Program Description
Health Data Science is a rapidly evolving field that integrates informatics, machine learning, artificial intelligence (AI) and statistics to enable innovative approaches to analytics and health research. It is more important than ever to focus on what data science training in the health space can do for the growing AI industry, especially within precision medicine and predictive analytics.
To rise to this challenge, our program prepares learners to:
- Master the machine learning algorithms that power AI systems
- Integrate and wrangle large and disparate real world data sources including registries and electronic health records
- Build statistical and predictive models using SAS, R and Python
- Create effective data visualization tools and reports to power research and business decision-making
- Communicate statistical and data-driven findings to technical and non-technical audiences
- Provide data analytics leadership to support value-based care in health organizations
The Master of Science (MS) builds upon the foundation concepts presented in the Graduate Certificate and focuses on the advanced application of HDS concepts necessary for the applied practice of health data science in industry and research settings. This option contains 10 online courses and a capstone project, which is specifically designed to enhance the student's career trajectory. This option can be completed in two years.
Two track options allow students to focus their studies in HDS:
Management Track
The Research Track prepares learners to conduct research using data scientific methods either academically or as a part of an organization. Learners acquire competencies in statistics, data wrangling, data visualization, supervised, unsupervised and deep learning machine learning methods for work on real-world health data science projects, including AI-infused technology. Learners acquire expertise in SAS, R and Python, with no expectation of prior coding proficiency. The target audience includes learners who seek the technical expertise to lead health data science research efforts with providers, payers, employers, data vendors, consulting and governmental agencies.
Research Track
The Research Track prepares learners to conduct research using data scientific methods either academically or as a part of an organization. Learners acquire competencies in statistics, data wrangling, data visualization, supervised, unsupervised and deep learning machine learning methods for work on real-world health data science projects, including AI-infused technology. Learners acquire expertise in SAS, R and Python, with no expectation of prior coding proficiency. The target audience includes learners who seek the technical expertise to lead health data science research efforts with providers, payers, employers, data vendors, consulting and governmental agencies.
Learning Goals/Program Outcomes
The HDS program prepares graduates to be successful in the ever-changing healthcare environment that is driven by data and analytics by preparing them to:
Graduate Certificate
- Explores the vital roles of data, information, and information systems in the implementation and evaluation of healthcare and value-based care initiatives
- Provides a comprehensive overview of data science, the practice of obtaining, modeling and interpreting data
- Adopt data visualization techniques that contribute to effective presentations and dashboards
- Provides a foundation for population health beginning with a working definition, incorporating public health science and policy.
Master’s Degree (Above Plus)
All Tracks
- Evaluate and apply multivariate statistical methodologies for various study designs of efficiency and effectiveness in healthcare
Management Track
- Apply management and leadership skills to data-driven decision-making and learn to communicate with technical and non-technical audiences
- Manage HDS projects in real-world healthcare settings
- Addresses implementation science and presents a multidisciplinary framework and methodology to promote the integration of scientific evidence into healthcare practice, policy and research
Research Track
- Learn key programming techniques for data wrangling, statistical modeling and predictive analytics
- Learn advanced data science methods including supervised and unsupervised learning algorithms
- Conduct HDS research in real-world healthcare settings
Curriculum: Management Track, 33 credits
| Code | Title | Credits |
|---|---|---|
| Master of Science | ||
| AHE 501 | Economics of Health Insurance (or POP 500: Essentials of Population Health ) | 3 |
| AHE 502 | Statistics I | 3 |
| AHE 505 | Statistics II | 3 |
| AHE 509 | Epi & Evidnc Outcomes Research | 3 |
| HDS 501 | Health Inform, Analytics & AI | 3 |
| HDS 518 | Sup & Unsup Learn: Pred & Clas | 3 |
| HDS 532 | Data Visualization | 3 |
| HDS 538 | Implementation Science | 3 |
| HDS 527 | Analytics & AI Leadership | 3 |
| HDS 652 | Strat Capstone Portfolio&Pres | 3 |
| Elective in HDS or AHE (PD Approval) | 3 | |
| Total Credits | 33 | |
Curriculum: Research Track, 33 credits
| Code | Title | Credits |
|---|---|---|
| Master of Science | ||
| AHE 501 | Economics of Health Insurance (or POP 500: Essentials of Population Health ) | 3 |
| AHE 502 | Statistics I | 3 |
| AHE 505 | Statistics II | 3 |
| HDS 500 | Fundamentals of Data Wrangling | 3 |
| HDS 501 | Health Inform, Analytics & AI | 3 |
| HDS 502 | Exp Data Ana & Unsprvsd Learn | 3 |
| HDS 518 | Sup & Unsup Learn: Pred & Clas | 3 |
| HDS 519 | Deep Learning & AI Systems | 3 |
| HDS 532 | Data Visualization | 3 |
| Elective in HDS or AHE (PD Approval) | 3 | |
| HDS 651 | Capstone Research Project | 3 |
| Total Credits | 33 | |
Both tracks culminate in a Capstone, which incorporates knowledge and skills gained through the Master’s Program education. The Capstone should advance knowledge which can be applied to the student’s discipline and/or organization.