Medical care is becoming increasingly personalized based on individual patient data. Data science is one enabler of this medical practice. For example, data science techniques are being integrated into healthcare applications, such as electronic medical record (EMR) information systems, to build predictive models based on useful information extracted from data. The application of data science to healthcare is now making it possible to provide personalized diagnosis of disease at an earlier stage and to monitor (remotely) patient health status. More than ever, COVID-19 has demonstrated the importance of data science in healthcare for an effective and efficient pandemic response.

This book seems to empower the reader to gradually embark on the development of medical applications incorporating data science. The book, obviously intended for health professionals, is divided into four parts. The first two parts are a collection of workshops on the use of data science in the healthcare system in general. The third part presents case studies of data projects, mainly in developing countries. The last part is a collection of results from data science projects presented by students. Parts 1, 2, and 4 can be classified as a textbook.

If one considers the content of each part from the perspective of health professionals--the primary audience--the first two parts, and in particular chapters 2 and 3, do not match the title of the book. Healthcare professionals are users of technology and systems and may not have the time to learn how to implement data science technologies. Instead, these first two parts are recommended for researchers and software developers working in (or looking to get into) data science in the medical field.

The third part of the book, which presents data science case studies, gives healthcare professionals insight into the benefits of applying data science in healthcare, but these reports are more interesting to scientists/researchers than to healthcare professionals. This is also true of Part 4. Assuming that this book is for beginners in data science or researchers who want to use data science techniques in their work, Parts 1, 2, and 4 can help such readers use data science and Part 3 could be considered appropriate for a literature review.

This book is well structured, written with a good level of linguistic guts, and could be recommended to data science students rather than researchers or health professionals. In addition to its weakness regarding the selection of an appropriate audience, I discovered some inconsistencies in the first part where some authors use “this article” instead of “this chapter,” indicating that some chapters in the book have been published elsewhere.