Wearable Real-Time Heart Attack Detection and Warning System to Reduce Road Accidents

Muhammad E H Chowdhury, Khawla Alzoubi, Amith Khandakar, Ridab Khallifa, Rayaan Abouhasera, Sirine Koubaa, Rashid Ahmed, Md Anwarul Hasan, Muhammad E H Chowdhury, Khawla Alzoubi, Amith Khandakar, Ridab Khallifa, Rayaan Abouhasera, Sirine Koubaa, Rashid Ahmed, Md Anwarul Hasan

Abstract

Heart attack is one of the leading causes of human death worldwide. Every year, about 610,000 people die of heart attack in the United States alone-that is one in every four deaths-but there are well understood early symptoms of heart attack that could be used to greatly help in saving many lives and minimizing damages by detecting and reporting at an early stage. On the other hand, every year, about 2.35 million people get injured or disabled from road accidents. Unexpectedly, many of these fatal accidents happen due to the heart attack of drivers that leads to the loss of control of the vehicle. The current work proposes the development of a wearable system for real-time detection and warning of heart attacks in drivers, which could be enormously helpful in reducing road accidents. The system consists of two subsystems that communicate wirelessly using Bluetooth technology, namely, a wearable sensor subsystem and an intelligent heart attack detection and warning subsystem. The sensor subsystem records the electrical activity of the heart from the chest area to produce electrocardiogram (ECG) trace and send that to the other portable decision-making subsystem where the symptoms of heart attack are detected. We evaluated the performance of dry electrodes and different electrode configurations and measured overall power consumption of the system. Linear classification and several machine algorithms were trained and tested for real-time application. It was observed that the linear classification algorithm was not able to detect heart attack in noisy data, whereas the support vector machine (SVM) algorithm with polynomial kernel with extended time-frequency features using extended modified B-distribution (EMBD) showed highest accuracy and was able to detect 97.4% and 96.3% of ST-elevation myocardial infarction (STEMI) and non-ST-elevation MI (NSTEMI), respectively. The proposed system can therefore help in reducing the loss of lives from the growing number of road accidents all over the world.

Keywords: heart attack; machine learning algorithm; portable device; real time system; support vector machine.

Conflict of interest statement

The authors certify that they have NO affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.

Figures

Figure 1
Figure 1
Comparison of the ST-segment variations in a normal subject (A) and in MI patients with ST-elevation myocardial infarction (STEMI) (B) and non-ST-elevation MI (NSTEMI) (C).
Figure 2
Figure 2
Overall system block diagram.
Figure 3
Figure 3
Exterior (A) and interior view (B) of the three-dimensional (3D) model of the electrocardiograms (ECG) amplifier and (C) the ECG amplifier with the chest best and (D) dry electrodes.
Figure 4
Figure 4
Intelligent decision-making subsystem hardware (A) with the 3D printed model (B) and the packet format used for communication (C).
Figure 5
Figure 5
Different ECG lead configurations tested: (A) Lead I; (B) Chest Lead II; (C) Chest Straight Lead.
Figure 6
Figure 6
Set-up of power consumption study for wearable subsystem (A) and decision-making subsystem (B).
Figure 7
Figure 7
Blocks of the linear classification (A) and machine learning (ML) (B) based MI detection algorithm.
Figure 8
Figure 8
Normal ECG waveform with the waves and intervals. Note: user-defined HI line represents the isoelectric (ISO) line and JK line represents the ST segments.
Figure 9
Figure 9
Overall representation of the signal before and after baseline wander correction: (A) Original signal; (B) baseline corrected ECG signal.
Figure 10
Figure 10
ECG trace averaged over traces and its power spectral density for (A,D) normal, (B,E) ST-elevation, and (C,F) T-wave inversion, respectively.
Figure 11
Figure 11
Performance of dry electrodes in comparison to wet electrodes (A) and different lead configurations (B) at different vehicle speeds.
Figure 12
Figure 12
ECG data collected wirelessly from (A) subject 1 and (B) from subject 2.
Figure 13
Figure 13
Current consumption in different operational scenarios for the wearable subsystem (A) and the RPI3 subsystem (B).
Figure 14
Figure 14
ECG parameters detection for normal subject (A) and effect of the motion artifact in the linear classification algorithm (B).

