ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Performance analysis and comparison of various machine learning algorithms for early stroke prediction

  • Vinay Padimi (Oracle Solution Services India Private Limited) ;
  • Venkata Sravan Telu (School of Computer Science and Information Systems, Northwest Missouri State University) ;
  • Devarani Devi Ningombam (Department of Computer Science and Engineering, National Institute of Technology (NIT) Patna)
  • Received : 2022.07.11
  • Accepted : 2022.09.26
  • Published : 2023.12.10
Download PDF
⟨ Previous Next ⟩

Abstract

Stroke is the leading cause of permanent disability in adults, and it can cause permanent brain damage. According to the World Health Organization, 795 000 Americans experience a new or recurrent stroke each year. Early detection of medical disorders, for example, strokes, can minimize the disabling effects. Thus, in this paper, we consider various risk factors that contribute to the occurrence of stoke and machine learning algorithms, for example, the decision tree, random forest, and naive Bayes algorithms, on patient characteristics survey data to achieve high prediction accuracy. We also consider the semisupervised self-training technique to predict the risk of stroke. We then consider the near-miss undersampling technique, which can select only instances in larger classes with the smaller class instances. Experimental results demonstrate that the proposed method obtains an accuracy of approximately 98.83% at low cost, which is significantly higher and more reliable compared with the compared techniques.

