----------------------------- ----------------------------
Volume 10, Issue 2 (Summer 2024)                   JMIS 2024, 10(2): 206-219 | Back to browse issues page

Ethics code: IR.MUMS.REC.1401.038

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tahmasbi H, Besharati R. Developing a Mobile Application for Early Prediction of Hypertension in Children. JMIS 2024; 10 (2) :206-219
URL: http://jmis.hums.ac.ir/article-1-502-en.html
Developing a Mobile Application for Early Prediction of Hypertension in Children
Hamidreza Tahmasbi , Reza Besharati
Department of Computer Engineering, Faculty of Engineering, Kashmar Branch, Islamic Azad University, Kashmar, Iran.
Keywords: Hypertension, Mobile applications, Early diagnosis, Child health, Machine learning
Full-Text [PDF 5823 kb]   (572 Downloads)     |   Abstract (HTML)  (1205 Views)
Full-Text:   (596 Views)
Introduction
Today, an increasing number of children and teenagers suffer from hypertension due to poor lifestyle, including poor nutrition, low physical activity, overweight or obesity. There is evidence that high blood pressure and cardiovascular disease in adulthood originate in childhood. Early identification of children with hypertension or at higher risk of hypertension is necessary to minimize the risks and consequences of this condition.
Today, the use of machine learning methods as a useful and effective solution in predicting and controlling hypertension has received special attention. On the other hand, diagnosing and predicting high blood pressure with the help of a mobile application can increase the ability to monitor blood pressure due to its ease of use for many people. In this study, we aim to design and develop a mobile application for diagnosing and predicting hypertension in children, using machine learning methods, so that parents can continuously control and monitor their children’s blood pressure.

Methods
In this applied-developmental study that was conducted in 2022, first, the values related to 19 factors affecting hypertension were collected from 1287 primary school children aged 7-13 years using questionnaires and measurements with the written consent of their parents. After data preprocessing and preparation, three commonly used machine learning methods in hypertension diagnosis and prediction, including multi-layer perceptron (MLP), support vector machine (SVM) and random forest (RF), were separately applied to the data set and performed the prediction. In the proposed model, four categories of normal blood pressure, pre-hypertension, stage 1 hypertension and stage 2 hypertension were considered as the observation framework. Then, the results obtained from the three mentioned learning methods were combined using the Dempster-Shafer evidence theory for the final prediction. Model implementation was done using Weka software, version 3.8.6 and Python programming language. To measure the effectiveness of the model, the 10-fold cross-validation method and the paired t-test were used for comparison. P<0.05 was considered statistically significant. Finally, the proposed model was implemented using the Kiwi software, version 2.1.0 development kit in an Android mobile application.

Results
The rates of precision, sensitivity and specificity for the proposed model and three machine learning methods are shown in Table 1.



The rates for the proposed model in comparison with other new methods for diagnosing and predicting hypertension are presented in Table 2.



The results showed that the precision, sensitivity and specificity for the proposed model were significantly higher than those of the three machine learning methods and those of other methods. The results of the paired t-test for comparing the accuracy of the proposed model and other methods are shown in Table 3. Considering that the P<0.05, it can be said that the difference in the effectiveness between the proposed model and learning methods and other methods was statistically significant. 




Conclusion
These results showed that the proposed model can better predict and diagnose hypertension in children and can help improve accuracy and reduce the error rate. By using the developed mobile application, parents can find out about their children’s blood pressure status and see a doctor immediately if there was any danger. This application, in addition to being a basis for timely and appropriate prevention and treatment of hypertension in children, can help make decisions for the allocation of health resources and necessary policies.

Ethical Considerations

Compliance with ethical guidelines
This study was approved by Mashhad University of Medical Sciences (Code: MUMS.IR 038.1401.REC).

Funding
This research did not receive any grant from funding agencies in the public, commercial, or non-profit sectors.

Authors' contributions
Conceptualization, formal analysis, methodology, investigation, supervision: All authors; Software, writing, funding acquisition, and resources: Hamidreza Tahmasbi.

