{"id":"W4383618673","doi":"10.1016/j.jvoice.2023.06.006","title":"A Machine-Learning Algorithm for the Automated Perceptual Evaluation of Dysphonia Severity","year":2023,"lang":"en","type":"article","venue":"Journal of Voice","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Perception; Computer science; Speech recognition; Vowel; Support vector machine; Correlation; Scale (ratio); Point (geometry); Gold standard (test); Quality (philosophy); Artificial intelligence; Pattern recognition (psychology); Psychology; Mathematics; Statistics","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":[0.002011982,0.0009905098,0.0016433,0.001986904,0.0006102119,0.001270958,0.001641595,0.001600268,0.003603129],"category_scores_gemma":[0.005348124,0.0003943011,0.0008969231,0.001324402,0.0003426031,0.0006927978,0.0009532606,0.001472778,0.002408957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007218781,"about_ca_system_score_gemma":0.001300339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00682709,"about_ca_topic_score_gemma":0.006521078,"domain_scores_codex":[0.9989976,0.0001746974,0.0001301077,0.0003155741,0.0002833373,0.00009858044],"domain_scores_gemma":[0.997997,0.001025394,0.0001163072,0.00009737966,0.0007041133,0.00005973992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003090601,0.0002349641,0.002876827,0.00008076482,0.00008861986,0.0000702932,0.00003725306,0.02579956,0.009562255,0.0007445217,0.004621981,0.9555739],"study_design_scores_gemma":[0.00005893017,0.0001410884,0.003926131,0.00003047104,0.00004427097,0.0001692935,0.00002564287,0.9858581,0.006478762,0.001568326,0.001670412,0.00002846778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02602729,0.0007304112,0.9670396,0.0002493056,0.0001641523,0.0002900724,0.000581992,0.003793798,0.001123358],"genre_scores_gemma":[0.2392628,0.0003141011,0.7541479,0.0003006004,0.0001580408,0.0007572434,0.001430548,0.0001514325,0.003477398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00682709,"threshold_uncertainty_score":0.01357472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04424312682559635,"score_gpt":0.354079837119072,"score_spread":0.3098367102934757,"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."}}