Advanced Cloud-Based Prediction Models for Cardiovascular Disease: Integrating Machine Learning and Feature Selection Techniques

Cardiovascular disease is a major cause of global mortality, and early detection and prevention are crucial for lessening the strain on the healthcare system. Over the past few years, cloud computing (CC) and Machine Learning methods have demonstrated significant promise in enhancing heart disease prediction precision and effectiveness. However, many commonly used methods are susceptible to feature omission, leading to reduced accuracy due to increased data variability. Furthermore, a heart disease prediction model can be developed using ANSIS classification and random forest feature selection implemented in a CC environment. This will solve that problem. By enhancing the power of Random Forest (RF) for feature selection and the adaptability of ANSIS for classification, we aim to improve the accuracy and robustness of the prediction model. This research could support more effective and scalable cardiac prediction systems, resulting in better patient outcomes and lower healthcare costs. The initial preprocessing involved Z-score normalization to reduce noise and verify the medical scaling factor, Heart Disease Prone Factor, which is estimated based on the entropy gain model to marginalize the disease rate. Feature selection was then applied to reduce non-relevant features and improve the disease impact finding rate. The dimensionality ratio was decreased, and the most significant characteristics were chosen using the RF approach. Finally, the Adaptive Neuro-Fuzzy Inference System method can be used to classify and generate predictions to achieve accuracy. Multiclass labels define the prediction class by referencing the disease impact rate. Heart disease prediction and patient outcomes could be improved through the use of this comprehensive approach. This research contributes to the field of predictive modelling for heart disease and provides valuable insights for improving performance in higher prediction rates, recall precision rates, F1 with redundant time complexity, and management of cardiovascular health by leveraging advanced data analysis techniques and machine learning algorithms.