002366586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001197264,"about_ca_topic_score_gemma":0.00003576613,"domain_scores_codex":[0.9975399,0.0004653676,0.000445665,0.000561415,0.0003653397,0.0006222966],"domain_scores_gemma":[0.9983518,0.0003754621,0.0002722975,0.0005226156,0.000201505,0.000276339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002131558,0.0001310305,0.9942632,0.0002046957,0.000461345,0.000002465023,0.001248669,0.00001831263,0.00002889463,0.0001719403,0.00009727692,0.003158954],"study_design_scores_gemma":[0.004483667,0.0009344648,0.8778884,0.00006986947,0.0003855013,0.000007596916,0.001354727,0.0001309308,8.605454e-7,0.00001176801,0.1145541,0.0001780851],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586508,0.003033926,0.0001504307,0.0004949057,0.0002003923,0.01842628,0.0001243607,0.0002785769,0.01864034],"genre_scores_gemma":[0.9889863,0.0002014405,0.00002955617,0.0006459847,0.0002607578,0.007259308,0.0000305993,0.00005497331,0.002531045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1163749,"threshold_uncertainty_score":0.7388885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01618817886135154,"score_gpt":0.3328059048448794,"score_spread":0.3166177259835278,"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."}}