Heart Failure Prediction for a Patient Using Hybrid African Buffalo Optimization with Naive Bayes Machine Learning Techniques

The first time the heart failure syndrome was referred to as an epidemic was about 25 years ago. Due to an ageing and expanding population, the overall number of heart failure patients is rising nowadays. The case mix for heart failure, on the other hand, seems to be changing. In certain populations, the prevalence has levelled off and may even be decreasing, but in the relatively young, alarmingly opposite tendencies have been detected, likely as a result of an increase in obesity. It has also been clear when heart failure transitions to ejection fraction preservation. Heart failure is exacerbated by modifications in cardiac energy metabolism. Yet, intricate modifications in energy metabolism brought on by heart failure depend not only on the type and severity of the disease but also on the presence of common comorbidities such as type 2 diabetes and obesity. The primary cause of the energy imbalance in the failing heart is a loss in mitochondrial oxidative capacity. Glycolysis's increased ATP production somewhat makes up for this. The relative contribution of different fuels to mitochondrial ATP synthesis changes as ketone oxidation rises and glucose and amino acid oxidation fall. This study uses the Kaggle heart disease dataset to improve the accuracy of HF prediction. The likelihood of HF was predicted using a number of machine learning algorithms after data from a medical database was analysed. The proposed approach employs a Hybrid African Buffalo Optimization with Naive Bayes (HABO+NB) to forecast a patient's heart failure. The new work also improved the prior accuracy score in forecasting heart disease, per the results and comparison analysis. The machine learning model presented in this research can be integrated with medical information systems to predict heart failure or any other disease using real-time patient data.