Enhancing heart disease risk prediction with GdHO fused layered BiLSTM and HRV features: A dynamic approach

•The highlights of the article are given below for your kind perusal. Kindly, consider and forward my article for further processes.•This research work is highly focused on image encryption. This research work is highly meaningful, as it includes Guard dog Hunt Optimization enabled fused layered BiLSTM (GdHO-BiLSTM) is developed for heart disease risk prediction.•Moreover, to know about the most interesting works undergone in literature, we have collected a total of 38 literature papers on heart disease risk prediction concepts.•Analyzing the past as well as recent works helps to gain more knowledge regarding the image encryption. In addition, it’s good to learn the advantage and drawbacks of existing works, which might be a mile stone for the future researchers. Heart disease remains a major global health concern, necessitating early and accurate diagnosis for effective intervention and risk management. Former heart disease diagnosis methods often rely on static data and lack real-time monitoring, potentially missing dynamic risk factors. They may also have limitations in sensitivity and specificity, leading to misdiagnoses. To overcome these obstacles, this research presents an intelligent decision support system (IDSS) for heart disease risk prediction that leverages the power of a Fused Layered Bidirectional Long Short-Term Memory with Guard dog Hunt Optimization (GdHO-BiLSTM). The IDSS takes advantage of the valuable information present in Heart Rate Variability (HRV) features that serve as indicators of autonomic nervous system function and cardiovascular well-being. The GdHO-BiLSTM model’s unique blend of deep learning and optimization techniques enhances its ability to discern intricate patterns within HRV data. The Fused Layered BiLSTM model is employed for its capability to acquire the temporal dependencies in sequential data, making the model ideal for analyzing heart rate variability and other physiological metrics. By incorporating IoT-generated data streams, the IDSS provides a dynamic and context-aware approach to heart disease risk assessment. This research demonstrates superior predictive performance, as measured by accuracy 94.17%, sensitivity 83.18%, and specificity 96% in TP90 offering clinicians and healthcare providers a valuable tool for early detection and personalized intervention.