DOI QR코드

DOI QR Code

Development of Big Data-based Cardiovascular Disease Prediction Analysis Algorithm

  • Kyung-A KIM (Department of Medical Artificial Intelligence, Eulji University) ;
  • Dong-Hun HAN (Department of Medical Artificial Intelligence, Eulji University) ;
  • Myung-Ae CHUNG (Department of BigData Medical Convergence, Eulji University)
  • Received : 2023.07.31
  • Accepted : 2023.09.05
  • Published : 2023.09.30

Abstract

Recently, the rapid development of artificial intelligence technology, many studies are being conducted to predict the risk of heart disease in order to lower the mortality rate of cardiovascular diseases worldwide. This study presents exercise or dietary improvement contents in the form of a software app or web to patients with cardiovascular disease, and cardiovascular disease through digital devices such as mobile phones and PCs. LR, LDA, SVM, XGBoost for the purpose of developing "Life style Improvement Contents (Digital Therapy)" for cardiovascular disease care to help with management or treatment We compared and analyzed cardiovascular disease prediction models using machine learning algorithms. Research Results XGBoost. The algorithm model showed the best predictive model performance with overall accuracy of 80% before and after. Overall, accuracy was 80.0%, F1 Score was 0.77~0.79, and ROC-AUC was 80%~84%, resulting in predictive model performance. Therefore, it was found that the algorithm used in this study can be used as a reference model necessary to verify the validity and accuracy of cardiovascular disease prediction. A cardiovascular disease prediction analysis algorithm that can enter accurate biometric data collected in future clinical trials, add lifestyle management (exercise, eating habits, etc.) elements, and verify the effect and efficacy on cardiovascular-related bio-signals and disease risk. development, ultimately suggesting that it is possible to develop lifestyle improvement contents (Digital Therapy).

Keywords

Acknowledgement

This paper was supported by IITP (Institute of information & Communications Technology Planning & Evaluation(www.iitp.kr), Korea) [Project Number: 2022-0-00317]. This paper was supported by the research grant of the KODISA scholarship foundation in 2023.

References

  1. Beak, S. K., Park, J. H., Kang, S. H., & Park, H. J. (2018). A study on the development of severity-adjusted mortality prediction model for discharged patient with acute stroke using machine learning. Journal of Korea Academia-Industrial cooperation Society, 19(11), 126-136. https://doi.org/10.5762/KAIS.2018.19.11.126
  2. Bosma, H., Peter, R., Siegrist, J., & Marmot, M. (1998). Two alternative job stress models and the risk of coronary heart disease. American Journal of Public Health, 88(1), 68-74. https://doi.org/10.2105/AJPH.88.1.68
  3. Choi, B. G., Rha, S. W., Kim, S. W., Kang, J. H., Park, J. Y., & Noh, Y. K. (2019). Machine Learning for the Prediction of New-Onset Diabetes Mellitus during 5-Year Follow-up in Non-Diabetic Patients with Cardiovascular Risk. Yonsei Med J, 60(2), 191-199. http://doi.org/10.3349/ymj.2019.60.2.191
  4. Cho, S. O., (2019). Change Pattern of Heart Age in Korean Population Using Heart Age Predictor of Framingham Heart Study. Journal of the Korea Academia-Industrial cooperation Society, 20(8), 331-343. https://doi.org/10.5762/KAIS.2019.20.8.331
  5. Hong, S. M., Byeon, H. W., Kim, J. S., & Mun, S. H. (2015). Development of Risk Prediction Model for Cardiovascular Disease Among Community-Dwelling Elderly. Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, 5(1), 37-46. http://doi.org/10.14257/AJMAHS.2015.02.02
  6. Hyun, J. K. (2022). Prediction of Diabetic Neuropathy Using Machine Learning Techniques. J Korean Diabetes, 23(4), 238-244. https://doi.org/10.4093/jkd.2022.23.4.238
  7. Jee, S. H., Song, J. W., Cho, H. L., Kim, S. Y., Jang, Y. S., & Kim, J. H. (2004). Development of Individualized Health Risk Appraisal Model of Ischemic Heart Disease Risk in Korea, Journal of Lipid and Atherosclerosis, 14(2), 153-168.
  8. Kang, S. A., Kim, S. H., & Ryu, M. H. (2022). Analysis of Hypertension Risk Factors by Life Cycle Based on Machine Learning. Journal of the Korea Industrial Information Systems Research, 27(5), 73-82. https://doi.org/10.9723/jksiis.2022.27.5.073
  9. Kim, C. J., & Kim, J. S. (2018). A Study of Heart Disease Prediction Using Multilayer Perceptron based on Deep Learning. Journal of Knowledge Information Technology and Systems(JKITS), 14(4), 411-419 https://doi.org/10.34163/jkits.2018.13.4.001
  10. Kim, S. H., & Cho, S. H. (2023). A Comparative Study of Predictive Factors for Hypertension using Logistic Regression Analysis and Decision Tree Analysis. Phys Ther Rehabil Sci, 12(2), 80-91. https://doi.org/10.14474/ptrs.2023.12.2.80
  11. Kipp, W. J., Soto, J. T., Glicksberg, B. S., Shameer, K., Miotto, R. Ali, M., & Joe. T. Dudley. (2018). Artificial Intelligence in Cardiology. Journal of the American College of Cardiology(JACC), 71(23), 2668-2679. https://doi.org/10.1016/j.jacc.2018.03.521
  12. Lee, Y. N., Lee, K. H., & Cho, W. S. (2021). Cost-Sensitive Learning for Cardio-Cerebrovascular Disease Risk Prediction. The Korea Journal of BigData, 6(2), 161-168. https://doi.org/10.36498/kbigdt.2021.6.2.161
  13. Mohd Faizal, A.S., Thevarajah, T. M., Khor, S. M., & Chang, S. W. (2021). A review of risk prediction models in cardiovascular disease, conventional approach vs. artificial intelligent approach. Computer methods and Programs in Biomedicine, 207, 1-11. https://doi.org/10.1016/j.cmpb.2021.106190
  14. Motwani, M., Dey D., Berman., Germano G., Achenbach S., & Al-Mallah M.H., Andreini, D., Budoff, M. J., et al. (2017). Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. European Heart Journal, 38, 500-507. http://doi.org/10.1093/eurheartj/ehw188
  15. Noh, M. J., & Park, S. C. (2020). A Prediction Model of Asthma Diseases in Teenagers Using Artificial Intelligence Models. J. Inf. Technol. Appl. Manag., 27(6), 171-180. http://doi.org/10.21219/jitam.2020.27.6.171
  16. Oh, T. S., Kim, D. K., Won, C. W., Kim, S. Y., Jeong, E. J., Yang, J. S., Yu, J. H., Kim, B. S., & Lee, J. H. (2022). A Machine-Learning-Based Risk Factor Analysis for Hypertension; Korea National Health and Nutrition Examination Survey 20016-2019. Korean j Fam Practice, 12(3),173-178. http://doi.org/10.21215/kifp.2022.12.3.17.3
  17. Park, D. W. (2023). Analysis of the Application Target and Scope of Artificial Intelligence Algorithm for the Development of 4th and 5th Industrial Revolution Technologies. The Journal of Korean Institute of Communications and Information Sciences, 48(1), 65-73. http://doi.org/10.7840/kics.2023.48.1.65
  18. Park, P. W., Kim, M. K., Lim, H. S., Yoon, D. Y., & Lee, S. W. (2014). A Comparative Study of Machine Learning Algorithms for Diagnosis of Ischemic Heart Disease. Journal of KIISE, 45(4), 376-389. http://doi.org/10.5026/JOK.2018.45.4.376
  19. Urrea, B., Misra S., Plante, T. B., Kelli, H. M., Misra, S., Blaha. M. J., Martin S. S. (2015). Mobile Health Initiatives to Improve Outcomes in Primary Prevention of Cardiovascular Disease. Curr Treat Options Cardio Med, 17, 59. https://doi.org/10.1007/s11936-015-0417-7
  20. Venkatesh, B. A., Yang, X., Wu, C. O., Kiu, K., & Hundley, G., et.al. (2017). Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circ Res., 121(9), 1092-1101. https://doi.org/10.1161/CIRCRESAHA.117.311312