Advertisement

Automated Cardiac Health Screening Using Smartphone and Wearable Sensors Through Anomaly Analytics

  • Arijit UkilEmail author
  • Soma Bandyopadhyay
Chapter
Part of the EAI/Springer Innovations in Communication and Computing book series (EAISICC)

Abstract

With the advent and rapid deployment of Internet of Things (IoT), artificial intelligence (AI), powerful smartphones, and wearable sensor devices (e.g., smartwatch), we are entering into the era of automated, remote, on-demand mobile healthcare services. According to the WHO, cardiovascular disease is the modern-day disease. However, prognosis rate of cardiac disease patients can be potentially made high with early detection and diagnosis. In this book chapter, we describe automated cardiac health monitoring system using smartphone and wearable sensors. The main contribution of such mobile applications and systems is to form a connected universe with biomedical sensors, patients, physicians, clinics, hospitals, and other medical service providers and to exploit robust analytics to infer and actuate the appropriate information and formative actions. The powerful anomaly analytics exploit AI, signal processing, and deep learning mechanisms that enable predictive decision-making and facilitate preventive cardiac health screening. The main emphasis is to develop and deploy smart, computationally efficient, rather than human-in-loop, user-friendly, data-driven cardiac healthcare solutions, where patients and healthcare service providers are seamlessly connected. In this book chapter, we discuss about important cardiovascular signals, namely, electrocardiogram (ECG), photoplethysmogram (PPG), and heart sound or phonocardiogram (PCG), and describe their role in the process of developing a mobile-based cardiac care solution. These cardiac marker signals constitute an intelligent and robust feature space for detection of different cardiac abnormalities and diseases like coronary artery disease, cardiac arrhythmia, and others. These sensor signals can be captured by affordable wearable sensors. In order to develop such mobile applications and systems, we need to address different challenges like noisy signal removal and data privacy protection along with providing robust analytics engine.

