Automated recognition of hypertension through overnight continuous HRV monitoring

  • Hongbo NiEmail author
  • Sunyoung Cho
  • Jennifer Mankoff
  • Jun Yang
  • Anind k. Dey
Original Research


Hypertension is a common and chronic disease, caused by high blood pressure. Since hypertension often has no warning signs or symptoms, many cases remain undiagnosed. Untreated or sub-optimally controlled hypertension may lead to cardiovascular, cerebrovascular and renal morbidity and mortality, along with dysfunction of the autonomic nervous system. Therefore, it could be quite valuable to predict or provide early warnings about hypertension. Heart rate variability (HRV) analysis has emerged as the most valuable non-invasive test to assess autonomic nervous system function, and has great potential for detecting hypertension. However, HRV indicators may be subtle and present at random, resulting in two challenges: how to support continuous monitoring for hours at a time while being unobtrusive, and how to efficiently analyze the collected data to minimize data collection and user burden. In this paper, we present a machine learning-based approach for detecting hypertension, using a waist belt continuous sensing system that is worn overnight. Using 24 hypertension patients and 24 healthy controls, we demonstrate that our approach can differentiate hypertension patients from healthy controls with 93.33% accuracy. This represents a promising approach for performing hypertension classification in the field, and also we would improve its performance based on a large number of hypertensive subjects monitored by the proposed pervasive sensors.


Human-centered computing Ubiquitous computing Computing methodologies Machine learning Electrocardiogram Pyramid methods Healthcare Heart rate sensing 



We thank the reviewers for the valuable comments and for the time spent towards the improvement of the paper. This work was supported by the China Scholarship Council, and is supported by the Key Project of National Found of Science of China (61332013) and Fundamental Research Grant of NWPU (3102015JSJ0010).


