Jena O Machine Learning And Deep Learning Of Healthcare Systems 2022

Textbook in PDF format

Rapid population growth coupled with the evolution of numerous diseases is a matter of concern worldwide. Due to this, the healthcare industry has emerged as an essential service sector. The generation of a large amount of healthcare data and the lack of insight from that data are significant problems in the healthcare sector. Therefore, there is a need for a fully effective and automated system that can help medical stakeholders to take prompt action at the right time. Artificial intelligence (AI) and machine learning (ML) have a very long association with the healthcare sector dating back to 1980s. It gained momentum with the emergence of rule-based systems, hierarchical clustering, and various regression models. ML is an important utility of AI that provides systems with the capacity to automatically examine and enhance action without being specially programmed. However, neither the computers nor the algorithms were efficient enough to enable effective ML based systems. The last five years had seen tremendous rise in the adoption of ML techniques mainly due to emergence of neural network that enhanced the overall computational power. Deep Learning (DL) is a subset of ML where innovations have led to the construction of several novel deep neural network architectures that can be used for the classification of large data sets. AI, ML, and DL techniques can be employed for efficient knowledge discovery from healthcare data. These techniques have shown tremendous results in huge range of tasks such as brain tumor segmentation, medical image reconstruction, lung nodule detection, classification of intestinal diseases, organ recognition.
Further, ML/DL models have also achieved significant performances in the realm of clinical medicine, radiology, clinical pathology, dermatology, and ophthalmology. It is expected that such models along with intelligent software will revolutionize the medical research and even assist physicians and radiologists in patient examination in the near future. This book aims to integrate several aspects of computational intelligence like ML and DL techniques from diversified healthcare perspectives. This book describes the fundamental concepts of ML and DL techniques and its applications in the healthcare domain. Further, the book is aimed to endow different communities with their innovative advances in theory, analytical approaches, numerical simulation, statistical analysis, case studies, analytical results, computational structuring, and other significant progresses in the healthcare sector