{"id":"W4416879348","doi":"10.1016/j.compbiomed.2025.111361","title":"Automated detection of chewing movements in videofluoroscopic swallowing studies using deep learning for landmark detection and motion analysis","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 Rehabilitation Institute; University Health Network","funders":"National Institute on Deafness and Other Communication Disorders; National Institute on Aging","keywords":"Swallowing; Mastication; Landmark; Segmentation; Deep learning; Motion analysis","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":[0.0003495372,0.0004622064,0.0005497052,0.001113946,0.000164393,0.0005060944,0.0004498325,0.0007398352,0.0008434996],"category_scores_gemma":[0.001144116,0.0002271265,0.0004931084,0.0005846371,0.0001283023,0.0003444666,0.000511704,0.0004841992,0.0005552049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002117082,"about_ca_system_score_gemma":0.0004162674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003354465,"about_ca_topic_score_gemma":0.007129143,"domain_scores_codex":[0.9998426,0.00002392068,0.0000104334,0.00005012018,0.00004032753,0.00003253271],"domain_scores_gemma":[0.9997131,0.0001129047,0.00003885562,0.0000227618,0.00008878767,0.0000235369],"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":[0.0005563286,0.0001812926,0.01614828,0.0002400424,0.0001244538,0.0004647178,0.000111991,0.01406556,0.1771463,0.0005682149,0.003903501,0.7864894],"study_design_scores_gemma":[0.00003776002,0.0002512718,0.04166649,0.00006291912,0.0001023524,0.00117509,0.0001015493,0.8904842,0.06226282,0.001162812,0.002653331,0.00003925417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2936774,0.002054942,0.6989012,0.0002759424,0.00009558039,0.0001441632,0.001010102,0.002271246,0.001569376],"genre_scores_gemma":[0.7785395,0.0008775361,0.2162293,0.0001414593,0.00005969667,0.000116295,0.0009810459,0.0001235649,0.002931518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003354465,"threshold_uncertainty_score":0.006669879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0439302690733535,"score_gpt":0.4581775290645605,"score_spread":0.414247259991207,"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."}}