Hypertension Risk Prediction Using GRU-Based Deep Learning Optimized with Stochastic Gradient Descent
Abstract views: 44 , PDF downloads: 77Abstract
Hypertension stands out as a highly common heart disease across the globe, where spotting risks early is vital to curb its prolonged effects. Still, standard check-up approaches usually hinge on unchanging health stats that overlook habit-based risk trends entirely. This gap complicates building precise alert systems for folks with different routines and body profiles. Fueled by the push for a more flexible and trend-focused strategy, the study delves into applying a Gated Recurrent Unit (GRU)-driven neural network to predict hypertension threats using lifestyle and past health data. The model blends sequential trend analysis with two GRU layers, dropout for stability, and L2 limits, tuned via Stochastic Gradient Descent (SGD) with momentum and Nesterov boosts. It lets the network uncover intricate links between factors such as age, salt consumption, stress, BMI, sleep time, family background, and treatment history. Trials on 1,985 patient records reveal solid prediction skills, with top classification rates and well-defined categories in the confusion matrix. The training and validation plots also prove smooth learning without major overfit. Next steps cover enlarging the data with continuous health metrics, incorporating attention tools for clearer insights, and pitting it against cutting-edge optimizers like AdamW and Ranger to enhance broader applicability.
Downloads
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[2] L. Huang, M. Wang, and T. Zhao, “Lifestyle determinants of hypertension: A cross-population analysis,” International Journal of Public Health Research, vol. 34, no. 1, pp. 112–124, 2021.
[3] S. Patel and Y. Lin, “Predictive modeling for hypertension using machine learning: A comparative study,” Healthcare Informatics Review, vol. 12, no. 3, pp. 88–99, 2021.
[4] J. Kim and H. Park, “A deep learning approach for early detection of cardiovascular diseases,” Biomedical Signal Intelligence, vol. 9, no. 4, pp. 201–214, 2021.
[5] T. Noor and K. Hasan, “Risk prediction of chronic diseases using hybrid classification models,” Computational Medicine Research, vol. 5, no. 2, pp. 76–89, 2021.
[6] R. Mahmud et al., “Impact of categorical encoding on health prediction models,” Journal of Data Science Applications, vol. 7, pp. 41–52, 2022.
[7] F. Liu and S. Wong, “Machine learning for lifestyle-based disease prediction,” Artificial Intelligence in Health Analytics, vol. 11, pp. 94–107, 2022.
[8] P. Adhikari and D. Sen, “Handling heterogeneous health datasets for predictive modeling,” Journal of Medical Computing, vol. 16, no. 2, pp. 133–147, 2022.
[9] G. Torres and V. Kumar, “Feature importance in hypertension prediction using statistical learning,” Clinical Data Engineering, vol. 8, no. 1, pp. 54–68, 2022.
[10] A. Rahman and M. Idris, “GRU networks for clinical risk evaluation,” IEEE Transactions on Neural Systems, vol. 31, no. 7, pp. 1151–1162, 2022.
[11] Y. Zhang and Q. Sun, “Optimization strategies for deep neural networks in medical tasks,” IEEE Access, vol. 10, pp. 19245–19258, 2022.
[12] R. S. Lee et al., “Regularization techniques in deep learning-based disease prediction,” Medical AI Letters, vol. 3, no. 2, pp. 44–59, 2022.
[13] F. Al-Sayed and K. Tao, “Evaluation metrics for clinical classification models: A review,” Health Informatics Review, vol. 14, no. 3, pp. 221–236, 2023.
[14] M. Silva and P. Duarte, “Sequential learning models for health records: GRU vs. LSTM,” IEEE Journal of Biomedical Computing, vol. 59, no. 1, pp. 102–114, 2023.
[15] D. H. Nguyen and B. Schoen, “Lifestyle factors as predictors of hypertension: A deep learning perspective,” Journal of Preventive Health AI, vol. 2, no. 1, pp. 15–28, 2023.
[16] W. Cheng, J. Luo, and T. Min, “SGD variants for medical data optimization: A performance study,” Neural Computing in Healthcare, vol. 6, pp. 67–82, 2023.
[17] S. Kim and E. Cho, “Performance comparison of adaptive optimizers in clinical prediction models,” IEEE Transactions on Health Informatics, vol. 12, no. 4, pp. 355–368, 2023.
[18] H. Parmar et al., “Deep learning for hypertension classification from multidimensional datasets,” Computational Health Sciences, vol. 4, no. 2, pp. 80–93, 2024.
[19] K. Mori and O. Tateyama, “Interpretable GRU frameworks for healthcare analytics,” IEEE Access, vol. 12, pp. 9124–9138, 2024.
[20] F. Abdullah and R. Hassan, “Generalization challenges in medical deep learning models,” International Journal of AI in Medicine, vol. 10, no. 1, pp. 71–85, 2024.
[21] S. Yakubu et al., “Hybrid GRU-attention architectures for risk prediction,” IEEE Biomedical Signal Processing Letters, vol. 8, no. 3, pp. 169–178, 2024.
[22] M. Patel and J. Rivera, “Lifestyle-oriented prediction models using deep neural architectures,” Journal of Digital Healthcare AI, vol. 5, no. 2, pp. 144–159, 2025.
[23] L. Fernández and P. Ortega, “Improving hypertension prediction with recurrent deep networks,” IEEE Transactions on Biomedical Intelligence, vol. 7, no. 1, pp. 1–12, 2025.
[24] Y. Nakamura, “Advances in sequential modeling for clinical decision support,” Medical Machine Intelligence Review, vol. 4, no. 1, pp. 22–38, 2025.
