{"id":"W4406898396","doi":"10.1088/1361-6579/adaf73","title":"PhysioEx: a new Python library for explainable sleep staging through deep learning","year":2025,"lang":"en","type":"article","venue":"Physiological Measurement","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; University of California, Davis; Dipartimenti di Eccellenza; Università di Pisa; York University; National Institutes of Health; Case Western Reserve University; Fonds Wetenschappelijk Onderzoek; University of Washington; Vlaamse regering; European Commission; Johns Hopkins University; University of Minnesota","keywords":"Computer science; Workflow; Toolbox; Python (programming language); Artificial intelligence; Preprocessor; Modular design; Deep learning; Sleep medicine; Pipeline (software); Sleep (system call); Benchmark (surveying); Machine learning; Programming language; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003417235,0.0002769947,0.0005182747,0.00009987285,0.0002838302,0.00005558779,0.0002318348,0.0001169941,0.000311706],"category_scores_gemma":[0.000721583,0.0002098981,0.0002485618,0.0004577511,0.00009971668,0.0002596095,0.0002456388,0.0004790127,0.00004700727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002813849,"about_ca_system_score_gemma":0.0001028312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002043255,"about_ca_topic_score_gemma":7.22779e-7,"domain_scores_codex":[0.9974549,0.0001640065,0.0003336436,0.0006528856,0.00068643,0.0007081046],"domain_scores_gemma":[0.9989617,0.0001518623,0.00008283575,0.0003592528,0.0002507873,0.0001934952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002575378,0.0009875149,0.003522298,0.000976583,0.0006874797,0.0000266949,0.0004747447,0.0007381702,0.7831936,0.01133757,0.007737254,0.1877427],"study_design_scores_gemma":[0.02002862,0.006229293,0.1537274,0.001264673,0.0006878624,0.00001123582,0.003781497,0.02459079,0.5060668,0.1187299,0.1632298,0.001652088],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6391954,0.008146863,0.267336,0.01618583,0.001437688,0.01027848,0.00001924286,0.002465924,0.05493464],"genre_scores_gemma":[0.9870708,0.0000535381,0.01023166,0.0007789819,0.0003821777,0.0002867662,0.00003758117,0.00004193154,0.001116586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3478754,"threshold_uncertainty_score":0.8559396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08895725188585488,"score_gpt":0.33242141269409,"score_spread":0.2434641608082352,"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."}}