References

    1. Peden M., Scurfield R., Sleet D., Mohan D., Hyder A.A., Jarawan E., Mathers C., editors. World Report on Road Traffic Injury Prevention. World Health Organization; Geneva, Switzerland: 2004.
    1. Lowman What Medical Conditions Can Lead To Auto Accidents? [(accessed on 8 June 2019)]; Available online: .
    1. Halinen M.O., Jaussi A. Fatal road accidents caused by sudden death of the driver in Finland and Vaud, Switzerland. Eur. Heart J. 1994;15:888–894. doi: 10.1093/oxfordjournals.eurheartj.a060606.
    1. Ostrom M., Eriksson A. Natural death while driving. J. Forensic Sci. 1987;32:988–998. doi: 10.1520/JFS12410J.
    1. McFarland R.A., Moore R.C. Accidents and accident prevention. In: Rystand D.A., Creger W.P., editors. Annual Review of Medicine Vol. 13. Annual Reviews, Inc.; Palo Alto, CA, USA: 1962.
    1. Lindsay V., Baldock M. Medical conditions as a contributing factor in crash causation; Proceedings of the 2008 Australasian Road Safety Research, Policing and Education Conference; Adelaide, Australia. 9–12 November 2008; pp. 610–628.
    1. Hitosugi M., Hasegawa M., Yamauchi S., Morita S., Furukawa S. Main factors causing health-related vehicle collisions and incidents in Japanese taxi drivers. Rom. J. Leg. Med. 2015;23:83–86. doi: 10.4323/rjlm.2015.83.
    1. Murray C.J., Lopez A.D. Global mortality, disability, and the contribution of risk factors: Global Burden of Disease Study. Lancet. 1997;349:1436–1442. doi: 10.1016/S0140-6736(96)07495-8.
    1. Gibson A.L., Wagner D., Heyward V. Advanced Fitness Assessment and Exercise Prescription, 8E. Human Kinetics; Champaign, IL, USA: 2018.
    1. Bhopal R.S. Epidemic of Cardiovascular Disease and Diabetes: Explaining the Phenomenon in South Asians Worldwide. Oxford University Press; Oxford, UK: 2019.
    1. Mechanic O.J., Shamai A.G. Acute Myocardial Infarction. StatPearls Publishing; Tampa/St. Petersburg, FL, USA: 2019. StatPearls [Internet]
    1. Patel S., Chauhan Y. Heart attack detection and medical attention using motion sensing device-kinect. Int. J. Sci. Res. Publ. 2014;4:1–4.
    1. Mittleman M.A., Malcolm M., Geoffrey H.T., Jane B.S., Robert J.G., James E.M. Triggering of acute myocardial infarction by heavy physical exertion--protection against triggering by regular exertion. N. Engl. J. Med. 1993;329:1677–1683. doi: 10.1056/NEJM199312023292301.
    1. Inan O.T., Kovacs G.T. An two-electrode transimpedance biosignal amplifier with active current feedback stabilization. IEEE Trans. Biomed. Circuits Syst. 2010;4:93–100. doi: 10.1109/TBCAS.2009.2032096.
    1. Dobrev D. Two-electrode non-differential biopotential amplifier. Med. Biol. Eng. Comput. 2002;40:546–549. doi: 10.1007/BF02345453.
    1. Nemati E., Deen M.J., Mondal T. A wireless wearable ECG sensor for long-term applications. IEEE Commun. Mag. 2012;50:36–43. doi: 10.1109/MCOM.2012.6122530.
    1. Singh R.K., Sarkar A., Anoop C. A health monitoring system using multiple non-contact ECG sensors for automotive drivers; Proceedings of the 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I2MTC); Taipei, Taiwan. 23–26 May 2016; pp. 1–6.
    1. Richard E., Chan A.D. Design of a gel-less two-electrode ECG monitor; Proceedings of the 2016 IEEE International Workshop on Medical Measurements and Applications (MeMeA); Ottawa, ON, Canada. 30 April–1 May 2010; pp. 92–96.
    1. Valchinov E., Pallikarakis N. A wearable wireless ECG sensor: A design with a minimal number of parts. In: Bamidis P.D., Pallikarakis N., editors. Proceedings of the XII Mediterranean Conference on Medical and Biological Engineering and Computing 2010; Chalkidiki, Greece. 27–30 May 2010; Berlin/Heidelberg, Germany: Springer; 2010. pp. 288–291.
