Affiliation:
1. Lloyd Institute of Engineering and Technology, Greater Noida, India
2. Galgotias University, India
3. G.L. Bajaj Institute of Technology and Management, India
Abstract
The rapid development in the field of medicine and healthcare in the recent years initiated as a large volumes of data are gathered. Taking this advancement, there is a requirement of the process and system needs both technological and analysis methods are to be used to deal with these data. The data which are gathered is health data which are accumulated electronically on the basis of patients' readings, texts, speeches or images as per convenience. The study of models that computer systems use to self-learn instructions based on the weight of parameters without being given explicit instructions is clearly one way to achieve artificial intelligence (AI). Over the past ten years, there has been a noticeable increase in the optimisation of machine learning algorithms and tools in tandem with advances in biomedicine. One of the more intriguing tools of these algorithms that is becoming increasingly important is deep learning. It's an artificial neural network that uses computer design to create multi-layered models that learn several degrees of abstraction from data representations. Deep learning is receiving a lot of attention these days since a lot of research indicates that it may be superior to earlier algorithms that relied just on machine learning and that its results have greater predictive performance. Deep learning has special and broad applications in health informatics and biomedicine, given its many levels of representation and outcomes that outperform human accuracy. In particular, these fall under the umbrella of molecular diagnostics, which includes the interpretation of experimental data involving gene splicing and DNA sequencing, protein structure prediction and classification, biomedical imaging, pharmacogenomics and pathogenic variant identification, drug discovery, and more. This chapter's only goal is to showcase these applications and go into further detail about how they are helping to advance healthcare and medicine in the contemporary world. Deep learning algorithms have enhanced capabilities for identifying patterns and obtaining features from intricate datasets. This chapter will first introduce deep learning and the latest advancements in artificial neural networks. It will then go over its applications in the healthcare industry and, lastly, how they are being used in biomedical informatics and computational biology-related public health research. Furthermore, the applicability of deep learning algorithms would be emphasised from the standpoint of contemporary healthcare.