{"id":"W4410076795","doi":"10.2196/69431","title":"Collection and Analysis of Repeated Speech Samples: Methodological Framework and Example Protocol","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Wellcome Trust","keywords":"Preprint; Protocol (science); Computer science; Data collection; Natural language processing; Psychology; Data science; World Wide Web; Medicine; Statistics; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2520132,0.003268987,0.002636225,0.003906113,0.004231001,0.00338623,0.004070919,0.004976009,0.01460706],"category_scores_gemma":[0.2888613,0.002710853,0.003773104,0.003994302,0.004084053,0.002135556,0.005097934,0.004279947,0.006088752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003288663,"about_ca_system_score_gemma":0.02149027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002374427,"about_ca_topic_score_gemma":0.004014396,"domain_scores_codex":[0.7954528,0.162755,0.02074788,0.006862929,0.01234912,0.001832224],"domain_scores_gemma":[0.7392727,0.1152125,0.01676233,0.06256083,0.06329019,0.002901476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.03514777,0.01152796,0.01110222,0.05669805,0.001928944,0.002565292,0.03404004,0.01060226,0.02919731,0.0639917,0.0890644,0.654134],"study_design_scores_gemma":[0.03849092,0.04009477,0.05302117,0.06030288,0.003385206,0.002274554,0.01208707,0.02886821,0.04462412,0.09544864,0.6194034,0.001999156],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.00435417,0.0004231938,0.2202173,0.0007308188,0.0005230301,0.7702657,0.001462418,0.0003235149,0.001699876],"genre_scores_gemma":[0.002456334,0.0001212507,0.1226485,0.0002465829,0.00004561751,0.874022,0.0001841186,0.00002143673,0.0002541186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2520132,"threshold_uncertainty_score":0.922401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.495173061314731,"score_gpt":0.6241466772327529,"score_spread":0.1289736159180218,"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."}}