Predicting the Onset of Hypertension Using Deep Learning Models in the Copperbelt Province of Zambia – Volume 12 Issue 5

Hypertension continues to be a significant health challenge in Zambia, particularly in the Copperbelt Province, where many cases are diagnosed late and often advance to severe complications. This research aimed to design an artificial intelligence–driven system capable of predicting hypertension at earlier stages, thereby supporting preventive healthcare in resource-constrained settings. The study adopted a flexible, mixed-methods design that combined publicly available health datasets with professional insights from local medical practitioners. Predictive variables, including blood pressure readings, cholesterol levels, body mass index, and heart rate, were utilized to train various deep learning models. The approaches tested included Deep Neural Networks, Convolutional Neural Networks, and Recurrent Neural Networks enhanced with Long Short-Term Memory capabilities. Model performance was assessed using widely accepted evaluation measures, namely accuracy, recall, precision, the F1 measure, and the area under the curve. The findings indicated that the optimized Convolutional Neural Network achieved an accuracy level of slightly above 85 percent. In comparison, the Long Short-Term Memory model produced an accuracy of eighty-three percent, with a recall rate exceeding ninety percent in detecting hypertensive cases. To ensure the system was practical for end-users, it incorporated a user-friendly interface developed with Python Tkinter and Jupyter Notebook, enabling real-time prediction and reporting. Its modular server-client architecture enhanced both scalability and security, while model interpretability was supported through visualization techniques such as gradient-based mapping. The research also highlighted several challenges, including the shortage of structured local datasets, insufficient computing resources, and limited knowledge of artificial intelligence within the health sector. Despite these obstacles, the research demonstrated that tailored deep learning applications can strengthen public health decision-making in Zambia and provide a foundation for the development of future data-driven medical solutions, as exemplified by the prototype system developed.

The research demonstrates that a deep learning–based hypertension prediction system can operate reliably in a low-resource context, with optimized models achieving high discrimination and clinically preferable sensitivity for hypertensive cases, thereby enabling earlier case detection, targeted confirmatory measurements, and more efficient allocation of limited primary-care resources. Its importance lies in moving routine care from reactive treatment toward proactive, data-informed prevention through a modular client–server workflow that delivers real-time risk scores, printable summaries, and an auditable trail suitable for integration into outpatient intake and follow-up. At the same time, several limitations temper generalization, including reliance on non-local training data, modest computational capacity in public facilities, limited practitioner familiarity with artificial intelligence, and performance gaps observed during initial live tests. The work is highly relevant to health systems in Zambia and similar settings, where structured registries are scarce, yet the burden of hypertension is rising. It provides a practical pathway for embedding prediction into everyday care without disrupting existing processes. Immediate applications include triage lists for community screening, clinic-side decision support that privileges high recall to reduce missed cases, and standardized reporting that supports monitoring and quality improvement. To strengthen impact, the research recommends curating and maintaining structured local datasets, adopting transfer learning and periodic model recalibration to local case mix, conducting prospective utility and safety evaluations, investing in lightweight acceleration and secure data infrastructure, and delivering targeted training for clinicians and administrators alongside transparent governance and privacy safeguards, so that the system evolves into a trustworthy, scalable tool for early hypertension detection and sustained cardiovascular risk reduction without switching between tools. Participants benefited from interactive problem-solving, instant feedback, and the opportunity to experiment within a supportive digital environment, highlighting the potential of such systems to bridge the gap between theoretical instruction and practical application in computer science education.

[1] C. W. Loomis, “Morbidity and its measurement: Concepts and methods,” J. Epidemiol. Community Health, vol. 48, no. 6, pp. 505–510, 1994. [2] [G. Bradski, “The OpenCV library,” Dr. Dobb’s J. Softw. Tools, 2000. [3] W. McKinney, “Data structures for statistical computing in Python,” in Proc. 9th Python in Science Conf. (SciPy), Austin, TX, USA, 2010, pp. 51–56. [4] T. M. Mitchell, The Discipline of Machine Learning. Pittsburgh, PA: Carnegie Mellon University, 2006. [5] J. D. Hunter, “Matplotlib: A 2D graphics environment,” Comput. Sci. Eng., vol. 9, no. 3, pp. 90–95, 2007. [6] M. Chen, Y. Hao, K. Hwang, L. Wang, and L. Wang, “Disease prediction by machine learning over big data from healthcare communities,” IEEE Access, vol. 5, pp. 8869–8879, 2017. [7] A. Rajkomar et al., “Scalable and accurate deep learning with electronic health records,” npj Digit. Med., vol. 1, no. 18, pp. 1–10, 2018. [8] [V. Kumar and M. Singh, “Applications of machine learning predictive models in chronic disease diagnosis,” Procedia Comput. Sci., vol. 132, pp. 1048–1057, 2018. [10] A. H. Kaiser, L. Hehman, B. C. Forsberg, W. M. Simangolwa, and J. Sundewall, “Availability, prices and affordability of essential medicines for treatment of diabetes and hypertension in private pharmacies in Zambia,” PLoS ONE, vol. 14, no. 12, e0226169, 2019. [11] Y. Tateyama et al., “Dietary habits, body image, and health service access related to cardiovascular diseases in rural Zambia: A qualitative study,” PLoS ONE, vol. 14, no. 2, e0212739, 2019. [12] P. Chanda-Kapata, R. Kapata, and N. Zumla, “Health systems challenges in Zambia and their impact on disease management,” Int. J. Infect. Dis., vol. 98, pp. 359–366, 2020. [13] J. M. Mwewa, B. Mutale, and S. Michelo, “Challenges in hypertension care in Zambia: A review of current evidence,” BMC Public Health, vol. 20, no. 1, pp. 1–10, 2020. [14] M. Cardoso, J. Lima, and A. Pereira, “Rapid prototyping of interactive applications with Python and Tkinter,” in Proc. Int. Conf. Inf. Syst. Design Commun. (ISDOC), Lisbon, Portugal, 2020, pp. 15–21. [15] M. Lee, H. Lee, M. Kim, and H. Yoo, “A precision health service for chronic diseases: Development and cohort study using wearable device, machine learning, and deep learning,” JMIR mHealth uHealth, vol. 8, no. 6, pp. 1–15, 2020. [16] C. R. Harris et al., “Array programming with NumPy,” Nature, vol. 585, no. 7825, pp. 357–362, 2020. [17] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn—Res., vol. 12, pp. 2825–2830, 2011. [18] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016. [19] M. Abadi et al., “TensorFlow: Large-scale machine learning on heterogeneous systems,” arXiv preprint arXiv:1603.04467, 2016. [20] Dulam, N., & Gosukonda, V. (2021). A comprehensive review of AI-based diagnostic tools for early disease detection in healthcare. IEEE Access, 9, 144210–144225. [21].Racic, L., Popovic, T., Cakic, S., & Sandi, S. (2021, February). Pneumonia detection using deep learning based on a convolutional neural network. In 2021, the 25th International Conference on Information Technology (IT) (pp. 1–4). IEEE. Nel, F., & Ngxande, M. (2021, January). Driver activity recognition through deep learning. In 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) (pp. 1–6). IEEE.

Call for Paper (Hub) Fast Paper Publication IJCT Indexing & Databases Submit Manuscript Call for Paper: Sep–Oct 2025 Call for Paper: Publish Research