  1. Acharya UR, Joseph KP, Kannathal N, Lim CM, Suri JS (2006) Heart rate variability: a review. Med Biol Eng Comput 44(12):1031–1051. doi: 10.1007/978-3-540-36675-1_5 CrossRefGoogle Scholar
  2. Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 123(1):69–87CrossRefGoogle Scholar
  3. EH Adelson, EP Simoncelli, WT Freeman (2003) Pyramids and multiscale representations. In: Proceedings of ECVPGoogle Scholar
  4. BO Al-Tabbaa, RJ Oweis (2014) QRS detection and heart rate variability analysis: a survey. Biomed Sci Eng 2(1):13–34Google Scholar
  5. Awal A, Mostafa SS, Ahmed M (2011) Performance analysis of savitzky-golay smoothing filter using ECG signal. Int J Comput Inf Technol 1(2):24–29Google Scholar
  6. HJ Baek, JS Kim, KK Kim, KS Park (2008) System for unconstrained ECG measurement on a toilet seat using capacitive coupled electrodes: the efficacy and practicality. In: Proceedings of EMBS, pp 2326–2328Google Scholar
  7. Y-L Boureau, J Ponce, Y Lecun (2010) A theoretical analysis of feature pooling in visual recognition. In: Proceedings of ICML, pp 111–118Google Scholar
  8. Burt PJ, Adelson EH (1983) The Laplacian pyramid as a compact image code. IEEE Trans Commun 31(4):532–540. doi: 10.1515/9781400827268.28 CrossRefGoogle Scholar
  9. H-C Chou, Y-M Wang, H-Y Chang (2015) Design intelligent wheelchair with ECG measurement and wireless transmission function. Technol Health Care 24:S345–S355. doi: 10.3233/THC-151092 CrossRefGoogle Scholar
  10. RR Coifman, Y Meyer, S Quake, MV Wickerhauser (1993) Signal processing and compression with wavelet packets. Wavelets Appl 442:363–379. doi: 10.1007/978-94-011-1028-0_18 CrossRefzbMATHGoogle Scholar
  11. Costa M, Goldberger AL, Peng CK (2002) Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett 89(6):068102. doi: 10.1103/PhysRevLett.89.068102 CrossRefGoogle Scholar
  12. Coyle S, Lau K-T, Moyna N, Gorman DO, Diamond D Fabio Di F, D Costanzo, P Salvo, MG Trivella, DE De Rossi (2010) BIOTEX-Biosensing textiles for personalised healthcare management. IEEE Trans Inf Technol Biomed 14(2):364–370. doi: 10.1109/TITB.2009.2038484 CrossRefGoogle Scholar
  13. Curone D, Secco EL, Tognetti A, Loriga G, Dudnik G, Risatti M, Whyte R, Bonfiglio A, Magenes G (2010) Smart garments for emergency operators: the ProeTEX project. IEEE Trans Inf Technol Biomed 14(3):694–701. doi: 10.1109/TITB.2010.2045003 CrossRefGoogle Scholar
  14. Da He D, Winokur ES, Sodini CG (2015) An Ear-Worn Vital Signs Monitor. IEEE Trans Biomed Eng 62(11):2547–2552CrossRefGoogle Scholar
  15. D Farotto, L Atallah, P van der Heijden, L Grieten (2015) ECG synthesis from separate wearable bipolar electrodes. In: Proceedings of EMBC, pp 5058–5061. doi: 10.1109/EMBC.2015.7319528
  16. Feng XL, Pang M, Beard J (2014) Health system strengthening and hypertension awareness, treatment and control: data from the China Health and Retirement Longitudinal Study. Bull World Health Organ 92(1):29–41. doi: 10.2471/BLT.13.124495 CrossRefGoogle Scholar
  17. Ho Y-L, Lin C, Lin Y-H, Lo M-T (2011) The prognostic value of non-linear analysis of heart rate variability in patients with congestive heart failure at a pilot study of multiscale entropy. PLoS One 6(4):e18699. doi: 10.1371/journal.pone.0018699 CrossRefGoogle Scholar
  18. K Ito, Y Fukuoka, G Cauwenberghs, A Ueno (2013) Noncontact sensing of electrocardiographic potential and body proximity by in-bed conductive fabrics. In: Proceedings of CinC, pp 523–526.Google Scholar
  19. KK Kim, YK Lim, KS Park (2006) Common mode noise cancellation for electrically non-contact ECG measurement system on a chair. In: Proceedings of EMBS, pp 5881–5883Google Scholar
  20. Kwon S, Kang S, Lee Y, Yoo C, Park K (2014) Unobtrusive monitoring of ECG-derived features during daily smartphone use. In: Proceedings of EMBC. IEEE, pp 4964–4967Google Scholar
  21. Lake DE, Richman JS, Griffin MP, Moorman JR (2002) Sample entropy analysis of neonatal heart rate variability. Am J Physiol 238(3):789–797. doi: 10.1152/ajpregu.00069.2002 CrossRefGoogle Scholar
  22. HJ Lee, SH Hwang, HN Yoon, WK Lee, KS Park (2015) Heart rate variability monitoring during sleep based on capacitively coupled textile electrodes on a bed. Sensors 15(5):11295–11311. doi: 10.3390/s150511295 CrossRefGoogle Scholar
  23. S Lemieux, Y Bengio, D Eck (2011) Temporal pooling and multiscale learning for automatic annotation and ranking of music audio. In: Proceedings of ISMIR, pp 729–734Google Scholar
  24. Lewicke A, Sazonov E, Corwin MJ, Neuman M, Schuckers S (2008) and CHIME Study Group. Sleep versus wake classification from heart rate variability using computational intelligence: consideration of rejection in classification models. IEEE Trans Biomed Eng 55(1):108–118. doi: 10.1109/TBME.2007.900558 CrossRefGoogle Scholar
  25. Li W, Gu H, Teo KK, Bo J, Wang Y, Yang J, Wang X, Zhang H, Sun Y, Jia X (2016) and others. Hypertension prevalence, awareness, treatment, and control in 115 rural and urban communities involving 47000 people from China. J Hypertens 34(1):39–46CrossRefGoogle Scholar
  26. Lim YG, Kim KK, K. S (2007) Park.ECG recording on a bed during sleep without direct skin-contact. Biomed Eng IEEE Trans 54(4):718–725CrossRefGoogle Scholar
  27. X Long, P Fonseca, R Haakma, RM Aarts, J Foussier (2012) Time-frequency analysis of heart rate variability for sleep and wake classification. In: Proceedings of BIBE, pp 85–90. doi: 10.1109/BIBE.2012.6399712
  28. D Lowe (2004) Distinctive image features from scale-invariant keypoints. IJCV 60(4):91–110. doi: 10.1023/B:VISI.0000029664.99615.94 MathSciNetCrossRefGoogle Scholar
