International Journal of Advances in Electrical Engineering
2024, Vol. 5, Issue 2, Part A
A solution for early detecting the stroke status of the elderly
Author(s): Vu Ngoc Kien and Nguyen Tat Thang
Abstract: Particularly in elderly people, one of the main causes of disability and mortality is stroke, where early detection is essential to minimizing long-term effects and enhancing treatment success. The symptoms of Posterior Circulation Syndrome (PCS) are diverse and vague, making diagnosis difficult. Improving patient outcomes requires prompt and precise detection. The study aims to improve early detection of PCS by utilizing clinical and demographic data and machine learning. The study collects data on elderly individuals aged 60 and above, focusing on risk factors for stroke using wearable sensors to monitor physiological parameters in real-time. In this study, a novel Efficient Osprey Optimized Malleable Random Forest (EOO-MRF) model is proposed for early detection of stroke status in elderly individuals. The collected data was preprocessed using data cleaning, and the noise was removed from the data using in a median filter. The model's performance was evaluated using various kinds of performance metrics, including the parameters accuracy of 95%, sensitivity of 99%, specificity of 96%, precision of 95% and AUC of 99%. The results demonstrate the proposed method outperforms conventional algorithms in the early detection of stroke status in the elderly. The study highlights the effectiveness of a model in predicting stroke risk, enhancing patient care, and reducing healthcare system burden, paving the way for further research and clinical deployment.
DOI: 10.22271/27084574.2024.v5.i2a.75
Pages: 74-79 | Views: 277 | Downloads: 90
Download Full Article: Click Here
How to cite this article:
Vu Ngoc Kien, Nguyen Tat Thang. A solution for early detecting the stroke status of the elderly. Int J Adv Electr Eng 2024;5(2):74-79. DOI: 10.22271/27084574.2024.v5.i2a.75
