ABSTRACT
The rise of diseases has affected the national healthcare system and economy. People have recently faced the problem of the COVID-19 virus. Today, healthcare applications have been suggested to meet the needs of the public due to the improvement in chip processing power, growth in data size, and advancements in deep learning research. Additionally, daily data production is significant. Image data can now be accessed because of advancements in the Internet of Things, technology, and mobile devices. Applications based on deep learning techniques are used to support the healthcare system to diagnose, forecast, or treat patients. Data such as images, video, audio, and text are used as input. This chapter focuses on an overview of suggested healthcare solutions based on deep learning algorithms. This advancement might speed up the creation and use of several deep learning-based medical applications. Front-line healthcare facilities are implementing a small number of real-world applications, though. This chapter examines the state of the art in deep learning in the medical field. It serves as a review and aims to categorically cover a number of commonly used deep learning algorithms, along with their architectures and practical applications: back propagation, autoencoders, variational autoencoders, restricted Boltzmann machines, deep belief networks, convolutional neural networks, recurrent neural networks, generative adversarial networks, CapsNets, transformers, embeddings from language models, and bidirectional encoder representations from transformers, This study explores the benefits and drawbacks of deep learning algorithms, as well as the applications of these techniques in the field of healthcare and the path that this field is likely to go in the future.
