Course Introduction to Machine Learning for Health Research

ECTS: 4.1

Course leader: Oleguer Plana-Ripoll

Language: English

Graduate school: Faculty of Health

Graduate program: ClinFO

Course fee: 4,920.00 DKK

Status: Course is open for application

Semester: Spring 2024

Application deadline: 15/04/2024

Cancellation deadline: 29/04/2024

Course type: Classroom teaching

Start date: 13/05/2024

Administrator: Thilde Møller Risgaard

The course 317/02 Introduction to Machine Learning for Health Research is being offered by the Graduate School of Health, Aarhus University, 2024.

Criteria for participation: University degree in medicine, dentistry, nursing, or Master’s degree in other fields and/or postgraduate research fellows (PhD students and research-year medical students).

Requirements for participation: It is recommended that students have basic prior knowledge in epidemiology and biostatistics, such as measures of association, study design, confounding and linear and logistic regression. In addition, the course will utilize R/R Studio software. Students will be given sample code and resources to supplement existing R skills. Ideally, students should have some exposure to R/R Studio prior to starting the course, but online materials will be distributed for those without previous experience.

Aim: This course will provide students with broad exposure to the elements of machine learning and its practical applications within epidemiologic research and practice. The course will combine didactic lectures with group discussions and programming exercises to ensure a balance of substantive knowledge and practical skills. Through this approach, students will learn to apply critical thinking techniques as they explore the opportunities and limitations of using machine learning within the context of epidemiology.

Learning outcomes: Students who successfully complete this course will be able to:

  • Discuss the scenarios where machine learning can or cannot enhance epidemiologic research and practice
  • Assess ethical dilemmas that may arise when data-driven tools (i.e. derived from patterns in data without human direction) are used for public health
  • List and describe various learning algorithms and approaches to evaluate their performance
  • Evaluate the appropriateness of using machine learning for specific research questions, using current examples from the scientific literature
  • Demonstrate ability to utilize analytic tools that promote reproducibility
  • Analyze public health data by applying learning algorithms and evaluating the resulting models
  • Compare different machine learning approaches to address common challenges in epidemiologic research

Workload: The full workload of the course is expected to be 56.25 hours

Content: Machine learning, broadly defined as analytic techniques that fit models algorithmically by adapting to patterns in data, is growing in use across many areas within public health and healthcare. Modern epidemiologists and health researchers may wonder how these methods complement the theoretically-grounded, causal inference approaches more common in our field. This course will explore the use of machine learning to advance their research and practice, while reflecting on some of the scientific and ethical considerations that arise from the use of data-driven techniques.

The course will begin by providing a general introduction to machine learning, its utility for epidemiologists and health researchers and the differences in predictive and explanatory modelling. Next, we will introduce unsupervised and supervised algorithms and the approaches used for their tuning and evaluation. The final sessions will focus on specific applications of machine learning within the field of epidemiology. All sessions will include clear examples from the scientific literature, discussions on ethical issues surrounding the use of machine learning and hands-on programming exercises in R/R Studio.

Instructors: Jeanette A. Stingone (Columbia University, New York)

Venue: Aarhus University, Aarhus

Participation in the course is without cost for:

Course dates:

  • 13 May 2024 08:30 - 15:30
  • 14 May 2024 08:30 - 15:30
  • 15 May 2024 08:30 - 15:30
  • 16 May 2024 08:30 - 15:30
  • 17 May 2024 08:30 - 15:30