{"id":"W4411583343","doi":"10.1159/000547077","title":"Hypertension Screening Using Acoustic Analysis and Machine Learning of Random Speech Samples: A Feasibility Study","year":2025,"lang":"en","type":"article","venue":"Digital Biomarkers","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Speech recognition; Random forest; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003729979,0.0001305232,0.0004856782,0.0006769937,0.00008559493,0.00004214699,0.00004306851,0.00004923768,0.000004499865],"category_scores_gemma":[0.0004749488,0.0001078815,0.0002664396,0.001627765,0.0001105565,0.0001313858,0.00005574662,0.00009327882,1.032586e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002007453,"about_ca_system_score_gemma":0.00002432374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002034548,"about_ca_topic_score_gemma":0.00001012159,"domain_scores_codex":[0.9990413,0.00006415432,0.0003073643,0.0002818904,0.0001812075,0.0001240896],"domain_scores_gemma":[0.9993405,0.0001949098,0.00009506692,0.0001824423,0.0001280549,0.00005906271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009372901,0.0002206672,0.9523513,0.00007192108,0.002493618,0.00001570723,0.0001045594,0.00004889413,0.02232696,0.000001010282,0.000005892864,0.02142215],"study_design_scores_gemma":[0.004858615,0.0003602554,0.9660306,0.0002127433,0.003683882,0.00001957217,0.002748141,0.0137106,0.008102115,0.00006938237,0.00002465299,0.0001794578],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8956523,0.0002589351,0.1031643,0.00001835342,0.00001295551,0.0004528498,0.00002888654,0.00008124124,0.0003302245],"genre_scores_gemma":[0.9968913,0.00002249215,0.00296141,0.00002570928,0.000004822542,0.000004020557,0.00006158442,0.000006736232,0.00002195538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.101239,"threshold_uncertainty_score":0.439928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04065832093129684,"score_gpt":0.3026623307893222,"score_spread":0.2620040098580254,"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."}}