Digital Health & Data Analytics Curriculum

Semester 1

The Healthcare Ecosystem: Behind the Scenes

Digital health professionals operate within a complex, multi-faceted and ever evolving health ecosystem, that encompasses everything from the clinic to the legislature. Every decision can have immense impact. We will take you behind the scenes of healthcare and you will expand your knowledge of how healthcare works, exploring several models with a keen focus on how Canada’s healthcare system provides care and supports digitally enabled systems in comparison to other systems. You will learn the fundamental vocabulary and concepts that are foundational to understanding the national and international healthcare landscape.

Key topics include:

  • Structure and governance of Canada’s healthcare system: local, provincial, and national
  • Comparative healthcare systems
  • Population health, including social determinants of health
  • Indigenous healthcare
  • Public and private organizations
  • Health economics: funding sources, key performance indicators, and digital tools

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Digital Health I: Empowering People

Digital Health I explores the role of e-health and digital health within the healthcare system. You will examine the critical importance of digital health and its emerging and dominant role in building a healthier world for all. According to Health Information Management System Society (HIMSS), digital health connects and empowers people to manage health and wellness and through this course, you will understand the key concepts and the practical and pragmatic knowledge and experience required to work within digital healthcare ecosystems. You will acquire key knowledge, skills and attitudes critical for implementing and optimizing flexible and interoperable digital tools, technologies and services that empower patients, providers and the community to manage health and build a healthier world for all.

Key topics include:

  • Definitions and frameworks for digital health
  • Health Information Systems
  • Interoperability and Collaborative Tools
  • Patient Safety and Digital Health
  • Mobile Health and Applications
  • Transformative capabilities of Digital Health
  • TeleHealth and Virtual Care at the Webside
  • Consumer and Public Digital Health
  • Human Factors

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Data Science and Analytics I

Digital health professionals require high quality, timely, relevant, clean data to support effective clinical decision making and diagnostics. The data need to be presented clearly using strategically merged, transformed datasets and entered into models to address research questions. You will learn the fundamentals of effective data collection, data definitions, data cleaning, and management, using current technologies and data standard practices. The course will explore a variety of structured and unstructured data types, including both clinical and patient-provided that are required to improve health and personalize health care. You will also become familiar with the basics of databases, managing data and building modern and safe data storage systems. The course will introduce concepts related to big data, machine learning, and predictive analytics.

You will be able to put into practice essential concepts of data collection, management and processing including visualization, as well as effective data communication tools and techniques to support a data driven and data enabled healthcare environment.

Key topics include:

  • Differences among big / high-dimensional data, large cohort study data, and smaller project data
  • Basics of clinical study designs, their level of evidence, and ways to extract information from and appraise health literature using the PICOTS system
  • Structured and unstructured quantitative and qualitative data types including both clinical and patient- reported outcomes
  • Fundamentals of effective data collection, data definitions / dictionaries, data governance
  • Basics of case report forms, database creation, managing data and building modern and safe data storage systems
  • Methods for data cleaning, data merging, data transformations, and management using current software (packages) (R, SAS, Python)
  • Distinguishing among exposures, outcomes, confounders, mediators, colliders
  • Concepts related to big data, machine learning, predictive analytics and computational power
  • Practical examples of how to log into and use a cloud computing platform
  • Visualization and effective ways to present data and analysis results (SAS, R, Python, Tableau)

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Semester 2

Digital Health II: Building Systems

Digital Health relies on dynamic, robust and adaptive systems to provide high quality care. Digital Health II is a survey course where you will  build on the key fundamental knowledge from Digital Health I, examining the social, ethical, financial, and systems issues that shape the experience of digital health at the systems level. Using contemporary case studies to highlight the potentials, perils, and pitfalls of digital health transformation, you will explore issues related to population health, privacy, cybersecurity, and governance. You will also examine issues related to using digital health to address social and ethical issues, such as equity, diversity and access to care for all.  You will also examine issues related to building responsive and adaptive digital health systems that connect communities together for integrated and coordinated care. In addition, you will hear from a diverse selection of experts in health policy, research, administration, industry, and evaluation, and will be exposed to potential areas for future study, work placement, and capstone projects.

