https://ojs.sin-chn.com/index.php/EHJ <p>The <em>e-Health Journal </em>is a multidisciplinary, peer-reviewed academic publication that focuses on the intersection of healthcare, technology, and digital innovation. The journal aims to provide a platform for cutting-edge research, discussions, and insights related to the application of electronic health technologies in clinical practice, healthcare management, and public health. It is dedicated to advancing the understanding and implementation of digital health tools and strategies that improve the delivery of healthcare services, enhance patient outcomes, and promote health equity across various populations.</p> <p>The journal publishes original research, review articles, case studies, and thought leadership pieces on topics that explore the role of technology in modern healthcare systems. By fostering collaboration between healthcare professionals, researchers, technologists, and policymakers, e-Health Journal serves as a leading resource for those involved in the development, implementation, and evaluation of e-health solutions.</p> Sin-Chn Scientific Press Pte. Ltd en-US e-Health Journal https://ojs.sin-chn.com/index.php/EHJ/article/view/1172 <p>In recent years, the high incidence of diabetes and its complications has posed a significant threat to public health. To enhance the early diagnosis rate, this paper proposes a risk prediction model based on an improved Whale Optimization Algorithm (WOA) and Support Vector Machine (SVM). The model first uses a Gaussian kernel function to address the issue of nonlinear data being linearly separable in high-dimensional feature space. Then, it optimizes the Whale Optimization Algorithm by incorporating Tent mapping, opposition-based learning, nonlinear functions, and an adaptive inertia weight strategy. Subsequently, SVM parameters are optimized to determine the optimal penalty factor and kernel function parameters, improving the efficiency of SVM kernel parameter search. Finally, the optimized PAWOA-SVM model is applied to the diabetes dataset of Iraqi Medical Institutions and the Alibaba Cloud Tianchi Precision Medical Contest dataset for diabetes prediction and validation, achieving a prediction accuracy of 93.54%. The prediction results of the PAWOA-SVM model are compared with other commonly used models such as BP neural networks, PSO-SVM, and decision trees, demonstrating the superior predictive performance of the PAWOA-SVM model. Both the model’s recognition accuracy and computational efficiency show considerable improvement. Therefore, this research provides an effective model that can assist doctors in making early judgments about prediabetes, thereby improving the diagnosis rate of prediabetes.</p> Xinyi Yang Jingyi Yang Xiaoyan Liu Qiang Hu Copyright (c) 2024 Xinyi Yang, Jingyi Yang, Xiaoyan Liu, Qiang Hu https://creativecommons.org/licenses/by/4.0/ 2024-12-27 2024-12-27 1 1 1172 1172 10.62617/ehj1172