Excessive treatment of cardiovascular disease-related health information has led to an increase in a specific order that limits independent analysis for variable estimation in decision-making. A major illness that can be fatal to a person is coronary disease, which is characterized by a heart condition that tends to malfunction. Proper identification during the first phases of the illness can avert cardiac failure, therefore sparing a person's life. Many studies are being conducted to identify heart problems. Improvements are obtained by accurate diagnosis and early identification of health problems through patient information analysis. The proposed structure offers a unique method depending on the blockages of the heart's major blood vessels—the hybrid Improved Multilayer Perceptron approach with Weighed Quantum Dragonfly Algorithms (IMLP-WQDA) to assess the degree of severity of heart disorders. To comprehend the direction of the qualities influencing the outcomes, the study uses principal characteristic assessment. The study employs a method to identify and extract the affecting variables, depending on the UCI information. The ultimate goal of this effort is to identify the criteria that have the most influence on the detection of heart illness and to acquire 36 traits that are primarily grouped. To do this, the IMLP-WQDA model—which uses a variety of characteristics to determine the severity of cardiac disease—is presented. For the best learning environment, the implemented IMLP-WQDA makes use of back-propagation. To comprehend the direction of the qualities influencing the outcomes, the study additionally uses a principal attribute assessment. The analysis of cardiovascular disease severity using the proposed IMLP-WQDA framework is the work's ultimate product. It has been discovered that, in comparison to conventional methods, the evaluation of the proposed approach offers somewhat greater precision and predictive indicators.