{"id":"W4409012183","doi":"10.1016/j.sleep.2025.106485","title":"Separating obstructive and central respiratory events during sleep using breathing sounds: Utilizing transfer learning on deep convolutional networks","year":2025,"lang":"en","type":"article","venue":"Sleep Medicine","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transfer of learning; Sleep (system call); Breathing; Respiratory system; Computer science; Medicine; Audiology; Speech recognition; Artificial intelligence; Anesthesia; Internal medicine","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":[0.0003680117,0.0006134798,0.0003735206,0.0005800638,0.0001913583,0.0005307078,0.0003958219,0.0005146612,0.001016251],"category_scores_gemma":[0.001012844,0.0002027407,0.0004962348,0.0004882579,0.0001798882,0.0006612351,0.0006774641,0.0007946051,0.0004659636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002302765,"about_ca_system_score_gemma":0.0004988786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003892859,"about_ca_topic_score_gemma":0.005934238,"domain_scores_codex":[0.9998763,0.00001827475,0.000008179461,0.00003770592,0.00002654041,0.00003290688],"domain_scores_gemma":[0.9997308,0.0001395771,0.00002509594,0.00002032328,0.00005715643,0.0000270164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007419089,0.0004946082,0.02062414,0.0001251298,0.0001609956,0.0002247616,0.0001219045,0.08787704,0.05835675,0.001318475,0.002516245,0.8274379],"study_design_scores_gemma":[0.00001337365,0.0001011366,0.01317234,0.00002074653,0.00005195523,0.00009411016,0.00004827658,0.9730985,0.01074568,0.001773917,0.0008623611,0.00001763337],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.387359,0.001492527,0.6045879,0.0004226864,0.0002838724,0.00009763838,0.0006657601,0.001412895,0.003677795],"genre_scores_gemma":[0.9457529,0.0005161904,0.04937283,0.000100976,0.000123977,0.00004076754,0.0007705917,0.00005192785,0.003269864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003892859,"threshold_uncertainty_score":0.007740438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0247965041509437,"score_gpt":0.3166241639548739,"score_spread":0.2918276598039302,"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."}}