In today's digital era, e-healthcare systems exploit digital technologies and telecommunication devices such as mobile devices, computers and the internet to provide high-quality healthcare services. E-healthcare decision support systems have been developed to optimize the healthcare services and enhance a patient's health. These systems enable rapid access to the specialized healthcare services via reliable information, retrieved from the cases or the patient histories. This phenomenon reduces the time taken by the patients to physically visit the healthcare institutions. In the current research work, a new Shuffled Frog Leap Optimizer with Deep Learning-based Decision Support System (SFLODL-DSS) is designed for the diagnosis of the Cardiovascular Diseases (CVD). The aim of the proposed model is to identify and classify the cardiovascular diseases. The proposed SFLODL-DSS technique primarily incorporates the SFLO-based Feature Selection (SFLO-FS) approach for feature subset election. For the purpose of classification, the Autoencoder with Gated Recurrent Unit (AEGRU) model is exploited. Finally, the Bacterial Foraging Optimization (BFO) algorithm is employed to fine-tune the hyperparameters involved in the AEGRU method. To demonstrate the enhanced performance of the proposed SFLODL-DSS technique, a series of simulations was conducted. The simulation outcomes established the superiority of the proposed SFLODL-DSS technique as it achieved the highest accuracy of 98.36%. Thus, the proposed SFLODL-DSS technique can be exploited as a proficient tool in the future for the detection and classification of CVD.