Methods Inf Med 2007; 46(02): 216-221
DOI: 10.1055/s-0038-1625410
Original Article
Schattauer GmbH

Detection of Sleep Apnea Episodes from Multi-lead ECGs Considering Different Physiological Influences

H. Dickhaus
1   Department of Medical Informatics, University of Heidelberg, Heidelberg, Germany
,
C. Maier
2   Department of Medical Informatics, Heilbronn University, Heilbronn, Germany
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
11. Januar 2018 (online)

Summary

Objectives : This article deals with recognition of sleep apnea, using solely information available from multilead ECGs.

Methods : Characteristic variations in heart rhythm and amplitude of the ECG are compared with respect to their diagnostic accuracy by means of an ROC analysis that is performed on a local similarity index. In 38 8-lead ECGs, each minute is classified with respect to occurrence of apnea events and the result is validated against expert annotations derived from synchronized polysomnographic recordings. Moreover, the results are compared to those obtained from the well known Physionet apnea-ECG database.

Results : Whereas the effect of amplitude modulation yields consistent results on both data sets (ROC-area 89.0% vs. 88.3%), a remarkable loss in performance is observed for the frequently applied heart rhythm (89.8% vs. 77.9%). Examples illustrating the reasons for this difference are given and discussed. With respect to aggregation of multi-lead information, two methods (PCA vs. averaging) are compared. The results indicate that averaging performs better (89.3%) than the adaptively estimated PCA (87.2) even when applied to a reduced set of leads.

Conclusions : It is concluded that sleep apnea recognition from heart rhythm should always be complemented by analysis of the amplitude variations of the ECG.

 
  • References

  • 1. Guilleminault C, Tilkian A, Dement WC. Cyclical variation of the heart rate in sleep apnoea syndrome. Mechanisms and usefulness of 24 hr electrocardiography as a screening technique. Lancet 1984; 126-131.
  • 2. Penzel T, McNames J, de Chazal P, Raymond B, Murray A, Moody G. Systematic comparison of different algorithms for apnoe detection based on electrocardiogram recordings. Med Biol Eng Comput 2002; 40: 402-407.
  • 3. Maier C, Dickhaus H, Bauch M, Penzel T. Comparison of heart rhythm and morphological ECG features in recognition of sleep apnea from the ECG. Proc Computers in Cardiology 2003. Piscataway: IEEE Press; 2003: 311-314.
  • 4. Stein PK, Duntley SP, Domitrovic PP, Nishith P, Carney RM. A simple method to identify sleep apnea using holter recordings. J Cardiovasc Electrophysiol 2003; 14: 467-73.
  • 5. M.Gillis AM. Ambulatory electrocardiographic monitoring for sleep apnea: is it really that simple?. J Cardiovasc Electrophysiol 2003; 14: 474-475.
  • 6. Moody GB, Mark RG, Zoccola A, Mantero S. Derivation of respiratory signals from multi-lead ECGs. Proc Computers in Cardiology 1985. Washington DC: IEEE Computer Society Press; 1985: 113-116.
  • 7. Weng J, Zhang Y, Hwang WS. Candid covariance free incremental principal component analysis. IEEE Trans PAMI 2003; 25 (08) 1034-1040.
  • 8. Zywietz CW, Von Einem V, Widiger B, Joseph G. ECG Analysis for Sleep Apnea Detection. Methods Inf Med 2004; 43 (01) 56-59.