Conflicts of interest
The authors declared no conflict of interest.




References
  1. Nematollahi MA, Jahangiri S, Asadollahi A, Salimi M, Dehghan A, Mashayekh M, et al. Body composition predicts hypertension using machine learning methods: A cohort study. Sci Rep. 2023; 13(1):6885. [DOI:10.1038/s41598-023-34127-6] [PMID]
  2. Chowdhury MZI, Naeem I, Quan H, Leung AA, Sikdar KC, O'Beirne M, et al. Prediction of hypertension using traditional regression and machine learning models: A systematic review and meta-analysis. Plos One. 2022; 17(4):e0266334. [DOI:10.1371/journal.pone.0266334] [PMID]
  3. Tozo TAA, Gisi ML, Brand C, Moreira CMM, Pereira BO, Leite N. Family history of arterial hypertension and central adiposity: Impact on blood pressure in schoolchildren. BMC Pediatr. 2022; 22(1):497. [DOI:10.1186/s12887-022-03551-4] [PMID]
  4. Martinez-R’ios E, Montesinos L, Alfaro-Ponce M, Pecchia L. A review of machine learning in hypertension detection and blood pressure estimation based on clinical and physiological data. Biomed Signal Process Control. 2021; 68:102813. [DOI:10.1016/j.bspc.2021.102813]
  5. Hamoen M, de Kroon MLA, Welten M, Raat H, Twisk JWR, Heymans MW, et al. Childhood prediction models for hypertension later in life: A systematic review.J Hypertens. 2019; 37(5):865-77. [DOI:10.1097/HJH.0000000000001970] [PMID]
  6. Hardy ST, Urbina EM. Blood pressure in childhood and adolescence. Am J Hypertens. 2021; 34(3):242-9. [DOI:10.1093/ajh/hpab004]
  7. Song P, Zhang Y, Yu J, Zha M, Zhu Y, Rahimi K, et al. Global prevalence of hypertension in children: A systematic review and meta-analysis. JAMA Pediatr. 2019; 173(12):1154-63. [DOI:10.1001/jamapediatrics.2019.3310] [PMID]
  8. Akbari M, Moosazadeh M, Ghahramani S, Tabrizi R, Kolahdooz F, Asemi Z, et al. High prevalence of hypertension among Iranian children and adolescents: A systematic review and meta-analysis. J Hypertens. 2017; 35(6):1155-63. [DOI:10.1097/HJH.0000000000001261] [PMID]
  9. Frey L, Menon C, Elgendi M. Blood pressure measurement using only a smartphone. NPJ Digit Med. 2022; 5(1):86. [DOI:10.1038/s41746-022-00629-2] [PMID]
  10. Visco V, Izzo C, Mancusi C, Rispoli A, Tedeschi M, Virtuoso N, et al. Artificial intelligence in hypertension management: An ace up your sleeve. J Cardiovasc Dev Dis. 2023; 10(2):74. [DOI:10.3390/jcdd10020074] [PMID]
  11. Cai A, Zhu Y, Clarkson SA, Feng Y. The use of machine learning for the care of hypertension and heart failure. JACC Asia. 2021; 1(2):162-72.[DOI:10.1016/j.jacasi.2021.07.005] [PMID]
  12. Silva GFS, Fagundes TP, Teixeira BC, Chiavegatto Filho ADP. Machine Learning for hypertension prediction: A systematic review. Curr Hypertens Rep. 2022; 24(11):523-33. [DOI:10.1007/s11906-022-01212-6] [PMID]
  13. Ambika M, Raghuraman G, SaiRamesh L. Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques. Soft Comput. 2020; 24(17):13293-304. [Link]
  14. Islam SMS, Talukder A, Awal MA, Siddiqui MMU, Ahamad MM, Ahammed B, et al. Machine learning approaches for predicting hypertension and its associated factors using population-level data from three South Asian Countries. Front Cardiovasc Med. 2022; 9:839379. [DOI:10.3389/fcvm.2022.839379] [PMID]
