{"id":"W4403811165","doi":"10.2196/58732","title":"Predictive Models for Sustained, Uncontrolled Hypertension and Hypertensive Crisis Based on Electronic Health Record Data: Algorithm Development and Validation","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Blood Pressure and Hypertension Studies","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; Random forest; Logistic regression; Multilayer perceptron; Blood pressure; Statistic; Calibration; Gradient boosting; Machine learning; Ambulatory; Artificial intelligence; Electronic health record; Cross-validation; Ambulatory blood pressure; Statistics; Algorithm; Internal medicine; Computer science; Mathematics; Artificial neural network; Health care","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0405432,0.001504908,0.002492958,0.004064123,0.0006401601,0.002280293,0.002517893,0.001647084,0.001768092],"category_scores_gemma":[0.08136873,0.0008321294,0.003206057,0.002470945,0.000578307,0.001750676,0.001601152,0.003188572,0.0006132524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001724025,"about_ca_system_score_gemma":0.003467437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01020165,"about_ca_topic_score_gemma":0.005768123,"domain_scores_codex":[0.987636,0.009063679,0.0008760727,0.001366301,0.0007789578,0.0002790154],"domain_scores_gemma":[0.9143969,0.07632612,0.003191693,0.001727403,0.003893737,0.0004641799],"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":[0.002505068,0.001241981,0.2332842,0.0008132454,0.004683152,0.0003329689,0.0002975242,0.5709548,0.0004965695,0.002657752,0.006751928,0.1759809],"study_design_scores_gemma":[0.0002040037,0.0001813506,0.008538813,0.0001852666,0.0003588476,0.00011983,0.00005204276,0.9864225,0.0002390146,0.003103022,0.0005689682,0.00002630082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.425925,0.007555796,0.5499033,0.003747268,0.0002444154,0.001859595,0.006289723,0.002302247,0.002172713],"genre_scores_gemma":[0.7839788,0.001152372,0.2072548,0.0004794269,0.0001333704,0.001584311,0.0048014,0.00008097168,0.0005345425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0405432,"threshold_uncertainty_score":0.2144155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03727592752764215,"score_gpt":0.3097807563775295,"score_spread":0.2725048288498874,"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."}}