Demystifying Big Data and Machine Learning for Healthcare 1st Edition

Great primer for those of us who are new to the world of big data in the healthcare domain. I was curious as to how these powerful tools apply in a clinical setting and how they can impact research to improve individual patient treatment methods and outcomes. The book goes over how tools such as Hadoop and GPU chips are used, outlines concepts such as neural networks, and highlights the use of software delivery methods such as Agile are used to implement big data solutions. The case studies were especially interesting as they highlighted across payer and provider.

As an engineer in machine learning, this book seems to me that it addresses in a spectacular way all the dimensions to take into account in the construction of analytical solutions in health, there are many things that I have thought intuitively, but this book has allowed me to confirm some Of my hypothesis, I am very happy to have been able to read it, it has been very useful in my work and in my passion to improve in the area of health, a great congratulation to all those who made possible its creation and publication.

This is what exactly the doctor ordered for advanced analytics sphere. Without such lucidly written books, advanced analytics in healthcare is at risk from issues related to hype. I enjoyed the book and I am confident it will help me in my work with Analytics1.0/3.0 strategy in my career.

When you read the title, Demystifying Big Data and Machine Learning for Healthcare, you may laugh a little and think “good luck on that” …but that is exactly what this book has done. As someone who has been dealing with all the data in healthcare for over 20 years and all the systems collecting the data (from government agencies systems to a PCP EHR), speaking to my clients is never just clear cut. Reading and now using this book and the information it shares, has enabled me to have better conversations around healthcare data and yes, it has helped to demystify it. Thank you, Prashant Natarajan and all the authors of this book for delivering a great book that I would recommend to anyone still feeling a bit mystified by data, or just needing a little more information to help shape your organizations data strategy and plans.

Often in healthcare topics like AI and ML are not explained to us effectively and it is a big reason why new tech has a hard time incorporating well into healthcare. This book does a great job of introducing hard concepts and providing interesting case examples as to why AI is important and how it is actively being used every day

It is a collection of barely academic quality papers that do not give enough detail. Frameworks are proprietary and names are not mentioned, technology or results are not really discussed.

As someone who has been in IT and analytics for 35 years I was surprised to see a book available about 3 things I'm passionate about. It didn't disappoint. I loved reading the real world use cases just to understand HOW they went about getting to a point of value so that I didn't drive in the wrong direction. The book also goes through the importance of data quality which is essential in any environment, but especially for Machine Learning where the computer can't raise it's hand and say "something seems fishy about that value." My biggest take away was it's description of data "FIDELITY" which I had never heard of, but is so important for healthcare data especially. Whether you have been in the industry and have been burned before with projects that tanked, or are about to embark into this field you owe it to yourself to read these examples.

I currently work on the technical side of the Big Data space and did some research work in the clinical setting and could not put this book down once I started reading it! My favorite part is the real-life case studies that the authors go through. The authors sum things up pretty well that the key to any successful big data analytics project is having a strongly defined business use-case that can show some tangible ROI. And the use-cases that he goes through show exactly that. You won't find details about big data projects in the healthcare space like the ones in this book. The NRF Framework provides a great set of points for any data scientist or business user to think about before beginning a big data project. I'm definitely going to be using it with my internal and external customers. And don't fret if you aren't super well-versed in machine learning terminology. The author does a phenomenal job at providing the readers with a way of thinking about what kind of models are applied in different use-cases and what the tradeoffs of using those models are! Whether you are new to the healthcare analytics space or have been in the field for a while, you'll find your money's worth!