Machine Learning for Healthcare Analytics: A complete handbook on Machine Learning for healthcare data scientists

Learn foundational concepts of machine learning for healthcare analytics and apply them to different domains in healthcare Key Features Build foundational concepts of statistics and ML for healthcare analytics Learn traditional ML algorithms as well as modern deep learning algorithms applied to healthcare Learn how ML is applied to traditional healthcare analytics involving cross-sectional and longitudinal data, biosignals, medical imaging and omics Discover emerging topics on ML applied to clinical NLP, digital biomarkers and multimodal data analysis Familiarise with ethical and regulatory topics for ML applications Book DescriptionHealthcare analytics is an immensely complex topic. It is characterised by a diversity in domain, data, challenges and analysis techniques. Application of machine learning for healthcare analytics adds another layer of complexity as one also requires a solid foundation on ML concepts. Finally, one also needs to consider ethical and regulatory aspects to build successful ML applications. This book demystifies this complexity by organizing the topics in healthcare analytics using a clear chapter layout. Once you have built up the basics, you will learn about how ML is applied traditional healthcare analytics problems involving cross-sectional and longitudinal clinical data. Then you will be introduced to the exciting world ML applications in biomedical signal processing, medical imaging and omics analysis. By the end of this book, you will be equipped with the know how to develop ML applications in any domain within healthcare.What you will learn Learn basic statistics for healthcare analytics Get introduced to deep learning model architectures Discover ML applications for cross-sectional and longitudinal data analysis Discover ML applications for biomedical signals processing, medical imaging and omics Learn about upcoming fields such as clinical NLP, digital biomarkers, and multi-modal data analysis Familarise with practical, ethical and regulatory considerations around ML applications Who this book is forIf you are a beginner who is looking to get introduced to the fascinating world of healthcare analytics, a researcher who wants to learn a new ML technique to derive insights from your biological data, or an experienced data scientist who is looking to refresh foundational concepts or gearing up to start a project in a new healthcare domain, then this book is just for you. Some familiarity with statistics, and ML, as well as experience in analysing biomedical dataset will certainly help you to get the most out of this book.

Table of Contents:
Table of Contents Product Information Document Introduction to healthcare analytics Foundational biostatistics Essential concepts in machine learning Introduction to healthcare data Disease diagnosis, prognosis and characterization Treatment effect estimation Survival analysis and event prediction Biomedical signals processing Medical image analysis using machine learning Data clustering Protein structure prediction Drug discovery Biomedical natural language processing Remote sensor data analytics Imaging + genomics Explainability and bias analysis Designing a clinical validation study Privacy and data anonymization techniques Regulatory requirements of ML-based software Future of healthcare analytics