    1. Yap J., Noh Y.H., Jeong D.U. The deployment of novel techniques for mobile ECG monitoring. Int. J. Smart Home. 2012;6:1–14.
    1. Noh Y.H., Jeong D.U. Implementation of fuzzy-rule based activity classification and optimized adaptive filter-set for wearable ECG recording. Int. J. Multimed. Ubiquitous Eng. 2012;7:59–72.
    1. Reichlin T., Hochholzer W., Bassetti S., Steuer S., Stelzig C., Hartwiger S. Early diagnosis of myocardial infarction with sensitive cardiac troponin assays. N. Engl. J. Med. 2009;361:858–867. doi: 10.1056/NEJMoa0900428.
    1. Sopic D., Aminifar A., Aminifar A., Atienza D. Real-time classification technique for early detection and prevention of myocardial infarction on wearable devices; Proceedings of the 2017 IEEE Biomedical Circuits and Systems Conference (BioCAS); Turin, Italy. 19–21 October 2017; pp. 1–4.
    1. Rad M.Z., Ghuchani S.R., Bahaadinbeigy K., Khalilzadeh M.M. Real time recognition of heart attack in a smart phone. Acta Inform. Med. 2015;23:151. doi: 10.5455/aim.2015.23.151-154.
    1. Blumenthal R., Braunstein J., Connolly H., Epstein A., Gersh B.J., Wittels E.H. Cardiovascular Advisory Panel Guidelines for the Medical Examination of Commercial Motor Vehicle Drivers. US Department of Transportation Federal Motor Carrier Safety Administration; Washington, DC, USA: 2002.
    1. Antecol D.H., Roberts W.C. Sudden death behind the wheel from natural disease in drivers of four-wheeled motorized vehicles. Am. J. Card. 1990;66:1329–1335. doi: 10.1016/0002-9149(90)91163-Z.
    1. West I., Nielsen G.L., Gilmore A.E. Natural death at the wheel. JAMA. 1968;205:68–73. doi: 10.1001/jama.1968.03140310024005.
    1. Myerburg R.J., Davis J.H. The medical ecology of public safety. 1. Sudden death due to coronary heart disease. Am. Heart J. 1964;68:586–595. doi: 10.1016/0002-8703(64)90266-2.
    1. Hanna R. The contribution of medical conditions to passenger vehicle crashes. Annu. Emerg. Med. 2010;55:563–564.
    1. National Transportation Safety Board (NTSB) Safety Study: Fatigue, Alcohol, Other Drugs, and Medical Factors in Fatal-to-the-Driver Heavy Truck Crashes. US Department of Transportation; Washington, DC, USA: 1990.
    1. Krueger G.P., Belzer M., Alvarez A., Knipling R., Husting E., Brewster R., Siebert J. Health and wellness of commercial drivers. Domain Truck. Bus Saf. Res. 2007;117:58–91.
    1. Goldberger A.L., Amaral L.A.N., Glass L., Hausdorff J.M., Ivanov P.C., Mark R.G., Mietus J.E., Moody G.B., Peng C.K., Stanley H.E. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation. 2015;101:e215–e220. doi: 10.1161/01.CIR.101.23.e215.
    1. BioRadio. [(accessed on 27 February 2017)]; Available online:
    1. ArduPi Library. [(accessed on 27 February 2017)]; Available online: .
    1. Pan J., Tompkins W.J. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 1985;32:230–236. doi: 10.1109/TBME.1985.325532.
    1. Cichocki A., Amari S.I. Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. Volume 1 John Wiley & Sons; Hoboken, NJ, USA: 2002.
    1. Clifford G.D., Azuaje F., Mcsharry P. ECG statistics, noise, artifacts, and missing data. Adv. Methods Tools ECG Data Anal. 2006;6:18.
    1. 1-D Digital Filter—MATLAB Filter. [(accessed on 22 December 2016)]; Available online: .
    1. Staszewski W.J., Robertson A.N. Time–frequency and time–scale analyses for structural health monitoring. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2006;365:449–477. doi: 10.1098/rsta.2006.1936.
    1. Chang C.C., Lin C.J. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2011;2:27. doi: 10.1145/1961189.1961199.

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi