{"id":"W2588815870","doi":"10.1109/ssci.2016.7849886","title":"Using machine learning to predict hypertension from a clinical dataset","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Indian Institute of Technology Bombay","keywords":"Artificial neural network; Computer science; Machine learning; Artificial intelligence; Demographics; Disease; Coronary artery disease; Warning system; Risk factor; Medicine; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008004014,0.0001483511,0.0002439611,0.00008699149,0.0001590604,0.00007213438,0.00085487,0.00009288514,0.0002047753],"category_scores_gemma":[0.001172963,0.00009152836,0.00005285376,0.0002167778,0.00002752022,0.0003138935,0.0009245187,0.0003091535,0.0004756258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004210421,"about_ca_system_score_gemma":0.00007343552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002883247,"about_ca_topic_score_gemma":0.0001271986,"domain_scores_codex":[0.9977703,0.0004331986,0.0004317593,0.0006977817,0.000330382,0.0003365485],"domain_scores_gemma":[0.9978753,0.00072141,0.00009942848,0.000905632,0.0000705911,0.0003276497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005840682,0.0001040764,0.6854192,0.00001329783,0.00003650545,0.0001366749,0.0002041721,0.0008704324,0.004526327,0.001478683,0.01641386,0.2907383],"study_design_scores_gemma":[0.0006536375,0.0002852863,0.03697747,0.0001169148,0.000008508884,0.0000348799,0.000006464337,0.8043609,0.0001802323,0.0003270868,0.1567716,0.0002770795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2790734,0.00006699707,0.7101563,0.008941509,0.0007438069,0.000200996,0.0001885606,0.0004693166,0.0001591007],"genre_scores_gemma":[0.6343539,0.00001977568,0.3606552,0.004186443,0.0003640612,0.000004417306,0.0001108514,0.00002273371,0.0002826414],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8034905,"threshold_uncertainty_score":0.6113366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1323618872952212,"score_gpt":0.3877024547970157,"score_spread":0.2553405675017945,"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."}}