Key topics include:

  • Big Data and Population Health
  • Privacy, Cybersecurity and Governance
  • Inclusion, Diversity, Equity and Accessibility in Digital Health
  • Canada Health Infoway and eHealth Ontario: One Record to Rule Them All?
  • COVID-19 and the Digital Transformation
  • Community Care and the Digital Divide
  • Transforming Quality and Safety with Digital Image Peer Review
  • Global Digital Health in Low and Middle Income Countries

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Artificial Intelligence and Machine Learning I

AI and ML are rapidly changing every aspect and dimension of the health system and, in fact, some say, will change healthcare as we know it. You will explore the power and limits of artificial intelligence and will provide practical skills and experience with AI applications that are currently enhancing healthcare. Building from concepts around clinical decision making and decision support, you will work with a wide range AI applications from robots to Chatbots to machine learning techniques and data-driven tools that predict and change health and wellness. You will understand the evolution of AI and explore concepts and models required for learning how to apply AI. The course will also consider the social and economic implications of AI looking critically at bias, ethics, as well as the impact on diverse communities and the accessibility of healthcare for even the most vulnerable populations. The AI and ML I focuses on the key concepts and principles rather than programming or engineering implementation of AI.

Key topics include:

  • Relevant history of AI/ ML, and most common AI/ML terminology and definitions.
  • How AI/ML are transforming healthcare and medicine; new skills and knowledge required.
  • Refresh of data and statistics fundamentals
  • Supervised ML: distinguishing the difference between descriptive and predictive modelling process, forecasting, classification, decision trees; generalizable supervised ML work flow, ways of evaluating and enhancing supervised ML algorithms. Examples of applying these algorithms to solve healthcare problems.
  • Unsupervised ML: knowledge discovery, learning patterns, reduction techniques, clustering (K-means, hierarchical), data-preprocessing steps, dimension reduction algorithms, and visualization tools to inform decision. Examples of applying these algorithms to solve healthcare problems.
  • Natural Language Processing: overview of text data mining and processing, sources of textual information; text data preprocessing steps, main NLP analyses types (classification, sentiment analysis, name-entity recognition). Examples of applying these algorithms to solve healthcare problems.
  • Deep Learning: overview of deep learning, deep learning versus conventional machine learning algorithms, comparison of deep learning libraries: Keras, Pytorch, and Tensorflow. Examples of applying these algorithms to solve healthcare problems.
  • Big data analytics: overview, efficient storage of big data, cloud computing, distributed computing, production machine learning pipelines. Big data programming models: map-reduce, dataflows, stream processing. Examples of applying these algorithms to solve healthcare problems.
  • Tools & technologies for implementing AI/ML: performance evaluation, explainability, ethical, legal and social issues of AI in healthcare, understand risk mitigation strategies, anonymization techniques, synthetic data.
  • Putting AI into practice and the future.

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Data Science and Analytics II

Using high quality data prepared using ETL and data mining methods as discussed in DHDS110, digital health professionals can follow the CRISP-DM plan to execute data analyses. The analytical considerations require input from the scientific team and clinicians to best inform the research question being studied, while considering the full impact of contextual variables. This course will delve into the full set of statistical and analytical methods described at the end of DHDS110 and go into detail regarding each type of analytical model’s utility, strengths, limitations, and appropriate adjustment for covariates. Execution of models will be demonstrated by multiple examples in each of SAS, R, and Python coding environments. Students will practice using and modifying syntax for each statistical model to suit their analytical needs as will be required in typical research environments. They will learn to interpret the model outputs and describe estimates in terms of units and contrasts. The course will also cover more advanced visualization graphics to illustrate relationships drawn in these statistical models. It will also detail methods for streamlining analyses and organizing outputs in a fully-automated fashion to save time and enable iterative model tweaking.