  15. Oanh TT, Tung NT. Predicting hypertension based on machine learning methods: A case study in Northwest Vietnam. Mobile Netw Appl. 2022; 27:2013–23. [DOI:10.1007/s11036-022-01984-w]
  16. AlKaabi LA, Ahmed LS, Al Attiyah MF, Abdel-Rahman ME. Predicting hypertension using machine learning: Findings from Qatar Biobank Study. Plos One. 2020; 15(10):e0240370. [DOI:10.1371/journal.pone.0240370] [PMID]
  17. Zhao H, Zhang X, Xu Y, Gao L, Ma Z, Sun Y, et al. Predicting the risk of hypertension based on several easy-to-collect risk factors: A machine learning method. Front Public Health. 2021; 9:619429. [DOI:10.3389/fpubh.2021.619429] [PMID]
  18. Chai SS, Goh KL, Cheah WL, Chang YHR, Ng GW. Hypertension prediction in adolescents using anthropometric measurements: Do machine learning models perform equally well? Appl Sci. 2022; 12(3):1600.  [DOI:10.3390/app12031600]
  19. Chai SS, Cheah WL, Goh KL, Chang YHR, Sim KY, Chin KO. A multilayer perceptron neural network model to classify hypertension in adolescents using anthropometric measurements: A cross-sectional study in Sarawak, Malaysia. Comput Math Methods Med. 2021; 2021:2794888.[DOI:10.1155/2021/2794888] [PMID]
  20. Dehghandar M, Hassani Bafrani A, Dadkhah M, Qorbani M, Kelishadi R. [Diagnosis of obesity and hypertension in Isfahani students using artificial neural network (Persian)]. J Health Biomed Inf. 2021; 8 (1):12-23. [Link]
  21. Tahmasbi H, Jalali M, Shakeri H. [An expert system for heart disease diagnosis based on evidence combination in data mining (Persian)]. J Health Biomed Inform. 2017; 3(4):251-8. [Link]
  22. Ren L, Zhang H, Seklouli AS, Wang T, Bouras A. Stacking-based multi-objective ensemble framework for prediction of hypertension. Expert Syst Appl. 2023; 215:119351. [DOI:10.1016/j.eswa.2022.119351]
  23. Fitriyani NL, Syafrudin M, Alfian G, Rhee J. Development of disease prediction model based on ensemble learning approach for diabetes and hypertension. IEEE Access. 2019; 7:144777-89. [DOI:10.1109/ACCESS.2019.2945129]
  24. 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(3):445-50. [DOI:10.1111/jch.13759] [PMID]
  25. Fang M, Chen Y, Xue R, Wang H, Chakraborty N, Su T, et al. A hybrid machine learning approach for hypertension risk prediction. Neural Comput Appl. 2021; 35:14487–97. [DOI:10.1007/s00521-021-06060-0]
  26. Rao G. Diagnosis, epidemiology, and management of hypertension in children. Pediatrics. 2016; 138(2):e20153616. [DOI:10.1542/peds.2015-3616] [PMID]
  27. Tahmasbi H, Amoozgar M, Adine H. [Replacement of missing values and its effect on the classification accuracy in medical data mining (Persian)]. J Health Biomed Inf. 2015; 2(1):24-32. [Link]
  28. Wang YC, Cheng CH. A multiple combined method for rebalancing medical data with class imbalances. Comput Biol Med. 2021; 134:104527. [DOI:10.1016/j.compbiomed.2021.104527] [PMID]
Type of Study: Research | Subject: Special
Received: 2023/12/4 | Accepted: 2024/06/6 | Published: 2024/07/1
Add your comments about this article : Your username or Email:
CAPTCHA
Send email to the article author

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2025 CC BY-NC 4.0 | Journal of Modern Medical Information Sciences

Designed & Developed by: Yektaweb