{"id":"W4281885821","doi":"10.1093/sleep/zsac079.603","title":"0606 A Paradigm for Testing the Accuracy of Digital Sleep Staging Systems","year":2022,"lang":"en","type":"article","venue":"SLEEP","topic":"Health Education and Validation","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Center for Innovations in Quality, Effectiveness and Safety; National Institutes of Health; Office of Research and Development","keywords":"Computer science; Consistency (knowledge bases); Sleep (system call); Artificial intelligence; Programming language","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":[0.0173786,0.0005008681,0.0003150865,0.00134369,0.0006440053,0.001120987,0.0009326618,0.0009817455,0.003434903],"category_scores_gemma":[0.03270683,0.000306796,0.0005075526,0.0008793586,0.001258677,0.001091352,0.001917898,0.000511006,0.0009428742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009101082,"about_ca_system_score_gemma":0.000751739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006764267,"about_ca_topic_score_gemma":0.0009341309,"domain_scores_codex":[0.9822462,0.009514831,0.001916927,0.002047753,0.003931741,0.0003426407],"domain_scores_gemma":[0.9719222,0.0125993,0.003963854,0.00384896,0.00702,0.0006457233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008039,0.002010428,0.4633338,0.001093132,0.0004072935,0.0002423235,0.003003018,0.006833491,0.141659,0.00838723,0.004772782,0.3602185],"study_design_scores_gemma":[0.001552674,0.05206627,0.7223017,0.0003419326,0.0003446223,0.00219103,0.002492157,0.07423191,0.1021666,0.0105129,0.0313486,0.0004495092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8046167,0.0004832112,0.176374,0.0004634304,0.0003254301,0.004124613,0.0009301091,0.0004567749,0.01222582],"genre_scores_gemma":[0.7269989,0.0001363369,0.2621022,0.000327378,0.00009149836,0.006544564,0.0007612657,0.00008174536,0.002956161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0173786,"threshold_uncertainty_score":0.09190792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1576774117074917,"score_gpt":0.4019923387980756,"score_spread":0.2443149270905839,"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."}}