Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

Ensemble Model for the Prediction of Hypertension using KNN and SVM Algorithms

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2021
Saadatu Ali Jijji, Asabe Ahmadu Sandra, Malgwi Yusuf Musa

Saadatu Ali Jijji, Asabe Ahmadu Sandra and Malgwi Yusuf Musa. Ensemble Model for the Prediction of Hypertension using KNN and SVM Algorithms. International Journal of Computer Applications 183(43):27-32, December 2021. BibTeX

	author = {Saadatu Ali Jijji and Asabe Ahmadu Sandra and Malgwi Yusuf Musa},
	title = {Ensemble Model for the Prediction of Hypertension using KNN and SVM Algorithms},
	journal = {International Journal of Computer Applications},
	issue_date = {December 2021},
	volume = {183},
	number = {43},
	month = {Dec},
	year = {2021},
	issn = {0975-8887},
	pages = {27-32},
	numpages = {6},
	url = {},
	doi = {10.5120/ijca2021921837},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Hypertension also known as high blood pressure is a dangerous illness because it can lead to strokes, heart disease, heart failure, kidney problem and many more ailment, but when hypertension is detected early it can be prevented or controlled. Thus an intelligent and accurate system is in need for early prediction. Data mining applied to medical field provide innovative results and when two data mining techniques are combined a better performance and more accurate model was developed. A model for the prediction of hypertension in patient using Hybrid data mining technique was developed using hyper-parameter tuning and ensemble method. The model was based on hypertension data set collected from Federal teaching hospital and specialist hospital Gombe state Nigeria. The dataset was further preprocessed and standardized by scaling, fixing missing values and fixing imbalanced data using SMOTE. Grid search technique was using for hyper-parameter tuning. KNN, SVM and Naïve Bayes was used in the model before applying the ensemble technique on KNN and SVM which Gradient Boosting has the accuracy of 0.9985.


  1. Adam, F. (2019). Everything you need to know about hypertension. MedicalNewsToday. Retrieved july 22, 2019 from
  2. Lackland, D, T & Weber, M, A. (2015). Global burden of cardiovascular disease and stroke: hypertension at the core. The Canadian Journal of cardiology, 31(5):569 – 571. DOI:10.1016/j.cjca.2015.01.009
  3. Bharati, M., R. (2010). Data mining techniques and application. Indian Journal of computer science and Engineering, 1(4) pp 301-305. Retrieved October 16 from
  4. Han, J., & kamber , J., P. (2011) Data Mining Concepts and Techniques. New York : Morgan Kaufmann Publishers.
  5. Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From Theory to Algorithms. New York: Cambridge university press.
  6. Manimekalai, K. (2016).Prediction of heart disease using data mining techniques. International journal of innovative research in computer and communication, 4(2), 2320 – 9801. DOI: 10.15680/IJIRCCE.2016.0402013
  7. Azian, A, A., Zulkarnay, Z., & Nur, F, M. (2011). Design and Dwevelopment of fuzzy expert system for Diagnosis of Hypertension. Paper Presented at second International Conference on Intelligent system, Modeling and simulation. DOI 10.1109/ISMS.2011.27
  8. dowu, P, A. (2017). Predictive model for the classification of hypertension Risk using Decision Tree Algorithm. American Journal of Mathematical and Computer Modeling, 2 (2) : 48 – 59. DOI : 10.11648/j.ajmcm.20170202.12
  9. Abrishami, Z., & Tabatabaee, H. (2015 October). Design of a Fuzzy expert system and a multi layer Neural Network system for Diagnosis of hypertension. Bulletin of Environment, pharmacology and life science, 4 (11), 138-145.
  10. Daniel, L., Farhana, Z., David, B., & Ken, M. (2016). Using machine learning to predict hypertension from clinical data set. [Electronic version]. DOI: 10.1109/SSCI.2016.7849886
  11. Afeni, B. O., Aruleba, T. I., & Oloyeda, A. I (2017). Hypertension Prediction system using Naïve bayes classifier. Journal of Advances in mathematics and computer science, 24(2) 1-11
  12. Dingkun, L., Hyun, W.P., Erdenebileg, B., Lkhagvadorj, M., Ibrahim, M., Meijing, L. & Keun, H.R. (2018). Application of a mobile Health – care system for Hypertension Based on Big Data Platforms. Journal of Sensors. Arcticle ID 3265281, 13. Doi:10.1155/2018/3265281
  13. Chang, C., Wang, C. & Jiang, B. (2011). Using Data mining techniques for multi – disease prediction modeling of hypertension and hyperlipidemia by common risk factors. Expert systems with Applications 38(2011), 5507 – 5513.
  14. Muhammad, F. I., Ganjar, A., Muhammad, S. & Jongtae, R. (2018). Hybrid Prediction model for type 2 diabetes and hypertension using DBSCAN – Based outlier Detection, synthetic minority over sample technique (SMOTE), and Random forest. Applied science, 8. Doi:10.3390/app8081325
  15. Sakr S, Elshawi R, Ahmed A, Qureshi W T, Brawner C, Keteyian S,Blaha M J., & Al mallah M H. (2018) Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project. PLoS ONE 13(4): e0195344.
  16. IComputer Modeling, 2 (2) : 48 – 59. DOI : 10.11648/j.ajmcm.20170202.12
  17. Huang , J., Tsai, Y., Wu, P., Lien, Y., Chien, C., Kuo, C., Hung, J., Chen, S & Kuo, C. (2020). Predictive Modelling of blod pressure during hemodialysis: a comparison of linear model,random forest,support vector,regression, XGBoost, LASSO regression and ensemble method. Computer methods and programs in biomedicine 195(0ctober 2020), 105536. Retrievied September 9 2020 from
  18. Alkaabi,L,A., Ahmed, L, S., Al attiyah, M, F & Abdel-Rahman, M, E.(2020).Predicting hypertension using machine learning: Findings from Qatar Biobank study. PLOS ONE 15 (10):e0240370.DOI: Retrieved September 9 2021 from
  19. López-Martínez, F., Núñez-Valdez, E.R., Crespo, R.G. & Giarcia-Diaz, V.(2020) An artificial neural network approach for predicting hypertension using NHANES data. Sci Rep 10, 10620. DOI : retrieved on September 9 2021 from


Hypertension, Data mining, Ensemble technique, Hyper-parameter tuning, SMOTE, Accuracy