{"id":"W2015334195","doi":"10.1016/j.artmed.2011.03.002","title":"Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals","year":2011,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Dysphagia Assessment and Management","field":"Health Professions","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; Toronto Rehabilitation Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Linear discriminant analysis; Medicine; Dysphagia; Airway; Bolus (digestion); Feature selection; Population; Artificial intelligence; Pattern recognition (psychology); Computer science; Radiology; Surgery","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001535864,0.0001406915,0.000313539,0.0003958045,0.0001420964,0.000003255344,0.0001311876,0.0001150969,0.0009580774],"category_scores_gemma":[0.0002596171,0.0001137089,0.00001634145,0.0003876272,0.0002314902,0.0001103254,0.00005359181,0.0003399879,0.00003005584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004868138,"about_ca_system_score_gemma":0.00006112632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000668522,"about_ca_topic_score_gemma":0.000500644,"domain_scores_codex":[0.9980539,0.0002435671,0.0008120614,0.00028961,0.0002810925,0.0003197805],"domain_scores_gemma":[0.9987627,0.0005588394,0.0002433765,0.0002200454,0.00008938384,0.0001256757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002555495,0.001085979,0.4978607,0.001141623,0.00006478974,0.00003393091,0.02098875,0.00007138844,0.008688501,0.1506556,0.002135351,0.3147179],"study_design_scores_gemma":[0.0008731352,0.003554193,0.8654668,0.001345827,0.00008411738,7.785589e-7,0.0348874,0.06732303,0.002901178,0.02216724,0.0009830552,0.000413232],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9634696,0.0001534662,0.01306001,0.003878675,0.0006347202,0.001060588,0.000003237664,0.00004410388,0.0176956],"genre_scores_gemma":[0.9969722,0.0001757145,0.0009973058,0.0015704,0.0001078921,0.00006710592,0.000008186419,0.00001264653,0.00008856096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3676061,"threshold_uncertainty_score":0.9999552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2288535864538902,"score_gpt":0.4560850632255627,"score_spread":0.2272314767716725,"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."}}