  29. Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693. doi: 10.1515/9781400827268.494 CrossRefzbMATHGoogle Scholar
  30. G Manis, A Alexandridi, S Nikolopoulos, K Davos (2005) The effect of white noise and false peak Detection on HRV Analysis. In: Proceedings of ICINCO, pp 161–166Google Scholar
  31. Melillo P, lzzo R, Orrico A, Scala P, Attanasio M, Mirra M, Luca ND, Pecchia L (2015) Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis. PLoS One 10(3):e0118504. doi: 10.1371/journal.pone.0118504 CrossRefGoogle Scholar
  32. Merritt CR, Nagle HT, Grant E (2009) Fabric-based active electrode design and fabrication for health monitoring clothing. IEEE Trans Inf Technol Biomed 13(2):274–280. doi: 10.1109/TITB.2009.2012408 CrossRefGoogle Scholar
  33. Natarajan N, Balakrishnan AK, kkirapandian K (2014) A study on analysis of heart rate variability in hypertensive individuals. Int J Biomedical Adv Res 5(2):109–111. doi: 10.7439/ijbar.v5i2.659 CrossRefGoogle Scholar
  34. J Nikolic-Popovic, R Goubran (2013) Impact of motion artifacts on Heart Rate Variability measurements and classification performance. In: MeMeA, pp 156–159. doi: 10.1109/MeMeA.2013.6549726
  35. J Nikolic-Popovic, R Goubran (2014) Towards increased usability of noisy ECG signals in HRV-based classifiers. In: MeMeA, pp 1–4. Doi: 10.1109/MeMeA.2014.6860125
  36. Pincus SM (1991) Approximate entropy as a measure of system complexity. PNAS 88(6):2297–2301. doi: 10.1073/pnas.88.6.2297 MathSciNetCrossRefzbMATHGoogle Scholar
  37. MG Poddar, V Kumar, Y Paul Sharma (2014) Heart rate variability based classification of normal and hypertension cases by linear-nonlinear method. Def Sci J 64(6):542–548CrossRefGoogle Scholar
  38. Puente ET (2010) Heart rate variability analysis during normal and hypertensive pregnancy. Doctoral dissertation, Faculty of Pharmacy, University of PortoGoogle Scholar
  39. Ramirez-Villegas JF, Lam-Espinosa E, Ramirez-Moreno DF, Calvo-Echeverry PC, Agredo-Rodriguez W (2011) Heart rate variability dynamics for the prognosis of cardiovascular risk. PLoS one 6(2):e17060CrossRefGoogle Scholar
  40. Rosamond W, Flegal K, Furie K, Go A, Greenlund K, Haase N, Hailpern SM, Ho M, Howard V, Kissela B (2008) American Heart Association Statistics Committee, and Stroke Statistics Subcommittee. Heart disease and stroke statistics-2008 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. Circulation 117(4):e25–e146Google Scholar
  41. J Rubin, H Eldardiry, R Abreu, S Ahern, H Du, A Pattekar, DG Bobrow (2015) Towards a mobile and wearable system for predicting panic attacks. In: Proceedings of UbiComp, pp 529–533. doi: 10.1145/2750858.2805834
  42. Savitzky A, MJE Golay (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36(8):1627–1639. doi: 10.1021/ac60214a047 CrossRefGoogle Scholar
  43. Schroeder EB, Liao D, Chambless LE, Prineas RJ, Evans GW, Heiss G (2003) Hypertension, blood pressure, and heart rate variability the atherosclerosis risk. In communities (ARIC) study. Hypertension 42(6):1106–1111CrossRefGoogle Scholar
  44. P Shi, H-L Yu (2013) Heart rate variability in essential hypertension patients with different stages by nonlinear analysis: a preliminary study. Adv Biomed Eng Res 1(3):33–39Google Scholar
  45. M Signorini, M Ferrario, M Marchetti, A Marseglia (2006) Nonlinear analysis of heart rate variability signal for the characterization of cardiac heart failure patients. In Proceedings of EMBS, pp 3431–3434. doi: 10.1109/IEMBS.2006.259744
  46. Singh JP, Larson MG, Tsuji H, Evans JC, O’Donnell CJ, Levy D (1998) Reduced heart rate variability and new-onset hypertension- Insights into pathogenesis of hypertension: the Framingham heart study. J Hum Hypertens 32(2):293–297. doi: 10.1161/01.HYP.32.2.293 CrossRefGoogle Scholar
  47. Subasi A (2005) Epileptic seizure detection using dynamic wavelet network. Expert Syst Appl 29(2):343–355. doi: 10.1016/j.eswa.2005.04.007 CrossRefGoogle Scholar
  48. F-T Sun, C Kuo, H-T Cheng, S Buthpitiya, P Collins, M Griss (2012) Activity-aware mental stress detection using physiological sensors. Mob Comput Appl Serv 76:211–230. doi: 10.1007/978-3-642-29336-8_12 CrossRefGoogle Scholar
  49. Terathongkum S, Pickler RH (2004) Relationships among heart rate variability, hypertension, and relaxation techniques. J Vasc Nurs 22(3):78–82. doi: 10.1016/j.jvn.2004.06.003 CrossRefGoogle Scholar
  50. Virtanen R, Jula A, Kuusela T, Helenius H, L-M Voipio-Pulkki (2003)Reduced heart rate variability in hypertension: associations with lifestyle factors and plasma renin activity. J Hum Hypertens 17(3):171–179. doi: 10.1038/sj.jhh.1001529 CrossRefGoogle Scholar
  51. Wall HK, Hannan JA, Wright JS (2014) Patients with undiagnosed hypertension: hiding in plain sight. JAMA 312(19):1973. doi: 10.1001/jama.2014.15388 CrossRefGoogle Scholar
  52. World Health Organization (WHO and others) (2015) A global brief on hypertension: silent killer, global public health crisis. WorldGoogle Scholar
  53. K-F Wu, Y-T Zhang (2008) Contactless and continuous monitoring of heart electric activities through clothes on a sleeping bed. In: Proceedings of ITAB, pp 282–285. doi: 10.1109/ITAB.2008.4570586

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Hongbo Ni
    • 1
    Email author
  • Sunyoung Cho
    • 2
  • Jennifer Mankoff
    • 2
  • Jun Yang
    • 3
  • Anind k. Dey
    • 2
  1. 1.School of Computer ScienceNorthwestern Polytechnical UniversityXi’anChina
  2. 2.Carnegie Mellon UniversityPittsburghUSA
  3. 3.Beijing Aviation Medical InstituteBeijingChina

Personalised recommendations