Week 3: Special Modules

The purpose of this course is to give an introduction to a number of statistical methods that we have found useful in epidemiology and that are often not part of standard courses. In each three-hour morning session (9.30-12.30), the first half will be a lecture on today’s topic to be followed by practicals using Stata. Inspiration to the coding to be used will be provided. After completion of the course, the students should be able to recognize situations where these methods could be used and to adapt the Stata code to do the analyses

• Competing risks
• Recurrent events and longitudinal data
• Cohort sampling
• Propensity score
• Causal modelling

In recent years several novel (to epidemiology) methods have been developed to explore causality and the idea that ‘triangulating’ results from different methods can provide more robust causal understanding is gaining traction. The idea of triangulation is that if different methods that all have very different key sources of bias point to the same causal answer we have more confidence that is the correct answer than if we just had information from one of those methods. Understanding these methods is important for all population health and clinical researchers and for practitioners who need to be able to understand new evidence to keep up to date.

In this course students will learn about Mendelian randomization (using genetic variants as instrumental variables), negative control studies, family-based analyses and cross-context comparisons. They will also learn about triangulating findings from these different methods and more conventional multivariable regression approaches to improve causal understanding.

The course will be taught with lectures, computer practicals (using Stata*), and group work.

*R scripts will also be provided

The aim is to introduce students to novel causal approaches and triangulation of evidence from different methods to improve causal understanding.

By the end of this module students should be able to:

1. Understand the principles and assumptions, strengths and limitations of each of the following methods:
   1. Cross-context comparisons;
   2. Negative control studies;
   3. Matched within sibship analyses;
   4. Mendelian randomization (genetic instrumental variables)
2. Understand the concepts behind sensitivity analyses to explore violation of key assumptions of each of these methods
3. Complete a (straight-forward) one-sample and two-sample MR analysis
4. Understand how different methods might be triangulated to improve causal inferenceThe module is suitable for anyone interested in epidemiological research aimed at improving causal understanding in relation to any disease or health related outcome. To get the most out of this course students need to
   1. have epidemiological understanding (e.g. how to define confounders, mediators and effect modifiers and the difference between causal effects and prediction/risk stratification)
   2. have experience of completing multivariable regression analyses and correctly interpreting the results from those analyses
   3. be able to use Stata or R statistical software.

   Students do not need advanced statistical knowledge; this is an introductory course aimed at providing students with overarching principles that will be valuable in future research and / or in understanding papers that use these methods.

   More information

The course on applied epidemiology is based on short lectures, group work and group discussion of case studies. We aim to review the methodological issues related to the epidemiologic study of the health consequences of exposures that are involuntary and that occur in the general environments (from cities to global, from individuals to in/outdoors and from physical to social). We cover designs, exposure measurement, co-exposures, modelisation, air pollution, built environment, climate change, exposome, child development, and impact assessment.

• Epidemiological designs for short temr exposures
• Exposome
• Child development
• Built environment
• Risk and impact assessment

Epidemiology is a core science to investigate and quantify the association between risk factors and health outcomes. However, public health professionals and policy makers need to understand the public health relevance of risks to plan and prioritize prevention and policy making. The epidemiology-based assessment of the risk related burden of disease provides a bridge between public health science and policy. This course will familiarize students with the use of epidemiology in quantitative risk assessment and the comparison across risks. Based on a range of examples, students will i) learn how epidemiology contributes to quantitative risk assessment, ii) understand the concepts and tools to assess the health burden and iii) critically interpret the derived outputs. Exercises based on the burden of disease data will train critical thinking for the comparison of different public health risks.

Approach: Lectures on concepts, self-studies with on-line exercises and group discussions will foster the understanding of how epidemiology is used in risk assessment and burden of disease studies. Students are expected to bring their personal note books to independently work on line, on the web.

*This course is available both face-to-face and (simultaneously) online

More information

Modern medicine relies on lab tests, imaging, and other forms of medical tests to find out more about the likely cause of a patient’s condition, to predict the future course of disease, or to select and monitor treatment. Like other interventions in healthcare, medical tests should be thoroughly evaluated before they can be given access to the market, be reimbursed, and recommended in practice guidelines.

Unfortunately, the evaluation of medical tests has received far less attention than the methods for evaluating pharmaceuticals and other interventions. It is now always clear what the best approaches are for evaluating the clinical performance of medical tests, or the best strategies for estimating their clinical effectiveness. This absence has generated interesting methodological developments, while awareness is increasing among epidemiologists.

