Fundamentals of Clinical Data Science - Book Review
With a stock pile of excellent books on health information and technology on my desk and electronically, I plan to review one book per week.
In only a few years, data science has become one of the most in-demand jobs in the world. Its application in healthcare, being even more recent, has created hype associated with artificial intelligence and machine learning. This book takes a real-world approach addressing the basics as well as the complexities of clinical data science. The editors and authors from Maastricht University in the Netherlands (Pieter Kubben, Michel Dumontier, and André Dekker) at times reflect a uniquely European perspective, such as, the chapter on GDPR. However, the bulk of the 200 page text provides a broadly applicable perspective on data management and analysis.
The first section of the book deals with data collection including sources, big data, data standards, research data and stewardship and data protection. Part 2 addresses modeling data using predictive modeling and time series. Predictive modeling makes up the core technique for data science using algorithms, machine learning and more complex techniques, such as, random forest and artificial neural networks. The final section details four applications of data science: clinical decision support systems, mobile apps, optimizing care processes and value-based care. Since the authors have focused on clinical data analysis, they do not address all areas of AI, for instance, chatbots (conversational AI).
The authors define data science through this vend diagram:
The book presents detailed explanations of advanced data models and so it meant as more than a text for novices. I would recommend it for data analysts who want to expand their knowledge of data science and also for graduate students in biostatistics or data science as an introductory text. As the importance of data science in healthcare becomes broadly acknowledged, particularly in predictive modeling, more healthcare professionals and data analyst will benefit from understanding this emerging field.
This book is available as an eBook or by downloading individual chapters.
?