Skip to main content

Advertisement

SpringerLink
Log in

Machine Learning for Hypertension Prediction: a Systematic Review

  • Guidelines/Clinical Trials/Meta-Analysis (WJ Kostis, Section Editor)
  • Published:
Current Hypertension Reports Aims and scope Submit manuscript

Abstract

Purpose of Review

To provide an overview of the literature regarding the use of machine learning algorithms to predict hypertension. A systematic review was performed to select recent articles on the subject.

Recent Findings

The screening of the articles was conducted using a machine learning algorithm (ASReview). A total of 21 articles published between January 2018 and May 2021 were identified and compared according to variable selection, train-test split, data balancing, outcome definition, final algorithm, and performance metrics. Overall, the articles achieved an area under the ROC curve (AUROC) between 0.766 and 1.00. The algorithms most frequently identified as having the best performance were support vector machines (SVM), extreme gradient boosting (XGBoost), and random forest.

Summary

Machine learning algorithms are a promising tool to improve preventive clinical decisions and targeted public health policies for hypertension. However, technical factors such as outcome definition, availability of the final code, predictive performance, explainability, and data leakage need to be consistently and critically evaluated.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

Papers of particular interest, published recently, have been highlighted as: • Of importance •• Of major importance

  1. World Health Organization. Hypertension. In: Overview. 2021. https://www.who.int/health-topics/hypertension#tab=tab_1. (Accessed 9 Jun 2021).

  2. Carretero AO, Oparil S. Clinical cardiology: new frontiers. Circulation. 2000;101:329–35.

    Article  CAS  Google Scholar 

  3. Messerli FH, Williams B, Ritz E. Essential hypertension. Lancet. 2007;370:591–603.

    Article  CAS  Google Scholar 

  4. Manosroi W, Williams GH. Genetics of human primary hypertension: focus on hormonal mechanisms. Endocr Rev. 2018. https://doi.org/10.1210/er.2018-00071.

    Article  PubMed Central  Google Scholar 

  5. Onusko E. Diagnosing secondary hypertension. Am Fam Physician. 2003;67:67–74.

    PubMed  Google Scholar 

  6. Charles L, Triscott J, Dobbs B. AFP-secondary HTN – discovering the underlying cause. Am Fam Physician. 2017;96:453–61.

    PubMed  Google Scholar 

  7. Cai L, Zhu Y. The challenges of data quality and data quality assessment in the big data era. Data Sci J. 2015;14:1–10.

    Article  CAS  Google Scholar 

  8. de Moraes Batista AF, Chiavegatto Filho AD. Machine learning aplicado à Saúde. Workshop: Machine Learning. 19° Simpósio Bras. Comput Apl à Saúde. Soc Bras Comput. 2019.

  9. van de Schoot R, de Bruin J, Schram R, et al. An open source machine learning framework for efficient and transparent systematic reviews. Nat Mach Intell. 2021;3:125–33.

    Article  Google Scholar 

  10. Kumar V. Feature selection: a literature review. Smart Comput Rev. 2014. https://doi.org/10.6029/smartcr.2014.03.007.

    Article  Google Scholar 

  11. Kwong EWY, Wu H, Pang GKH. A prediction model of blood pressure for telemedicine. Health Informatics J. 2018;24:227–44.

    Article  Google Scholar 

  12. •• Sakr S, Elshawi R, Ahmed A, Qureshi WT, Brawner C, Keteyian S, et al. Using machine learning on cardiorespiratory fitness data for predicting hypertension: the Henry Ford exercise testing (FIT) Project. PLoS One. 2018. https://doi.org/10.1371/journal.pone.0195344. The model was constructed using the Henry Ford Health System dataset containing 23,095 samples. After applying an information gain-based feature selection, the best model was obtained by the random forest algorithm, achieving an AUROC of 0.880 in the test set (20% of the sample).

  13. Ma Y, Yang B, Kang G, Hou B. Hypertension warning model based on random forest and distance metrics. In 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2018;2274–2279.

  14. Heo BM, Ryu KH. Prediction of prehypertenison and hypertension based on anthropometry, blood parameters, and spirometry. Int J Environ Res Public Health. 2018. https://doi.org/10.3390/ijerph15112571.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Nour M, Polat K. Automatic classification of hypertension types based on personal features by machine learning algorithms. Math Probl Eng. 2020. https://doi.org/10.1155/2020/2742781.

    Article  Google Scholar 

  16. •• Ye C, Fu T, Hao S, et al. Prediction of incident hypertension within the next year: prospective study using statewide electronic health records and machine learning J Med Internet Res. 2018;20(e22). The authors developed an analysis from the Maine Health Information Exchange Network, an American dataset with eighty features. Two cohort studies were used, one for training the model and the other for its validation. XGBoost achieved the best performance, with an AUROC of 0.917.

  17. •• Ijaz MF, Alfian G, Syafrudin M, Rhee J. Hybrid prediction model for type 2 diabetes and hypertension using DBSCAN-based outlier detection, synthetic minority over sampling technique (SMOTE), and random forest. Appl Sci. 2018. https://doi.org/10.3390/app8081325. This article applied machine learning to predict type 2 diabetes and hypertension while using DBSCAN for outlier detection, SMOTE for balancing the data, and random forest as the predictive algorithm. They used a dataset from a private university in Brazil for the hypertension model with 155 samples. The model achieved an accuracy of 0.76, but the AUROC result was not presented.

