Diploma - Health Data Science & Biostatistics
Why the Health Data Science & Biostatistics Curriculum?
This specialization will provide the skills necessary to advance precision medicine and precision public health. You will learn how to use various modern analytic techniques including machine learning, natural language processing and data visualization and how to apply these skills in the fast-paced world of medicine.
Possible career paths
Graduates with a diploma in the Health Data Science & Biostatistics Specialization will work as data scientists in the areas of animal and human health.
Career opportunities include working as an analyst within the health care system working with large administrative health databases or developing algorithms to identify serious health conditions such as atrial fibrillation from wearable devices. Health data scientists are at the cutting edge of medicine using the vast amount of data produced on a daily basis to improve the lives of Canadians.
Certificate courses
Once students have completed the certificate's four courses (DATA 601, 602, 603 and 604) they are able to enter the diploma program, with a specialization in Health Data Science & Biostatistics, and complete the following courses:
An introduction to the fundamental statistical methods used in health data science including interpretation and communicating the results of these methods. Explores modelling using an epidemiological paradigm such as the assessment for modification and confounding. Introduces fundamental health research methods including study design and the evidence hierarchy. The following statistical methods will be examined under this paradigm:
- Generalized linear models
- Survival analysis
- Longitudinal data analysis
- Causal inference
An introduction to the application of machine learning methods to problems in health data. The concepts of precision medicine and precision public health are introduced and the role of data science in these endeavors is explored. Using real examples from health data, various contemporary machine learning techniques are taught.
Routinely collected health data form the foundation for this course. Increasingly, clinical care generates vast amounts of health data that is largely untapped for routine reporting, surveillance, clinical research, and for informing policy. Many of the major health data assets that exist in Alberta and Canada will be explored through hands-on experience with several datasets. Issues relating to access, confidentiality, privacy and data stewardship will be examined. Methodological challenges related to data linkage will be discussed. Examples of the types of data that will be explored include DAD, NACRS/AACRS, EMR/HER, PIN, Blue Cross, Social databases, and “Omics” data.
Increasingly, data visualization is being recognized as an important modality for conveying information to a wide audience. The synthesis and summary of large volumes of information into interpretable and compelling results will be explored. Various software packages useful for visualization data will be examined including software for geographic information systems, augmented reality and infographics. Data Science software commonly used in the health industry will be examined. Fundamental design principles will be introduced to guide the approach to data presentation, communication, and interpretation.
Do you have a question? Check out the FAQs