Intelligence - based decision support system for diagnosing the incidence of hypertensive type

Hypertension is a major non-communicable disease, a silent killer that serves as a root cause for many entangled maladies. Early analysis and detection will play vital roles in reducing the prevalence of hypertension and its associated risk factors. As medicine moves forward, there is a need for sophisticated decision support systems to make real-time predictions. Since most medical applications need to deal with multi-class problems, high diagnostic prediction accuracy is extremely important. The quality of data also significantly affects the learning model's performance. These issues induce the need for proper exploration and investigation of the multi-class medical dataset. This research intends to present an intelligent learning model that can explore medical data and offer decision support for domain experts and individuals. As clinical data tend to be, grimy appropriate pre-processing techniques are essential to ensure high data quality. This paper deals with the poor-quality data using computational statistical techniques. The prominent features are obtained by employing diverse feature selection techniques and provide a competitive report. We evolved a supervised learning model that can handle multi-class issues in diagnosing medical data categories. This model will learn from the data samples by using a multi-class support vector machine technique to generate precise predictions. We evaluated our learning model by using a real-time hypertension dataset obtained from primary health centres. The proposed approach improves predictive accuracy, precision and recall for handling the multi-class dataset above that of existing techniques. The outcome positively reveals that the proposed intelligent model is effective in undertaking medical decision-making task.