References

  1. 1.
    American Heart Association, Heart Disease and Stroke Statistics – 2013. [Online]. Available: http://www.heart.org/HEARTORG/General/Cardiac-Arrest-Statistics_UCM_448311_Article.jsp. Accessed 20 Feb 2018
  2. 2.
    Clifford G, Clifton D (2012) Annual review: wireless technology in disease management and medicine. Ann Review Med 63:479–492CrossRefGoogle Scholar
  3. 3.
    Alivecor. [Online]. Available: https://www.alivecor.com/. Accessed 20 Feb 2018
  4. 4.
    KARDIABAND, Your personal EKG on your wrist: [Online] Accessed on 20 February, 2018. Available: https://www.alivecor.com/kardiaband/
  5. 5.
    Grimaldi D, Kurylyak Y, Lamonaca F, Nastro A (2011) Photoplethysmography detection by smartphone’s video camera. Proceedings of the 6th IEEE international conference on intelligent data acquisition and advanced computing systems, Prague, 2011, pp 488–491Google Scholar
  6. 6.
    Boloursaz Mashhadi M, Asadi E, Eskandari M, Kiani S, Marvasti F (2016) Heart rate tracking using wrist-type photoplethysmographic (PPG) Signals during physical exercise with simultaneous accelerometry. IEEE Signal Process Lett 23(2):227–231CrossRefGoogle Scholar
  7. 7.
    Zhang Z, Zhouyue P, Benyuan L (2015) TROIKA: a general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Trans Biomed Eng 62(2):522–531CrossRefGoogle Scholar
  8. 8.
    Shelley K, Shelley S (2001) Pulse oximeter waveform: photoelectric plethysmography. In: Lake C, Hines R, Blitt C (eds) Clinical monitoring. W.B. Saunders Company, pp 420–721Google Scholar
  9. 9.
  10. 10.
    Wang J, Li Z (2007) Research on a practical electrocardiogram segmentation model. 2007 1st International Conference on Bioinformatics and Biomedical Engineering, Wuhan, 2007, pp. 652–655Google Scholar
  11. 11.
    Wang J, Li Z (2007) Research on a practical electrocardiogram segmentation model. Intern Conf BioinformaBiomed Eng:652–655Google Scholar
  12. 12.
    Amiri AM, Armano G, Rahmani AM, Mankodiya K (2015) PhonoSys: mobile phonocardiography diagnostic system for newborns. EAI international conference on wireless mobile communication and healthcareGoogle Scholar
  13. 13.
    Puri C, Singh R, Bandyopadhyay S, Ukil A, Mukherjee A (2017) Analysis of phonocardiogram signals through proactive denoising using novel self-discriminant learner. 2017 39th annual international conference of the IEEE engineering in medicine and biology society (EMBC), Jeju Island, South Korea, 2017, pp 2753–2756Google Scholar
  14. 14.
    Lu S, Zhao H, Ju K, Shin K, Lee M, Shelley K, Chon K (2008) Can photoplethysmography variability serve as an alternative approach to obtain heart rate variability information? J Clin Monit Comput 22:23–29CrossRefGoogle Scholar
  15. 15.
    Shahrbabaki SS, Ahmed B, Penzel T, Cvetkovic D (2016) Photoplethysmography derivatives and pulse transit time in overnight blood pressure monitoring. IEEE EMBCGoogle Scholar
  16. 16.
    Clifford GD et al (2017) Recent advances in heart sound analysis. Physiol Meas 38:E10–E25CrossRefGoogle Scholar
  17. 17.
    Ukil A, Bandyopadhyay S, Puri C, Singh R, Pal A (2018) Effective noise removal and unified model of hybrid feature space optimization for automated cardiac anomaly detection using phonocardiogram signals. ICASSPGoogle Scholar
  18. 18.
    Puri C, Ukil A, Bandyopadhyay S, Singh R, Pal A, Mukherjee A, Mukherjee D (2016) Classification of normal and abnormal heart sound recordings through robust feature selection. IEEE Comput Cardiol 43:1125–1128Google Scholar
  19. 19.
    Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of maxdependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238CrossRefGoogle Scholar
  20. 20.
    Bandyopadhyay S, Ukil A, Singh R, Puri C, Pal A, Murthy CA (2016). 3S: sensing sensor signal: demo abstract. SensysGoogle Scholar
  21. 21.
    Ukil A, Bandyopadhyay S, Pal A (2015) Privacy for IoT: involuntary privacy enablement for smart energy systems. IEEE Int Confer Commun (ICC), London 2015:536–541.  https://doi.org/10.1109/ICC.2015.7248377 CrossRefGoogle Scholar
  22. 22.
    Bandyopadhyay S, Ukil A, Puri C, Singh R, Pal A, Mandana KM, Murthy CA (2016) An unsupervised learning for robust cardiac feature derivation from PPG signals. IEEE Inter Conf Eng Med Biol Soc (EMBC) 2016:740–743Google Scholar
  23. 23.
    Davies L, Gather U (1993) The identification of multiple outliers. J Am Stat Assoc 88:782–792MathSciNetCrossRefGoogle Scholar
  24. 24.
    Chuah FC, Fu F (2007) ECG anomaly detection via time series analysis. ACM ISPA, pp 123–135Google Scholar
  25. 25.
    Nunes D et al (2015) A low-complex multi-channel methodology for noise detection in phonocardiogram signals. Conf Proc IEEE Eng Med Biol Soc 2015:5936–5939Google Scholar
  26. 26.
    Ukil A, Bandyopadhyay S, Puri C, Pal A (2016) Heart-trend: an affordable heart condition monitoring system exploiting morphological pattern. IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 6260–6264Google Scholar
  27. 27.
    Lin W, Zhang H, Zhang Y (2013) Investigation on cardiovascular risk prediction using physiological parameters. Comput Math Methods Med 2013:1–21Google Scholar
  28. 28.
    Papadaniil CD, Hadjileontiadis LJ (2014) Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features. IEEE J Biomed Health Inform 18:1138–1152CrossRefGoogle Scholar