Keywords

References

  1. Cerebrovascular disease-classifications, symptoms, diagnosis and treatments. https://www.aans.org/
  2. Centers for Disease Control and Prevention, USA, Prevalence and most common causes of disability among adults--United States, 2005, MMWR Morb. Mortal Wkly. Rep. 58 (2009), no. 16, 421-426.
  3. A. Z. Sherzai and M. S. V. Elkind, Advances in stroke prevention, Ann. N. Y. Acad. Sci. 1338 (2015), no. 1, 1-15. https://doi.org/10.1111/nyas.12723
  4. S. Mayor, Warning signs often occur hours or days before a stroke, BMJ 330 (2005), no. 7491, 556. https://doi.org/10.1136/bmj.330.7491.556-b
  5. A. K. Boehme, C. Esenwa, and M. S. V. Elkind, Stroke risk factors, genetics, and prevention, Circ. Res. 120 (2017), no. 3, 472-495. https://doi.org/10.1161/CIRCRESAHA.116.308398
  6. G. Briganti and O. Le Moine, Artificial intelligence in medicine: today and tomorrow, Front Med. (Lausanne) 7 (2020), 27. https://doi.org/10.3389/fmed.2020.00027
  7. L. Ding, C. Liu, Z. Li, and Y. Wang, Incorporating artificial intelligence into stroke care and research, Stroke 51 (2020), no. 12, e351-e354. https://doi.org/10.1161/STROKEAHA.120.031295
  8. Patient characteristics survey (PCS): 2019\State of New York. https://data.ny.gov/Human-Services/Patient-Characteristics-Survey-PCS-2019/urn3-ezfe
  9. M. U. Emon, M. S. Keya, T. I. Meghla, Md. M. Rahman, M. S. A. Mamun and M. S. Kaiser, Performance analysis of machine learning approaches in stroke prediction, (2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India), Nov. 2020, pp. 1464-1469. https://doi.org/10.1109/ICECA49313.2020.9297525
  10. T. Tazin, M. N. Alam, N. N. Dola, M. S. Bari, S. Bourouis, and M. Monirujjaman Khan, Stroke disease detection and prediction using robust learning approaches, J. Healthc. Eng. 2021 (2021), e7633381. https://doi.org/10.1155/2021/7633381
  11. T. Kansadub, S. Thammaboosadee, S. Kiattisin and C. Jalayondeja, Stroke risk prediction model based on demographic data, in 2015 8th biomedical engineering international conference (BMEiCON), Pattaya, Thailand, Nov. 2015, pp. 1-3. https://doi.org/10.1109/BMEiCON.2015.7399556
  12. D. Guo, X. Zhuang, and T. Rabczuk, A deep collocation method for the bending analysis of Kirchhoff plate, Comput. Mater. Continua. 59 (2019), no. 2, 433-456. https://doi.org/10.32604/cmc.2019.06660
  13. C. Anitescu, E. Atroshchenko, N. Alajlan, and T. Rabczuk, Artificial neural network methods for the solution of second order boundary value problems, Comput. Mater. Continua. 59 (2019), no. 1, 345-359. https://doi.org/10.32604/cmc.2019.06641
  14. D. D. Ningombam, B. Yoo, H. W. Kim, H. J. Song, and S. Yi, CuMARL: Curiosity-based learning in multiagent reinforcement learning, IEEE Access 10 (2022), 87254-87265. https://doi.org/10.1109/ACCESS.2022.3198981
  15. B. Yoo, D. D. Ningombam, S. Yi, H. W. Kim, E. Chung, R. Han, and H. J. Song, A novel and efficient influence-seeking exploration in deep multiagent reinforcement learning, IEEE Access 10 (2022), 47741-47753. https://doi.org/10.1109/ACCESS.2022.3171053
  16. C. S. Nwosu, S. Dev, P. Bhardwaj, B. Veeravalli and D. John, Predicting stroke from electronic health records, (2019 41st Annual international Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany), July 2019, pp. 5704-5707. https://doi.org/10.1109/EMBC.2019.8857234
  17. S. Dev, H. Wang, C. S. Nwosu, N. Jain, B. Veeravalli, and D. John, A predictive analytics approach for stroke prediction using machine learning and neural networks, Healthc. Anal. 2 (2022), 100032. https://doi.org/10.1016/j.health.2022.100032
  18. Y. Wu and Y. Fang, Stroke prediction with machine learning methods among older Chinese, Int. J. Environ. Res. Public Health 17 (2020), no. 6, 1828. https://doi.org/10.3390/ijerph17061828
  19. A. Onan, Consensus clustering-based undersampling approach to imbalanced learning, Sci. Prog. 2019 (2019), 1-14.
  20. A. Onan, Mining opinions from instructor evaluation reviews: a deep learning approach, Comput. Appl. Eng. Edu. 28 (2020), 117-138. https://doi.org/10.1002/cae.22179
  21. A. Onan, Two-stage topic extraction model for bibliometric data analysis based on word embeddings and clustering, IEEE Access 7 (2019), 145614-145633.
  22. S. Ray, K. Alshouiliy, A. Roy, A. AlGhamdi and D. P. Agrawal, Chi-squared based feature selection for stroke prediction using AzureML, (2020 Intermountain Engineering, Technology and Computing (IETC), Orem, UT, USA), Oct. 2020, pp. 1-6. https://doi.org/10.1109/IETC47856.2020.9249117
  23. J. Heo, J. G. Yoon, H. Park, Y. D. Kim, H. S. Nam, and J. H. Heo, Machine learning-based model for prediction of outcomes in acute stroke, Stroke 50 (2019), no. 5, 1263-1265. https://doi.org/10.1161/STROKEAHA.118.024293
  24. T. F. Luscher, What is a normal blood pressure? Eur. Heart J. 39 (2018), no. 24, 2233-2240. https://doi.org/10.1093/eurheartj/ehy330
  25. R.-N. Horodinschi, A. M. A. Stanescu, O. G. Bratu, A. Pantea Stoian, D. G. Radavoi, and C. C. Diaconu, Treatment with statins in elderly patients, Medicina 55 (2019), no. 11, 721. https://doi.org/10.3390/medicina55110721
  26. O. Y. Bang, J.-W. Chung, M. J. Lee, W.-K. Seo, G.-M. Kim, and M.-J. Ahn, Cancer-related stroke: an emerging subtype of ischemic stroke with unique pathomechanisms, J. Stroke 22 (2020), no. 1, 1-10. https://doi.org/10.5853/jos.2019.02278
  27. G. J. Hankey, Smoking and risk of stroke, J. Cardiovasc. Risk 6 (1999), no. 4, 207-211. https://doi.org/10.1177/204748739900600403
  28. L. R. Kurukulasuriya, G. Govindarajan, and J. Sowers, Stroke prevention in diabetes and obesity, Expert Rev. Cardiovasc. Ther. 4 (2006), no. 4, 487-502. https://doi.org/10.1586/14779072.4.4.487
  29. A. Ergul, W. Li, M. M. Elgebaly, A. Bruno, and S. C. Fagan, Hyperglycemia, diabetes and stroke: focus on the cerebrovasculature, Vascul. Pharmacol. 51 (2009), no. 1, 44-49. https://doi.org/10.1016/j.vph.2009.02.004
  30. M. L. McHugh, The chi-square test of independence, Biochem. Med. 23 (2013), no. 2, 143-149. https://doi.org/10.11613/BM.2013.018