Journal of Cybersecurity and Information Management JCIM 2690-6775 2769-7851 10.54216/JCIM https://www.americaspg.com/journals/show/3647 2019 2019 Department of Computer Science and Engineering, Faculty of Engineering, Karpagam Academy of Higher Education, Coimbatore, India K. K. Department of Computer Science and Engineering, Faculty of Engineering, Karpagam Academy of Higher Education, Coimbatore, India N. Mohana Sundaram Department of Computer Science and Engineering, Faculty of Engineering, Karpagam Academy of Higher Education, Coimbatore, India R. Santhosh One of the most intriguing study subjects in the scientific world is medical data visualization. Researchers focus more on creating a medical that is reliable and efficient. Over the past ten years, varieties of methods have been developed, and investigation is still ongoing to improve healthcare systems' efficiency. To forecast or identify illnesses from medical information, the first stage in medical evaluation of information systems uses statistical techniques. However, statistical techniques yield unreliable findings due to the high amount and variety of the data, which affects the performance of the healthcare system. Numerous methods and solutions for conventional problems were made possible by the advancement of technology and the implementation of AI in the clinical field. To improve patient results and save medical expenses, acute illness prediction is essential. With an emphasis on diabetes, CVD, and specific cancers, this study investigates the effectiveness of many hybrid DL approaches in forecasting the beginning of chronic illnesses. Using a varied dataset of 100 thousand patient records, we evaluated the performance of a few hybrid methods, such as Autoencoder-Support Vector Machine (AE-SVM), Gradient Boosting-Neural Network (GB-NN), and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM). Our findings show that when it came to forecasting the development of disease within a period of five years the CNN-LSTM model offered the greatest accuracy of 95.3%, closely followed by GB-NN with 94.1% and AE-SVM with 92.8%. Along with discussing the possible incorporation of these hybrid models into healthcare DSS, the study also found important predictive criteria. Our results indicate that hybrid DL techniques, as opposed to conventional single-algorithm approaches, can greatly improve early disease identification and treatment procedures in healthcare settings. 2025 2025 107 119 10.54216/JCIM.160109 https://www.americaspg.com/articleinfo/2/show/3647