Key topics include:

  • Review of how each analytical method fits within different study designs
  • Description of data distribution and comparison to a standard
  • Comparison between two groups, more than two groups, with correlation between groups
  • Correlations, linear and logistic regression
  • Factorial and multivariable effects on outcomes
  • Model parameter estimation, uncertainty, optimization, model fit
  • Diagnostic thresholds, classification, diagnostic power and performance
  • Prediction and time-to-event / survival analyses
  • Health economics analysis – QALY, ICER and INB
  • Internal validation and missing data handling
  • Visualization methods matching each analytical approach
  • Analysis output streamlining and tabulation

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Semester 3

Fundamentals of Implementation Science

Change and helping people change is incredibly difficult and this is particularity true in healthcare where it often takes and decade or more for good science and practice to reach our patients and our communities. Fortunately, there is a discipline to help us: implementation science. You will learn the fundamentals of implementation beginning with clearly identifying the problem, putting together a clear plan based on the best available evidence, managing the change with appropriate tool and processes, and working with key stakeholders to make that change a reality. Making the change is hard, but maintaining and sustaining change is even more challenging. You will acquire the skills to ensure that change is measured and sustained over a long period of time to ensure the best care is in practice.

Key topics include:

  • Understanding Critical and Wicked Problems
  • Engaging Stakeholders and Building Effective Relationships
  • Using Evidence to Inform Practice
  • Assessing the Environment
  • Managing Projects Effectively
  • Delivering on Time and on Budget

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Design Thinking and Quality Improvement

Designing change and continually improving that change on a human scale in healthcare is complex. There are practical and pragmatic approaches to achieving this change that work. You will learn to find solutions that are desired by your stakeholders, viable within the context that you are working in and feasible with the resources at hand. You will learn to deploy quickly, change continuously and evolve practice rapidly. You will learn key concepts, tools and processes related to design thinking, human factors and quality improvement, including human centred design and lean methodologies.

Key topics include:

  • Engaging and Involving Stakeholders in Framing the Problem
  • Inspiring through Clear Vision
  • Co-Creation and Co-Design with End Users
  • Human Factors and User-Centred Design
  • Generating Impactful Ideas
  • Rapid Prototyping for Progress
  • PDSA and Rapid testing cycles
  • Improving with Data
  • Sharing Success for Continuous Change

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Artificial Intelligence and Machine Learning II

This course will build on your knowledge from DHAI120 – Artificial Intelligence and Machine Learning I. You will continue to learn and build your knowledge on advanced topics in machine learning with more focus on applied machine learning. In this course you will learn more specific details on data preprocessing and exploratory data analysis required in any machine learning project. You will get hands-on exposure of model training and evaluation in Python programing language. We will cover many examples from industry (both healthcare and outside of healthcare for broader perspective). This course will also introduce you to a new area that you haven’t seen before in this program i.e., Natural Language Processing. We will talk about the key tasks in NLP and look at the state-of-the-art language models such as GPT-3. Finally, we will finish this course by building some understanding of Big Data Landscape.

Key topics include:

  • Machine Learning and types of ML
  • Exploratory Data Analysis in Python and automated frameworks
  • Data preprocessing required for model training
  • Model training and selection in Python
  • Model analysis and interpretation of results.
  • Key concepts in ML (overfitting, bias, validation, hyperparameter tuning)
  • Natural Language Processing and key tasks of NLP
  • Big Data Landscape

Semester 4

Advanced Topics in Implementation Science

Making the change in a complex system like healthcare is hard, but maintaining and sustaining change is even more challenging. Building on the critical skills and knowledge you have acquired through Implementation Science, you will acquire the skills to ensure that change is measured and sustained over a long period of time to ensure the best care is realized in practice.

Key topics include:

  • Building Change and Programs to Last
  • Understanding the Logic and Theory of Change
  • Developing Key Performance Indicators
  • Assessing and Evaluating Change
  • Communicating the Impact of Change
  • Disseminating New Knowledge

This course will be delivered online using a combination of lectures, independent readings, and seminars.

