Название: Machine Learning and Deep Learning in Medical Data Analytics and Healthcare Applications
Автор: Om Prakash Jena, Bharat Bhushan, Utku Kose
Издательство: CRC Press
Год: 2022
Страниц: 292
Язык: английский
Формат: pdf (true)
Размер: 14.3 MB

Machine Learning and Deep Learning in Medical Data Analytics and Healthcare Applications introduces and explores a variety of schemes designed to empower, enhance, and represent multi-institutional and multi-disciplinary Machine Learning (ML) and Deep Learning (DL) research in healthcare paradigms. Serving as a unique compendium of existing and emerging ML/DL paradigms for the healthcare sector, this book demonstrates the depth, breadth, complexity, and diversity of this multi-disciplinary area. It provides a comprehensive overview of ML/DL algorithms and explores the related use cases in enterprises such as computer-aided medical diagnostics, drug discovery and development, medical imaging, automation, robotic surgery, electronic smart records creation, outbreak prediction, medical image analysis, and radiation treatments.

The most astonishing difference between computers and humans lies in the fact that computers need to be programmed in order to respond to any event whereas humans learn from their past experience. However, with the advent of Machine Learning (ML) and Deep Learning (DL), it is possible for computers to learn from their experiences. Recent advances in ML/DL algorithms are impervious to large-scale technological disruptions and have transformed numerous industries such as governance, transportation, manufacturing, and healthcare. These techniques have shown tremendous results in varied healthcare-related tasks such as brain tumor segmentation, medical image reconstruction, lung nodule detection, classification of lung diseases, and medical image recognition. Furthermore, the exponentially growing volume of bio-medical Big Data generated due to health data collection through digital health wearables, genomic sequencing, and electronic health records (EHRs) is another matter of concern. ML/DL schemes have a proven ability to extract actionable knowledge from these large health datasets. ML models can also contribute toward improving the quality of care, enhancing patient safety, and mitigating the overall healthcare costs.

Extraction of appropriate data would be extremely beneficial in resolving serious medical conditions to a significant extent. ML/DL approaches can be used to extract certain attributes, and the trained model can be used to make proper diagnoses and prognoses from available medical data and photographs. These can also ease the identification of high-risk patients, early detection of lung cancer, detection of abusive and fraudulent health insurance claims, and diagnosis of respiratory ailments from chest X-rays. ML and big data strategies are used to build predictive diagnostic systems on collected data. However, designing and implementing an effective diagnostic system remains a difficult task due to a variety of issues such as stability, accessibility, scalability, safety, development standards, and technologies. This book covers the fundamentals of ML and DL in the healthcare domain where these models are used to train the system and implicitly extract positive solutions.

The main aim of this book is to highlight the role of ML/DL algorithms in improved healthcare diagnostic systems, processing EHRs, medical signal analysis, and consequently enhance the overall quality of life by enhancing disease diagnosis and life expectancy. Further, this book endows varied communities with its innovative advances in theory, modeling, statistical analysis, analytical approaches, analytical results, numerical simulation, computational structuring, and case studies related to applications of ML/DL models in the healthcare domain.