Datascience in Healthcare
Full course description
The ability to manipulate and understand health-data is increasingly critical to discoveriesand innovations in healthcare. Data science is an emerging field that focuses on theprocesses and systems that enable us to extract knowledge or insight from data invarious forms and to translate it into action. With techniques such as machine learningand artificial intelligence being used for prevention of diseases, defining patient profilesand treatment interventions, Data Science plays an increasingly important role in healthscience.The Data Science in this DTZ module covers novel tools, methods and best practices of adata science project. The module is designed around the data science life-cycle and thetechniques and challenges into handling data analysis and management in healthcare.Students will gain knowledge on how to formulate a data research question and identifythe right dataset and methods needed to answer it. Students will become familiar withbasic data analysis algorithms, and will be able to visualize and interpret the results withregard to the data question/hypothesis. The module teaches basic programming skillsand how to apply them to perform the data science lifecycle: namely select, clean,analyze, visualize and interpret healthcare data. Each week, practical sessions will enablestudents to gain hands-on experience with data in healthcare topics.
Course objectives
Knowledge and insight
- differentiating the steps of the data science life cycle;
- formulating data research questions and identifying the right dataset and methods needed to answer these;
- knowledge of how basic data analysis and machine learning algorithms work;
- knowledge of the ways in which algorithms are validated and conclusions are drawn with regard to questions/hypotheses.
Application of knowledge and understanding
- interpret the validity of the findings;
- apply visualization techniques to gain insight into the data and the models;
- identify hypotheses in a dataset;
- use a programming language to define models which test questions and
- apply the right methods within each step of the data science life cycle
Forming opinions
- critically evaluate data science applications for use in the healthcare domain;
- perform critical thinking by discussing given literature and case studies;
- learn to use and extend their knowledge with respect to realistic data science problems
Specific attention will be paid to the communication skills needed to form a bridge-building professionals. By hosting specific meetings to present their knowledge, students will improve their communication skills as well as their professional attitude.The module is designed to enable interaction, feedback, and teamwork.
Recommended reading
Fundamentals of Clinical Data Science, Editors: P.Kubben, M.Dumontier, A.Dekker, (Downloadable for free here http://www.clinicaldatasciencebook.com/ ) ❏ Book: Jake Vanderplas Python Data Science Handbook | Python Data Science Handbook (Downloadable for free here jakevdp.github.io/PythonDataScienceHandbook/) ❏ Book: Data Science from Scratch - Joel Grus, second edition, Publisher(s): O'Reilly Media, Inc. SBN: 9781492041122 (we use very few chapters of this book) ❏ Additional state of the art readings are included and specified in the student portal ❏ The lecture slides and recordings will be shared via the student portal