A Comprehensive Review on Machine Learning Based Models for Healthcare Applications

Abstract

At present, there has been significant progress concerning AI and machine learning, specifically in medical sector. Artificial intelligence refers to computing programmes that replicate and simulate human intelligence, such as an individual's problem-solving capabilities or their capacity for learning. Moreover, machine learning can be considered as a subfield within the broader domain of artificial intelligence. The process automatically identifies and analyses patterns within unprocessed data. The objective of this work is to facilitate researchers in acquiring an extensive knowledge of machine learning and its utilisation within the healthcare domain. This research commences by providing a categorization of machine learning-based methodologies concerning healthcare. In accordance with the taxonomy, we have put forth, machine learning approaches in the healthcare domain are classified according to various factors. These factors include the methods employed for the process of preparing data for analysis, which includes activities such as data cleansing and data compression techniques. Additionally, the strategies for learning are utilised, such as reinforcement learning, semi-supervised learning, supervised learning, and unsupervised learning. are considered. Also, the evaluation approaches employed encompass simulation-based evaluation as well as evaluation of actual use in everyday situations. Lastly, the applications of these ML-based methods in medicine pertain towards diagnosis and treatment. Based on the classification we have put forward; we proceed to examine a selection of research that have been presented in the framework of machine learning applications within the healthcare domain. This review paper serves as a valuable resource for researchers seeking to gain familiarity with the latest research on ML applications concerning medicine. It aids towards the recognition for obstacles and limitations associated with ML in this domain, while also facilitating the identification of potential future research directions.