A somnologist’s guide to explainable deep neural networks for sleep scoring

Watson NF, Fernandez CR (2021) Artificial intelligence and sleep: Advancing sleep medicine. Sleep Med Rev 59:101512

Article  PubMed  Google Scholar 

Bandyopadhyay A, Goldstein C (2023) Clinical applications of artificial intelligence in sleep medicine: a sleep clinician’s perspective. Sleep Breath 27(1):39–55

Article  PubMed  Google Scholar 

Iber C, Ancoli-Israel S, Chesson AL, Quan S (2017) The AASM manual for the scoring of sleep and associated events: rules, terminology and technical specifications. American Academy of Sleep Medicine, Westchester

Google Scholar 

Stephansen JB, Olesen AN, Olsen M, Ambati A, Leary EB, Moore HE, Carrillo O, Lin L, Han F, Yan H, Sun YL, Dauvilliers Y, Scholz S, Barateau L, Hogl B, Stefani A, Hong SC, Kim TW, Pizza F, Plazzi G, Vandi S, Antelmi E, Perrin D, Kuna ST, Schweitzer PK, Kushida C, Peppard PE, Sorensen HBD, Jennum P, Mignot E (2018) Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy. Nat Commun 9(1):5229

Article  CAS  PubMed  PubMed Central  Google Scholar 

Ehrlich F, Sehr T, Brandt M, Schmidt M, Malberg H, Sedlmayr M, Goldammer M (2024) State-of-the-art sleep arousal detection evaluated on a comprehensive clinical dataset. Sci Rep 14(1):16239

Article  CAS  PubMed  PubMed Central  Google Scholar 

Park MJ, Choi JH, Ha TK, Lee HD, Lee YJ (2024) 0521 validation of deep learning algorithm model in automatic scoring of the respiratory events in adult polysomnography. Sleep 47(Supplement_1):A223–A224

Article  Google Scholar 

Penzel T, Behler P‑G, Von Buttlar M, Conradt R, Meier M, Moller A, Danker-Hopfe H (2003) Reliablitat der visuellen Schlafauswertung nach Rechtschaffen und Kales von acht Aufzeichnungen durch neun Schlaflabore. Reliability of Visual Evaluation of Sleep Stages According to Rechtschaffen and Kales from Eight Polysomnographs by Nine Sleep Centres. Somnologie 7(2):49–58

Article  Google Scholar 

Basner M, Griefahn B, Penzel T (2008) Inter-rater agreement in sleep stage classification between centers with different backgrounds. Somnol Schlafforsch Schlafmed 12(1):75–84

Article  Google Scholar 

Penzel T, Zhang X, Fietze I (2013) Inter-scorer reliability between sleep centers can teach us what to improve in the scoring rules. J Clin Sleep Med 9(1):89–91

Article  PubMed  PubMed Central  Google Scholar 

Penzel T (2022) Sleep scoring moving from visual scoring towards automated scoring. Sleep 45(10):zsac190

Article  PubMed  PubMed Central  Google Scholar 

Smith JR, Karacan I (1971) EEG sleep stage scoring by an automatic hybrid system. Electroencephalogr Clin Neurophysiol 31(3):231–237

Article  CAS  PubMed  Google Scholar 

Task Force “Auswertung polysomnographischer Ableitungen” der AG, Kommission Ausbildung der DGSM, Rodenbeck A, Danker-Hopfe H, Geisler P, Binder R, Lund R, Raschke F, Weeß H‑G, Schulz H (2014) Ergänzende Regeln zu Frequenzen und Graphoelementen der Schlafstadienanalyse. Somnol Schlafforsch Schlafmed 19:51–60

Google Scholar 

Boostani R, Karimzadeh F, Nami M (2017) A comparative review on sleep stage classification methods in patients and healthy individuals. Comput Methods Programs Biomed 140:77–91

Article  PubMed  Google Scholar 

Jansen C, Hodel S, Penzel T, Spott M, Krefting D (2018) Feature relevance in physiological networks for classification of obstructive sleep apnea. Physiol Meas 39(12):124003

Article  PubMed  Google Scholar 

Yue H, Chen Z, Guo W, Sun L, Dai Y, Wang Y, Ma W, Fan X, Wen W, Lei W (2024) Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice. Sleep Med Rev 74:101897

Article  PubMed  Google Scholar 

Goldammer M, Zaunseder S, Brandt MD, Malberg H, Gräßer F (2022) Investigation of automated sleep staging from cardiorespiratory signals regarding clinical applicability and robustness. Biomed Signal Process Control 71:103047

Article  Google Scholar 

Supratak A, Dong H, Wu C, Guo Y (2017) Deepsleepnet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans Neural Syst Rehabil Eng 25(11):1998–2008

Article  PubMed  Google Scholar 

Maurer MC, Metsch JM, Hempel P, Bender T, Spicher N, Hauschild A‑C (2024) Explainable artificial intelligence on biosignals for clinical decision support. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp 6597–6604

Chapter  Google Scholar 

Hassija V, Chamola V, Mahapatra A, Singal A, Goel D, Huang K, Scardapane S, Spinelli I, Mahmud M, Hussain A (2024) Interpreting black-box models: a review on explainable artificial intelligence. Cogn Comput 16(1):45–74

Article  Google Scholar 

Lee YJ, Lee JY, Cho JH, Choi JH (2022) Interrater reliability of sleep stage scoring: a meta-analysis. J Clin Sleep Med 18(1):193–202

Article  PubMed  PubMed Central  Google Scholar 

Zhang L, Fabbri D, Upender R, Kent D (2019) Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks. Sleep 42(11):zsz159

Article  PubMed  PubMed Central  Google Scholar 

Zhou W, Zhu H, Shen N, Chen H, Fu C, Yu H, Shu F, Chen C, Chen W (2023) A lightweight segmented attention network for sleep staging by fusing local characteristics and adjacent information. Ieee Trans Neural Syst Rehabil Eng 31:238–247

Article  PubMed  Google Scholar 

Zhu H, Zhou W, Fu C, Wu Y, Shen N, Shu F, Yu H, Chen W, Chen C (2023) Masksleepnet: a cross-modality adaptation neural network for heterogeneous signals processing in sleep staging. IEEE J Biomed Health Inform 27(5):2353–2364

Article  PubMed  Google Scholar 

Biswal S, Sun H, Goparaju B, Westover MB, Sun J, Bianchi MT (2018) Expert-level sleep scoring with deep neural networks. J Am Med Inform Assoc 25(12):1643–1650

Article  PubMed  PubMed Central  Google Scholar 

Ellis CA, Zhang R, Carbajal DA, Miller RL, Calhoun VD, Wang MD (2021) Explainable sleep stage classification with multimodal electrophysiology time-series. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp 2363–2366

Google Scholar 

Dutt M, Redhu S, Goodwin M, Omlin CW (2023) SleepXAI: An explainable deep learning approach for multi-class sleep stage identification. Appl Intell 53(13):16830–16843

Article  Google Scholar 

Vaquerizo-Villar F, Gutiérrez-Tobal GC, Calvo E, Álvarez D, Kheirandish-Gozal L, del Campo F, Gozal D, Hornero R (2023) An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea. Comput Biol Med 165:107419

Article  PubMed  Google Scholar 

Zhang G‑Q, Cui L, Mueller R, Tao S, Kim M, Rueschman M, Mariani S, Mobley D, Redline S (2018) The national sleep research resource: towards a sleep data commons. J Am Med Inform Assoc 25(10):1351–1358

Article  PubMed  PubMed Central  Google Scholar 

Quan SF, Howard BV, Iber C, Kiley JP, Nieto FJ, O’Connor GT, Rapoport DM, Redline S, Robbins J, Samet JM, Wahl PW (1997) The Sleep Heart Health Study: design, rationale, and methods. Sleep 20(12):1077–1085

CAS  PubMed  Google Scholar 

Howe-Patterson M, Pourbabaee B, Benard F (2018) Automated detection of sleep arousals from polysomnography data using a dense convolutional neural network. In: 2018 Computing in Cardiology Conference (CinC), vol 45, pp 1–4

Chapter  Google Scholar 

Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol 70, pp 3319–3328

Google Scholar 

Kokhlikyan N, Miglani V, Martin M, Wang E, Alsallakh B, Reynolds J, Melnikov A, Kliushkina N, Araya C, Yan S, Reblitz-Richardson O (2020) Captum: A unified and generic model interpretability library for PyTorch. arXiv

Google Scholar 

Huijben IAM, Overeem S, van Gilst MM, van Sloun RJG (2024) Attention on sleep stage specific characteristics. In: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp 1–4

Google Scholar 

Bender T, Beinecke JM, Krefting D, Muller C, Dathe H, Seidler T, Spicher N, Hauschild A‑C (2023) Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria. IEEE J Biomed Health Inform

Comments (0)

No login
gif