  29. 29.
    Seiffert C, Khoshgoftaar TM, Van Hulse J (2008) RUSBoost: improving classification performance when training data is skewed. ICPR, Washington, DCGoogle Scholar
  30. 30.
    Chawla N et al (2003) SMOTEBoost: improving prediction of the minority class in boosting. European Confe Princ Data Min Knowl Discov 2838:107–119Google Scholar
  31. 31.
    Yang CY, Yang JS, Wang JJ (2009) Margin calibration in svm class imbalanced learning. Neurocomputing 73(1–3):397–411CrossRefGoogle Scholar
  32. 32.
    Batuwita R, Palade V (2010) Fsvm-cil: fuzzy support vector machines for class imbalance learning. IEEE Trans Fuzzy Syst 18(3):558–571CrossRefGoogle Scholar
  33. 33.
    A. Ukil, S. Bandyopadhyay, C. Puri, R. Singh, A. Pal, K.M. Mandana, "CardioFit: Affordable Cardiac Healthcare Analytics for Clinical Utility Enhancement," Ehealth 360, LNICST, 2016Google Scholar
  34. 34.
    Schmidt SE, Holst-Hansen C, Hansen J, Toft E, Struijk JJ (2015) Acoustic features for the identification of coronary artery disease. IEEE Trans Biomed Eng 62:2611–2619CrossRefGoogle Scholar
  35. 35.
    Ukil A, Bandyopadhyay S, Pal A (2014) Iot-privacy: to be private or not to be private. IEEE conf Commun Workshops (INFOCOM WKSHPS)Google Scholar
  36. 36.
    Ukil A, Bandyopadhyay S, Pal A (2015) Privacy for IoT: involuntary privacy enablement for smart energy systems. IEEE Inter conf commun: London, 536–541 doi:10.1109/ICC.2015.7248377Google Scholar
  37. 37.
    Ukil A, Bandyopadhyay S, Pal A (2014) Sensitivity inspector: Detecting privacy in smart energy applications. IEEE Symposium on Computers and Communication (ISCC)Google Scholar
  38. 38.
    Ukil A (2011). Secure trust management in distributed computing systems. IEEE international symposium on electronic design, test and application (DELTA), pp 116–121Google Scholar
  39. 39.
    Ukil A, Jana D, De Sarkar A (2013) A security framework in cloud computing infrastructure. Int J Netw Secur Appl (IJNSA) 5(5)CrossRefGoogle Scholar
  40. 40.
    Ukil A, Sen J, Koilakonda S (2011) Embedded security for internet of things.In: 2nd National Conference on emerging trends and applications in computer science, Shillong, pp. 1–6Google Scholar
  41. 41.
    Sen J, Ukil A (2010) A secure routing protocol for wireless sensor networks. Computational science and its applications, pp 277–290Google Scholar
  42. 42.
    Kotz D, Gunter CA, Kumar S, Weiner JP (2016) Privacy and security in mobile health: a research agenda. Computer 49:22–30CrossRefGoogle Scholar
  43. 43.
    Cardiio Touchless Camera Pulse Sensor. [Online] Available: https://itunes.apple.com/us/app/cardiio-heart-rate-monitor/id542891434?mt=8. Accessed 20 Feb 2018
  44. 44.
    Instant Heart Rate: HR Monitor, Pulse Tracker & Stress Test, Azumio Inc.: [Online] Available: https://itunes.apple.com/us/app/instant-heart-rate-hr-monitor/id409625068?mt=8. Accessed 20 Feb 2018
  45. 45.
    Shyamkumar P, Rai P, Oh S, Ramasamy M, Harbaugh RE, Varadan V (2014) Wearable wireless cardiovascular monitoring using textile-based nanosensor and nanomaterial systems. Electronics 3:504–520CrossRefGoogle Scholar
  46. 46.
    Kakria P, Tripathi NK, Kitipawang P (2015) A real-time health monitoring system for remote cardiac patients using smartphone and wearable sensors. Int J Telemed Appl 3(3):504–520Google Scholar
  47. 47.
    Zheng YL et al (2014) Unobtrusive sensing and wearable devices for health informatics. IEEE Trans Biomed Eng 61(5):1538–1554CrossRefGoogle Scholar
  48. 48.
    Kim C et al (2016) Ballistocardiogram: mechanism and potential for unobtrusive cardiovascular health monitoring. Nature Scientific Reports, Article number:31297Google Scholar
  49. 49.
    Giovangrandi L, Inan OT, Wiard RM, Etemadi M, Kovacs GTA (2011) Ballistocardiography – a method worth revisiting. 33rd annual international conference of the IEEE engineering in medicine and biology society, pp 4279–4282Google Scholar
  50. 50.
    Chu L (2016) Medicine X 2016 sessions of interest to the Pharma and Life Sciences Industries. Stanford Med. https://medicinex.stanford.edu/2016-schedule/, https://medicinex.stanford.edu/2016-accepted-presentations/
  51. 51.
    A. Ukil (2010). Privacy preserving data aggregation in wireless sensor networks. pp 435–440. IEEE international conference on wireless and mobile communications (ICWMC)Google Scholar
  52. 52.
    Shamir M, Eidelman LA, Floman Y, Kaplan L, Pi-zov R (1999) Pulse oximetry plethysmographic waveform during changes in blood volume. Br J Anaesth 82:178–181CrossRefGoogle Scholar
  53. 53.
    Brown G et al (2012) Conditional likelihood maximisation: a unifying framework for information theoretic feature selection. J Mach Learn Res 13:27–66MathSciNetzbMATHGoogle Scholar
  54. 54.
    Qardio.: [Online], Accessed on 20 February, Available: https://www.getqardio.com/
  55. 55.
    Ukil A, Sen J (2010) Secure multiparty privacy preserving data aggregation by modular arithmetic. International conference on parallel distributed and grid computing (PDGC), pp 344–349Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.TCS Research and Innovation, Embedded systems and RoboticsKolkataIndia

Personalised recommendations