{"id":"W4413355529","doi":"10.1016/j.compbiomed.2025.110887","title":"Non-invasive integrated swallowing kinematic analysis framework leveraging transformer-based multi-task neural networks","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Dysphagia Assessment and Management","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto General Hospital; North York General Hospital","funders":"National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Pittsburgh","keywords":"Computer science; Kinematics; Artificial neural network; Transformer; Task (project management); Swallowing; Artificial intelligence; Machine learning; Medicine; Engineering; Systems engineering; Voltage; Electrical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005719741,0.0009528892,0.0009936823,0.0006856717,0.0002937529,0.0007305166,0.0009839119,0.0006942364,0.002341623],"category_scores_gemma":[0.001002932,0.0004102094,0.0009151698,0.0006276004,0.0001888417,0.0009075034,0.001064786,0.0008521273,0.001135765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002673112,"about_ca_system_score_gemma":0.0007940907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004684832,"about_ca_topic_score_gemma":0.008332759,"domain_scores_codex":[0.9996943,0.00003754907,0.00002296145,0.0000858049,0.0001130333,0.00004630231],"domain_scores_gemma":[0.999755,0.00007177166,0.00002426901,0.00001764112,0.0001103346,0.00002093596],"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":[0.0004325645,0.0002966484,0.002479307,0.000219017,0.0002338017,0.0002598321,0.0000685918,0.1418889,0.03680542,0.001918406,0.002927207,0.8124703],"study_design_scores_gemma":[0.000008652999,0.00007846526,0.001018616,0.00001160036,0.00004208354,0.0001150446,0.00001178515,0.9930468,0.003810027,0.001145817,0.0006976609,0.00001333776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01015712,0.0003829351,0.9872262,0.00006929884,0.0000688295,0.00005376584,0.000131043,0.0009481877,0.0009627084],"genre_scores_gemma":[0.6968096,0.001036426,0.2926609,0.0002564706,0.0001801435,0.0002872729,0.001003913,0.0002026367,0.007562685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004684832,"threshold_uncertainty_score":0.009315133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03256685843091433,"score_gpt":0.4151724076177434,"score_spread":0.382605549186829,"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."}}