An Innovative Data-Driven Computational Model to Predict High Blood Pressure Based on AAA++

  • Authors

    • Satyanarayana Nimmala
    • Y Ramadevi
    • B Ashwin Kumar
    2018-06-21
    https://doi.org/10.14419/ijet.v7i3.3.14502
  • Blood Pressure, Blood Cholesterol, Hypertension, Age, Anxiety, Stress Anger, Obesity

  • Every tissue of human body needs energy and oxygen for its livelihood. In order to supply energy and oxygen, the heart pumps the blood around the body. When heart pushes the blood against the walls of arteries, it creates some pressure inside the arteries, called as blood pressure. If this pressure is more than the certain level we treat it as high blood pressure (HBP). Nowadays HBP is a silent killer of many across the globe. So here we proposed a new data-driven computational model to predict HBP. Blood Pressure (BP) may be elevated because of many changes such as physical and emotional. In the proposed model we have considered AAA++ (age, anger level, anxiety level, obesity (+), blood cholesterol (+)), for experimental analysis. Our model initially calculates the correlation coefficient (CC) between each risk factor and class label attribute. Then based on the impact of each risk factor value and CC, it assigns the corresponding weight to it. Then proposed model uses risk factor value and its weight to predict whether person becomes a victim of HBP or not. We have used real-time data set for experimental analysis. It consists of 1000 records, which are collected from Doctor C, a Medical Diagnostic center, Hyderabad, India.

     

  • References

    1. [1] Satyanarayana, N., Ramalinga swamy, CH., Ramadevi, Y. High blood pressure prediction based on AAA using J48 classifier. In

      [2] 2018 IEEE conference on signal processing and communication

      [3] Engineering(SPACES) 2018.

      [4] Mikko Peltokangas., Antti Vehkaoja., J armo Verho. 2017. Age

      [5] Dependence of Arterial Pulse Wave Parameters Extracted from

      [6] Dynamic blood pressure and Blood Volume Pulse Waves. IEEE

      [7] journal of biomedical and Health informatics, 21: 142-149.

      [8] Satyanarayana, N., Ramalinga swamy, CH., Ramadevi, Y. 2014.

      [9] Survey of Classification Techniques in Data mining,

      [10] International Journal Innovative Science, Engineering &

      [11] Technology, 1:268-278.

      1. Alwan. 2011 Global status report on noncommunicable diseases

      [12] 2010, World Health Organization, 2011.

      [13] Julie K.K. Vishram., Anders Borglykke., Anne H. Andreasen.,

      [14] Jorgen Jeppesen., Hans Ibsen. 2012. Impact of Age on the

      [15] Importance of Systolic and Diastolic Blood Pressures for

      [16] Stroke Risk, Hypertension, 60:1117- 1123.

      [17] Raghupathy Anchala., Nanda K. Kannuri ., Hira Pant . 2014.

      [18] Hypertension in India: a systematic review and meta- analysis

      [19] of prevalence, awareness, and control of hypertension, Journal of

      [20] Hypertension, 32:1170-1177.

      [21] World Health Organization [available online at]:

      [22] http://www.who.int/gho/ncd/risk_factors/blood_pressure_prevale-

      [23] _text/en/.

      [24] Ilse L. Mertens., Luc F. Van Gaal. 2000. Overweight, Obesity, and

      [25] Blood Pressure The Effects of Modest Weight Reduction. Obesity

      [26] research, 8:270-278.

      [27] Richard N. Re. 2009. Obesity Related Hypertension. The Ochsner

      [28] Journal, 9:133-136.

      [29] Mohamad Forouzanfar., Hilmi R. Dajani., Mohamad Forouzanfar.,

      [30] hilmi R. Dajani.,Voicu Z. Groza., Miodrag Bolic.,Sreeraman Rajan.

      [31] ,and Izmail Batkin.2015. Oscillometric Blood pressure Estimation:

      [32] Past, Present, and Future. IEEE reviews in biomedical

      [33] Engineering, 8:44-61.

      [34] National Heart, lung and blood institute [available online at]:

      [35] https://www.nhlbi.nih.gov/health/healthtopics/hbc/Causes.

      [36] Meenakshi Kalyan., Shubhangi A. Kanitkar. 2015. Ultrasonogra-

      [37] -phic assessment of abdominal fat and its correlation with blood

      [38] pressure. International Journal of Biomedical and Advance

      [39] Research, 6:259-263.

  • Downloads

  • How to Cite

    Nimmala, S., Ramadevi, Y., & Ashwin Kumar, B. (2018). An Innovative Data-Driven Computational Model to Predict High Blood Pressure Based on AAA++. International Journal of Engineering & Technology, 7(3.3), 114-118. https://doi.org/10.14419/ijet.v7i3.3.14502