Sleep apnea detection: accuracy of using automated ECG analysis compared to manually scored polysomnography (apnea hypopnea index)
- 278 Downloads
Adequate sleep is fundamental to wellness and recovery from illnesses and lack thereof is associated with disease onset and progression resulting in adverse health outcomes. Measuring sleep quality and sleep apnea (SA) at the point of care utilizing data that is already collected is feasible and cost effective, using validated methods to unlock sleep information embedded in the data. The objective of this study is to determine the utility of automated analysis of a stored, robust signal widely collected in hospital and outpatient settings, a single lead electrocardiogram (ECG), using clinically validated algorithms, cardiopulmonary coupling (CPC), to objectively and accurately identify SA.
Retrospective analysis of de-identified PSG data with expert level scoring of Apnea Hypopnea Index (AHI) dividing the cohort into severe OSA (AHI > 30), moderate (AHI 15–30), mild (AHI 5–15), and no disease (AHI < 5) was compared with automated CPC analysis of a single lead ECG collected during sleep for each subject. Statistical analysis was used to compare the two methods.
Sixty-eight ECG recordings were analyzed. CPC identified patients with moderate to severe SA with sensitivity of 100%, specificity of 81%, and agreement of 93%, LR+ (positive likelihood ratio) 5.20, LR− (negative likelihood ratio) 0.00 and kappa 0.85 compared with manual scoring of AHI.
The automated CPC analysis of stored single lead ECG data often collected during sleep in the clinical setting can accurately identify sleep apnea, providing medically actionable information that can aid clinical decisions.
KeywordsSleep apnea Cardiopulmonary coupling Cyclic variation of heart rate Apnea Hypopnea Index
American Academy of Sleep Medicine
Apnea Hypopnea Index
Cyclic alternating pattern
Continuous positive airway pressure
Cyclic variation of heart rate
Elevated low-frequency broad-band
Elevated low-frequency narrow-band
Heart rate variability
Non-rapid eye movement sleep
Non-cyclic alternating pattern
Prevalence adjusted and bias adjusted kappa
Rapid eye movement
Sleep Apnea Indicator
Sleep Quality Index
Very low frequency coupling
Dr. Thomas Penzel of Philipps-University, Marburg, Germany who provided the data for this analysis, PhysioBank Database https://www.physionet.org/physiobank/database/apnea-ecg/(assessed November 2016).
Neale Lange: Drafting and final approval of the manuscript.
Hugi Hilmisson: Analysis of data, initial drafting, and final approval of the manuscript.
Stephen P Duntley: Final approval of the manuscript.
Compliance with ethical standards
Formal consent was not required for this analysis, as the data had already been de-identified.
Conflict of interest
Lange, Neale, MD:
Assistant Clinical Professor of Medicine, University of Colorado Health Sciences Center, Denver, CO; Partner Critical Care Pulmonary and Sleep Associates.
Dr. Lange declares no conflict of interest.
Hilmisson, Hugi, MA works as a data Analyst, MyCardio LLC. SleepImage is the brand name of MyCardio LLC, a privately held entity. MyCardio LLC is a licensee of the CPC algorithm, a method using ECG recordings during sleep to phenotype sleep and sleep apnea, from the Beth Israel Deaconess Medical Center, Boston, MA, USA.
Stephen P Duntley, MD declares no conflict of interest.
- 2.Young T, Finn L, Peppard PE et al (2008) Sleep disordered breathing and mortality: eighteen-year follow-up of the Wisconsin sleep cohorts. Sleep 31:1071–1078Google Scholar
- 3.Frost & Sullivan. Hidden Health Crisis Costing America Billions. American Academy of Sleep Medicine 2016 http://www.aasmnet.org/Resources/pdf/sleep-apnea-economic-crisis.pdf (assessed March 2017).
- 11.Peker Y, Glantz H, Eulenburg C, Wegscheider K, Herlitz J, Thunström E (2016) Effect of positive airway pressure on cardiovascular outcomes in coronary artery disease patients with nonsleepy obstructive sleep apnea. The RICCADSA randomized controlled trial. Am J Respir Crit Care Med 194(5):613–620. https://doi.org/10.1164/rccm.201601-0088OC Google Scholar
- 19.Sharma S, Chowdhury A, Tang L, Willes L, Glynn B, Quan SF (2016) Hospitalized patients at high risk for obstructive sleep apnea have more rapid response system events and intervention is associated with reduced events. PLoS One 11:e0153790Google Scholar
- 22.Thomas RJ (2016) CardioPulmonary coupling sleep spectrograms. In: Kryger MH, Roth T, Dement WC (eds) Principles and practice of sleep medicine, 6th edn. Elsevier, Inc, Philadelphia, pp 1615–1623Google Scholar
- 23.Thomas RJ, Mietus JE, Peng CK, Guo D, Gozal D, Montgomery-Downs H, Gottlieb DJ, Wang CY, Goldberger AL (2014) Relationship between delta power and the electrocardiogram-derived cardiopulmonary spectrogram. Possible implications for assessing the effectiveness of sleep. Sleep Med 15(1):125–131. https://doi.org/10.1016/j.sleep.2013.10.002 Google Scholar
- 25.Guilleminault C, Connolly S, Winkle R, Melvin K, Tilkian A (1984) Cyclical variation of the heart rate in sleep apnea syndrome: mechanisms, and usefulness of 24h electrocardiography as a screening technique. Lancet 1:126Google Scholar
- 32.Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCH, Mark RG, Mietus JE, Moody GB, Penc CK, Stanley HE (2000) PhysioBank, PhysioToolkit and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215–e220. https://doi.org/10.1161/01CIR10123.e215
- 33.Thomas RJ, Mietus JE, Peng CK et al (2007) Differentiation obstructive from central and complex sleep apnea using an automated electrocardiogram-based method. Sleep 30(12):1756–1759Google Scholar
- 35.Thomas RJ, Weiss MD, Mietus JE et al (2009) Prevalent hypertension and stroke in the Sleep Heart Health Study: association with an ECG-derived spectrographic marker of cardiopulmonary coupling. Sleep 32(7):897–904Google Scholar
- 42.Centers for Medicare and Medicate Services https://www.cms.gov/medicare-coverage-database/details/nca-decision-memo.aspx?NCAId=227&ver=11&NcaName=Sleep+Testing+for+Obstructive+Sleep+Apnea+(OSA)&CoverageSelection=National&KeyWord=sleep+testing&KeyWordLookUp=Title&KeyWordSearchType=And&bc=gAAAACAAEAAA& (accessed Jan 2017)
- 43.StataCorp (2011) Stata statistical software: release 12. StataCorpLP, College StationGoogle Scholar
- 44.American Academy of sleep Medicine Task Force (1999) Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research. Sleep 22(5):667–689Google Scholar
- 46.Penzel T, McNames J, Murray A et al (2002) Systematic comparison of different algorithms for apnoea detection based on electrocardiogram recordings. Med Biol Eng Comput 40(4):402–407Google Scholar
- 49.Mendez MO, Cortbout J, van Huffel S, Matteucci M, Penzel T, Cerutti S, Bianchi AM (2010) Automatic screening of obstructive sleep apnea from the ECG based on empirical mode decomposition and wavelet analysis. Physiol Meas 31:273–289Google Scholar
- 50.Khandoker AH, Palaniswami M, Karmakar CK (2002) Support vector machines for automated recognition of obstructive sleep apnea syndrome from ECG recordings. Med Biol Eng Comput 40:402–407Google Scholar