Abstract
According to a study conducted by the World Health Organization, cardiovascular diseases (CVDs) are the first cause of death globally. About 17.9 million people die each year from CVDs, which represents an estimated 31% of all deaths worldwide, and more than 75% of the deaths occur in low and middle-income countries. Therefore, it is very important to develop new methodologies that could be used in the future for diagnosing CVDs. They should be accessible both in terms of price and technologies, so that they can be available for low and middle-income countries as well. Because of the recent technological progress, Artificial Intelligence (AI) algorithms along with big data produce very accurate results even in the healthcare field, and we believe they can help in solving this problem.
The study presented in this paper is based on using a cheap and powerful Internet of Things (IoT) programmable PSoC6 device to acquire blood pressure data from people and the data is then processed using the LabVIEW virtual instrumentation environment using a machine learning model developed in the Python programming language. For choosing the most appropriate machine learning model for our case, we compared the most widely used algorithms and selected the one that had the best performance indicators. The model was trained using a data set of 70.000 records of patient data and predicts 5-year risk of developing CVDs very accurately.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
World Health Organization website, [Online] at https://www.who.int/health-topics/cardiovascular-diseases/, last accessed 2020/12/12.
References
Lucci S, Kopec D (2016) Artificial intelligence in the 21st century: a living introduction, second edition. In: Mercury learning and information. ISBN: 978-1-942270-00-3
Theus AS, et al (2019) Biomaterial approaches for cardiovascular tissue engineering. Emer Mater
Sharma D, Ferguson M, Kamp TJ, Zhao F (2019) Constructing biomimetic cardiac tissues: a review of scaffold materials for engineering cardiac patches. Emerg Mater
Krittanawong C, Virk H, Bangalore S et al (2020) Machine learning prediction in cardiovascular diseases: a meta-analysis. Sci Rep 10:16057
PSoC 6 CY8CKIT-062 Pioneer Kit, Cypress/Infineon – DigiKey. https://www.digikey.com/en/product-highlight/c/cypress/psoc-6-cy8ckit-062-pioneer-kit. Accessed 17 Dec 2020
Alpaydin E (2020) Introduction to machine learning, 4th edn. MIT Press Ltd., ISBN 9780262043793
Tae K, Roh Y, Hun Oh Y, Kim H, Whang S (2019) Data cleaning for accurate, fair, and robust models: a big data - ai integration approach. arXiv:1904.10761v1
Xu Y, Goodacre R (2018) On splitting training and validation set: a comparative study of cross-validation, bootstrap systematic sampling for estimating the generalization performance of supervised learning. J Anal Test 2:249–262
Langley P (2011) The changing science of machine learning. Mach Learn J 82: 275–279
NI VISA User Manual. https://www.ni.com/pdf/manuals/370423a.pdf. Accessed 17 Dec 2020
Hassan AU, Khan MS, Shah MA (2018) Comparison of machine learning algorithms in data classification. In: 24th international conference on automation and computing (ICAC), newcastle upon Tyne, United Kingdom, pp 1–6
Powers D (2010) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness & correlation. J Mach Learn Technol 2:37–63
Naraei P, Abhari A, Sadeghian A (2016) Application of multilayer perceptron neural networks and support vector machines in classification of healthcare data. In: 2016 future technologies conference (FTC), San Francisco, CA, pp 848–852
Omary Z, Mtenzi F (2010) Machine learning approach to identifying the dataset threshold for the performance estimators in supervised learning. Int J Inf (IJI) 3(3)
Acknowledgements
We would like to express our great appreciation to National Instruments for providing us free LabVIEW license, thus facilitating this study and making it possible. Special thanks goes to the Cypress/Infineon company as well, for giving us several PSoC kits free of charge. Their generosity and collaboration were greatly appreciated.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Modran, H.A., Ursuțiu, D., Samoilă, C., Chamunorwa, T. (2022). Artificial Intelligence System for Predicting Cardiovascular Diseases Using IoT Devices and Virtual Instrumentation. In: Auer, M.E., Bhimavaram, K.R., Yue, XG. (eds) Online Engineering and Society 4.0. REV 2021. Lecture Notes in Networks and Systems, vol 298. Springer, Cham. https://doi.org/10.1007/978-3-030-82529-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-82529-4_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82528-7
Online ISBN: 978-3-030-82529-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)