  18. •• Nusinovici S, Tham YC, Chak Yan MY, Wei Ting DS, Li J, Sabanayagam C, et al. Logistic regression was as good as machine learning for predicting major chronic diseases. J Clin Epidemiol. 2020;122:56–69. This article used a dataset from Singapore to predict hypertension. Clinical and sociodemographic features were included and selected by the z-statistic value from logistic regression. The best performance was achieved with the support vector machine algorithm (AUROC = 0.780).

  19. •• Pei Z, Liu J, Liu M, Zhou W, Yan P, Wen S, et al. Risk-predicting model for incident of essential hypertension based on environmental and genetic factors with support vector machine. Interdiscip Sci Comput Life Sci. 2018;10:126–130. This study analyzed a Chinese dataset with 1200 observations. The authors developed a prediction model based on environmental and genetic factors, and the best algorithm was the support vector machine with an AUROC of 0.886.

  20. Kanegae H, Suzuki K, Fukatani K, Ito T, Harada N, Kario K. Highly precise risk prediction model for new-onset hypertension using artificial intelligence techniques. J Clin Hypertens. 2020;22:445–50.

    Article  Google Scholar 

  21. Soh DCK, Ng EYK, Jahmunah V, Oh SL, San TR, Acharya UR. A computational intelligence tool for the detection of hypertension using empirical mode decomposition. Comput Biol Med. 2020. https://doi.org/10.1016/j.compbiomed.2020.103630.

    Article  PubMed  Google Scholar 

  22. Xu F, Zhu J, Sun N, et al. Development and validation of prediction models for hypertension risks in rural Chinese populations. J Glob Health. 2019. https://doi.org/10.7189/jogh.09.020601.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Li C, Sun D, Liu J, Li M, Zhang B, Liu Y, et al. A prediction model of essential hypertension based on genetic and environmental risk factors in northern Han Chinese. Int J Med Sci. 2019;16:793–9.

    Article  CAS  Google Scholar 

  24. Zhang L, Yuan M, An Z, et al. Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: a cross-sectional study of chronic diseases in central China. PLoS ONE. 2020;15:1–11.

    CAS  Google Scholar 

  25. López-Martínez F, Núñez-Valdez ER, Crespo RG, García-Díaz V. An artificial neural network approach for predicting hypertension using NHANES data. Sci Rep. 2020;10:10620.

    Article  Google Scholar 

  26. Ambika M, Raghuraman G, SaiRamesh L. Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques. Soft Comput. 2020;24:13293–304.

    Article  Google Scholar 

  27. AlKaabi LA, Ahmed LS, Al Attiyah MF, Abdel-Rahman ME. Predicting hypertension using machine learning: findings from Qatar Biobank Study. PLoS ONE. 2020;15: e0240370.

    Article  CAS  Google Scholar 

  28. Marin I, Goga N. Hypertension detection based on machine learning. In Proceedings of the 6th Conference on the Engineering of Computer Based Systems ACM, New York, NY, USA, 2019;1–4.

  29. • Boutilier JJ, Chan TCY, Ranjan M, Deo S. Risk stratification for early detection of diabetes and hypertension in resource-limited settings: machine learning analysis. J Med Internet Res. 2021. https://doi.org/10.2196/20123. This is the most recent article identified by our systematic review. The authors used a dataset collected by community health workers in the urban slums of Hyderabad (India). The random forest algorithm obtained the best performance with an AUROC of 0.792, considering a 25-iterative 10-fold cross-validation.

  30. Patnaik R, Chandran M, Lee SC, Gupta A, Kim C, Kim C. Predicting the occurrence of essential hypertension using annual health records. In 2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC) IEEE 2018;1–5

  31. Liu Y, Li S, Jiang H, Wang J. Exploring the relationship between hypertension and nutritional ingredients intake with machine learning. Healthc Technol Lett. 2020;7:103–8.

    Article  Google Scholar 

  32. Chobanian AV, Bakris GL, Black HR, et al. Seventh report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure. Hypertension. 2003;42:1206–52.

    Article  CAS  Google Scholar 

  33. England TN. Numb Er 18 of cardiovascular disease. English J. 2001;345:1291–7.

    Google Scholar 

  34. Giles TD, Berk BC, Black HR, Cohn JN, Kostis JB, Izzo JL Jr, et al. Expanding the definition and classification of hypertension. J Clin Hypertens. 2005;7:505–12.

    Article  Google Scholar 

  35. Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med. 2001;23:89–109.

    Article  CAS  Google Scholar 

  36. Nisbet R, Elder J, Miner GD. Handbook of statistical analysis and data mining applications. Academic Press; 2009.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Epidemiology, School of Public Health, University of São Paulo, São Paulo, SP, Brazil

    Gabriel F. S. Silva & Alexandre D. P. Chiavegatto Filho

  2. Laboratory of Big Data and Predictive Analysis in Healthcare, School of Public Health, University of São Paulo, São Paulo, SP, Brazil

    Thales P. Fagundes & Bruno C. Teixeira

Authors
  1. Gabriel F. S. Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thales P. Fagundes
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bruno C. Teixeira
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alexandre D. P. Chiavegatto Filho
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alexandre D. P. Chiavegatto Filho.

Ethics declarations

Conflict of Interest

The authors declare no competing interests.

Human and Animal Rights and Informed Consent

This article does not contain any studies with human or animal subjects performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the Topical Collection on Guidelines/Clinical Trials/Meta-Analysis

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Silva, G.F.S., Fagundes, T.P., Teixeira, B.C. et al. Machine Learning for Hypertension Prediction: a Systematic Review. Curr Hypertens Rep 24, 523–533 (2022). https://doi.org/10.1007/s11906-022-01212-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11906-022-01212-6

Keywords

Search

Navigation