Applied Project

You will develop a project that will showcase the advanced knowledge and skills that you have acquired during the program. Your project will form an invaluable piece of your professional portfolio that you can use to demonstrate to potential employers in the field that you are ready to be part of a high performing digital health team. You will focus on one of the primary program streams of artificial intelligence, machine learning, robotics, or data science. You will apply your skills in design thinking and implementation science to maximize potential impact to the healthcare system, while ensuring feasibility and facilitating robust evaluation.

Sample projects include:

  • Development of a dashboard to track patient and staff vaccination rates
  • Integration of data from various health information databases to support clinical decision making
  • Development of an evaluation strategy for a new technology, process, or policy
  • Application of machine learning to predict patterns in community disease spread
  • Development of an AI chat bot to support essential service triage

You will receive mentorship and feedback from experts in your chosen subject area.

Semester 5

Practicum I

You will be placed within a healthcare organization that has an active machine learning, artificial intelligence, robotics, or data science project. You will apply the knowledge, skills, and judgement that you have acquired through the program to date to embed yourself within a team of digital health professionals. This first of two practicums will be an opportunity for you to not only demonstrate what you have learned, but also to get feedback from industry professionals on how you can improve and eventually become employed in your chosen field.

If you are already employed at an organization that has a digital health project that you could contribute to, you may choose to complete your practicum at your workplace. We will work with your organization to ensure that you receive the challenge and feedback that you need to advance your skills.

This practicum will be taken full-time, 35 hours per week over 15 weeks.

Special Topics in Professional Development

During your practicum you will connect on a weekly basis with your Michener faculty and the rest of your class cohort who are in placements to reflect on your progress, set goals for the rest of the placement, and discuss topics relevant to professional growth in the field of AI, machine learning, data science and robotics. You will participate in a professional learning community that will help you constructively integrate the feedback you receive from your practicum leaders, as well as giving you an opportunity to refine your skills in teamwork and communication.

Finally, guest lectures from industry professionals will give you valuable insights into the emerging trends and workplace dynamics of your chosen field. Guest lectures will be tailored as much as possible to the development needs of your cohort.

Sample guest lecture topics include:

  • Workplace culture and the “hidden” skills of career success
  • Professional communication and relationship management
  • Leadership and followership
  • Conflict management
  • Emerging trends in AI, machine learning, data science and robotics
  • Equity, diversity and inclusion in the workplace

Semester 6

Practicum II

For your second practicum you will have the choice of either continuing with your first placement and becoming more central to the team’s projects, or switching focus and beginning a new placement. Regardless of your path, this practicum will be an opportunity to further develop your skills and demonstrate your readiness for employment in your chosen stream. You will continue to receive feedback from leaders on your placement team as you work together to refine your professional development goals.

As with the first practicum, if you are already employed at an organization that has a digital health project that you could contribute to, you may choose to complete your practicum at your workplace.

This practicum will be taken full-time, 35 hours per week over 15 weeks.

Special Topics in Professional Development (cont.)

During your practicum you will connect on a weekly basis with your Michener faculty and the rest of your class cohort who are in placements to reflect on your progress, set goals for the rest of the placement, and discuss topics relevant to professional growth in the field of AI, machine learning, data science and robotics. You will participate in a professional learning community that will help you constructively integrate the feedback you receive from your practicum leaders, as well as giving you an opportunity to refine your skills in teamwork and communication.

Finally, guest lectures from industry professionals will give you valuable insights into the emerging trends and workplace dynamics of your chosen field. Guest lectures will be tailored as much as possible to the development needs of your cohort.

Sample guest lecture topics include:

  • Workplace culture and the “hidden” skills of career success
  • Professional communication and relationship management
  • Leadership and followership
  • Conflict management
  • Emerging trends in AI, machine learning, data science and robotics
  • Equity, diversity and inclusion in the workplace

This course will be delivered online using a seminar format.