K-means Under-Sampling for Hypertension Prediction using NHANES Dataset

doi:10.23940/ijpe.21.08.p9.733740

Abstract

Abstract: Supervised machine learning algorithms are extensively used in various sectors to extract useful patterns from a large dataset. In real-life applications such as in the medical dataset, it is common to have less instances of a positive class compared to negative classes. This leads to the biased performance of machine learning algorithms towards the negative class and misclassifies positive class instances. However, this problem becomes worse with class-overlap. In this paper, a novel framework K-means under-sampling (KUS) is proposed to solve the class imbalance and class overlap problem together to improve the classifier's performance for the diagnosis of hypertension using the NHANES dataset. KUS improves the visibility of minority class instances to the classifiers. The results show that the KUS improved the performance of the classifiers and the results also show that KUS performed better as compared to other resampling algorithms.

Key words: hypertension, class-imbalance, class-overlap, K-means, Silhouette score

Kajal Dwivedi, Ramanathan Lakshmanan, and Rajeshkannan Regunathan. K-means Under-Sampling for Hypertension Prediction using NHANES Dataset [J]. Int J Performability Eng, 2021, 17(8): 733-740.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

1. Sakr S., Elshawi R., Ahmed A., Qureshi W.T., Brawner C., Keteyian S., Blaha M.J., and Al-Mallah, M.H. Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford Exercise Testing (FIT) Project. PLoS One, 13(4), pp.e0195344, 2018.
2. Singh S., Shankar R., andSingh G.P.Prevalence and associated risk factors of hypertension: a cross-sectional study in urban Varanasi.International journal of hypertension, 2017.
3. Vuttipittayamongkol P., Elyan E., andPetrovski A.On the class overlap problem in imbalanced data classification. Knowledge-based systems, 212, pp.106631, 2021.
4. Spelmen, V.S. and Porkodi, R.A review on handling imbalanced data. In2018 International Conference on Current Trends towards Converging Technologies (ICCTCT), IEEE, pp.1-11, 2018.
5. National Health and Nutrition Examination Survey Data (2015-2018). Centers for Disease Control and Prevention. https://wwwn.cdc.gov/nchs/nhanes/
6. López-Martínez, F., Núñez-Valdez, E.R., Crespo, R.G., and García-Díaz, V. An artificial neural network approach for predicting hypertension using NHANES data.Scientific Reports, 10(1), pp.1-14, 2020.
7. National Center for Health Statistics. Data Access—Data User Agreement. https://www.cdc.gov/nchs/data_access/restrictions.htm
8. Lopez-Martinez, F., Schwarcz, A., Núñez-Valdez, E.R., and Garcia-Diaz, V. Machine learning classification analysis for a hypertensive population as a function of several risk factors.Expert Systems with Applications, 110, pp.206-215, 2018.
9. Tengnah M.A.J., Sooklall, R., and Nagowah, S.D. A predictive model for hypertension diagnosis using machine learning techniques. In Telemedicine Technologies, Academic Press, pp.139-152, 2019.
10. Branco P., Torgo L., and Ribeiro R.P.A survey of predictive modeling on imbalanced domains.ACM Computing Surveys (CSUR), 49(2), pp.1-50, 2016.
11. Chawla N.V., Bowyer K.W., Hall L.O., andKegelmeyer W.P.SMOTE: synthetic minority over-sampling technique.Journal of artificial intelligence research, 16, pp.321-357, 2002.
12. Han H., Wang W.Y., andMao B.H.Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In International conference on intelligent computing, Springer, Berlin, Heidelberg, pp.878-887, 2005.
13. Last F., Douzas G., andBacao, F. Oversampling for imbalanced learning based on k-means and smote,2017, arXiv preprint arXiv:1711.00837.
14. Nguyen H.M., Cooper E.W., andKamei K.Borderline over-sampling for imbalanced data classification.International Journal of Knowledge Engineering and Soft Data Paradigms, 3(1), pp.4-21, 2011.
15. Prati R.C., Batista G.E., andMonard M.C.Class imbalances versus class overlapping: an analysis of a learning system behavior. In Mexican international conference on artificial intelligence, Springer, Berlin, Heidelberg, pp.312-321, 2004.
16. Ogbuabor, G. and Ugwoke, F.N.Clustering algorithm for a healthcare dataset using silhouette score value.International Journal of Computer Science & Information Technology (IJCSIT), 10(2), pp.27-37, 2018.

[1]	M. Muzammil Parvez, J. Shanmugam, and V.S. Ghali. Fuzzy C-based Automatic Defect Detection using Barker Coded Thermal Wave Imaging [J]. Int J Performability Eng, 2021, 17(5): 484-490.
[2]	Huaiguang Wu, Pengjie Xie, Ming Cheng, and Hongwei Tao. A Hybrid Model of Predicting Breast Cancer Survivability based on Specific Stages [J]. Int J Performability Eng, 2020, 16(8): 1183-1192.
[3]	Chulei Zhang, Honghua Cui, Yizhang Wang, Tiantian Zhao, and You Zhou. LDKM: An Improved K-Means Algorithm with Linear Fitting Density Peak [J]. Int J Performability Eng, 2020, 16(3): 454-461.
[4]	Lian Yu, Lei Zhang, Cong Tan, Bei Zhao, Chen Zhang, and Lijun Liu. Repeatedly Coding Inter-Packet Delay for Tracking Down Network Attacks [J]. Int J Performability Eng, 2020, 16(2): 265-283.
[5]	Zhiguo Liu and Changqing Ren. Unknown Protocol Data Frame Classification Algorithm based on Improved K-Means [J]. Int J Performability Eng, 2020, 16(11): 1721-1731.
[6]	Qinggang Wu and Xueming Zhai. Remote Sensing Object Detection via an Improved YOLO Network [J]. Int J Performability Eng, 2020, 16(11): 1803-1813.
[7]	Mingzhu Li and Yufeng Deng. A Machine Learning-based Building Operational Pattern Identification [J]. Int J Performability Eng, 2020, 16(11): 1835-1844.
[8]	Wenjie Li. Imbalanced Data Optimization Combining K-Means and SMOTE [J]. Int J Performability Eng, 2019, 15(8): 2173-2181.
[9]	Ming Lei, Bin Wen, Jianhou Gan, and Jun Wang. Clustering Algorithm of Ethnic Cultural Resources based on Spark [J]. Int J Performability Eng, 2019, 15(3): 756-762.
[10]	Yan Zhang, Li Qiao, Xingya Wang, Jingying Cai, and Xuefei Liu. Automatic Software Testing Target Path Selection using K-Means Clustering Algorithm [J]. Int J Performability Eng, 2019, 15(10): 2667-2674.
[11]	Wenqian Shang, Kaixiang Wang, and Junjie Huang. An Improved Tensor Decomposition Model for Recommendation System [J]. Int J Performability Eng, 2018, 14(9): 2116-2126.
[12]	Rui Han, Zhiquan Feng, Changsheng Ai, Wei Xie, and Kang Wang. A Data Glove-based KEM Dynamic Gesture Recognition Algorithm [J]. Int J Performability Eng, 2018, 14(11): 2590-2600.