In this course, we will give an overview of current concepts and modern methods for evaluation medical tests. As guiding principle, we take the premise that decisions about tests are now based on the effect that they have on patient outcomes – clinical effectiveness – and that measures of the clinical performance of tests should be inform about the effectiveness.

The course will look specifically at a few purposes for medical testing: diagnosis, prognosis, treatment selection, and screening. We will distinguish between the scientific validity of medical tests, the technical and analytical performance, the clinical performance, and the clinical effectiveness and clinical utility.

We rely on a combination of online lectures and assignments, with background reading material. Sessions will be organized in Zoom, with online quizzes, and offline paper-and-pencil assignments.

*This course is available both face-to-face and (simultaneously) online

More information

1. Observational studies in epidemiology are susceptible to an array of biases due to confounding, misclassification and missing data that may threaten their validity. Often such problems are qualitatively discussed in papers, but to a lesser extent quantified. In this course we will demonstrate modern analytic techniques and epidemiological study designs that will enable course participants to quantify and deal with unobserved information in observational studies.   The course participants will be introduced to quantitative bias analysis, instrumental variable analysis, self-controlled study designs and multiple imputation.    
   • Quantitative bias analysis
   • Instrumental variable analysis
   • Self-controlled study design
   • Missing Data and Multiple Imputation part I
   • Missing Data and Multiple Imputation part II

This module presents to researchers, health professionals and clinicians particularly interested in prevention a perspective critically examining how the individualized and the population approaches, as a classically outlined by Geoffrey Rose in the 1980s, may represent useful concepts and operational principles in a time when on one side  the availability of massive health data on each person promotes a ‘precision prevention’ approach and on the other the Covid-19 pandemic makes population level interventions mandatory. Each of the four days will be focused on a main theme : 1.Concepts. 2. Prediction 3. Choices 4. Questions. Relevant methodological aspects will be reviewed, including an introductory presentation of causal versus predictive models and of machine learning instruments. Specific ethical issues that prevention research and measures raise will be sketched for discussion.

Approach: lectures, reading of papers with critical discussion and ‘pros and cons’ arguments.

Infectious disease are closely integrated with human existence. Progress in the understanding of infectious disease epidemiology over the past few centuries, have basically transformed human societies. Vaccines, antibiotics and hygiene measures have played an important role in the fight against infectious diseases in the past, however, infectious diseases remain important aspects of everyday life both in high and low income countries. Worldwide inequalities in accessing health care including treatments and vaccines, re-emergence of vaccine preventable diseases, and the threat of antimicrobial resistance underline the fact that infectious diseases remain a global public health challenge. The COVID-19 pandemic has put the ever present risk of new emerging pathogens high on the agenda and shown how a new infectious disease may pose severe clinical and public health problems and also have vast societal, economic  and political consequences.

This course will introduce the epidemiological fields of transmissibility, vaccinology, disease surveillance and outbreak investigations. We will use the current COVID-19 pandemic in addition to other diseases and recent outbreaks as examples in the course.

The purpose of this course is to give an introduction to the field of infectious disease epidemiology. We will try to describe what sets this field apart from classical epidemiology and stress the applied aspects of the discipline (the ’field epidemiology’ aspects). We are both working at a national public health institute and in our daily work use epidemiology for disease surveillance, risk asessment and outbreak control – and we’ll discuss infectious disease epidemiology from this perspective.

By the end of this module, the student should be able to understand:

1. The terminology and definitions used in infectious disease epidemiology
2. Principles of disease transmission including a brief introduction to mathematical models for epidemics
3. Basic concepts of vaccinology
4. Principles of infectious disease surveillance and interpretation of surveillance data
5. The 10 steps of an outbreak investigation – with a focus on water/foodborne outbreaks
6. The use and interaction of microbiological and epidemiological methods in outbreak detection and control.
7. The use of epidemiological study designs in infectious disease epidemiology.

The course will use a mix of lectures and case studies. The course consists of four afternoon sessions, Mon-Thu, in the same week. Each session will contain two lectures and a longer case study. For the latter, relevant papers/material will be send round before the course.

It is helpful if students have basic prior knowledge of infectious diseases and of principles of epidemiology, including a basic knowledge of measures of frequency and associations and epidemiological study designs. The course will not cover mathematical concepts nor make use of statistical software.

More information