UTILIZING ARTIFICIAL INTELLIGENCE AND DEEP LEARNING MACHINE-LEARNING APPROACH FOR OPTIMIZING DRUG DELIVERY SYSTEMS

Abstract

The thesis structure covers in short introducers the role of machine learning in explaining future behavior, and in depth it investigates the concepts of supervised, un-supervised, semi-supervised, reinforcement learning, highlighting deep learning. Hypertension is one of the most significant public health issues globally, with millions of individuals infected. Therefore, accurately predicting treatment groups for patients with hypertension will assist healthcare providers in making informed decisions that will enhance the outcome. However this study aims to create machine learning model capable of predicting the best treatment group for patients with hypertension based on demographic and clinical traits. A patient dataset was used comprising individuals diagnosed with hypertension and different machine learning models were evaluated. Findings from this study imply that machine learning models can be applied in predicting the ideal treatment group for hypertensive patients mandatorily. This research used a dataset available on Kaggle named “Hypertension Treatment Clinical Trial Dataset.