The courses included in the programme will address comparative effectiveness research, “the generation and synthesis of evidence that compares the benefits and harms of alternative methods to prevent, diagnose, treat, and monitor a clinical condition or to improve the delivery of care”.
Comparative Effectiveness Research courses (2025/26 programme)
| Module (UE) | Description | Lecturers |
|---|---|---|
| UE1 Upgrade in statistics and use of statistical software | Principles and interpretation of statistical tests, correlation, analysis of variance and covariance, linear regression, logistic regression, survival analysis, laws of probability, groups sequential testing and stopping rules. Introduction to R software, descriptive statistics with R, statistical tests, correlation, linear regression, analysis of variance and covariance with R, logistic regression with R, random variables, simulation and bootstrap. | Raphaël PORCHER - Céline Béji - Elodie PERRODEAU |
| UE2 part 1 Methods in randomised controlled trials I | General principles for the planning, conduct, analysis and reporting of randomized trials: principle of randomized trial, defining the research question (PICO, pragmatic/explanatory trial), choice of the outcome (metrology, composite outcome, surrogate markers), definition of response to treatment (MCID, PASS), biases, patient timeline, specific issues when assessing non-pharmacologic treatments, reporting guidelines (SPIRIT CONSORT) Statistical analysis: sample size calculation, handling of missing data, estimands, “typical” analysis of a randomised controlled trial, interim analyses, subgroup analyses | Mike CLARKE - Isabelle BOUTRON - Gabriel Baron |
| UE2 part 2 Methods in randomised controlled trials II | General principles, advantages and limitations of different experimental designs: non-inferiority/equivalence trial, cluster trial, cross over, factorial design, N of 1, split body design, platform trials, stepped wedge. Randomized RWE (trials embedded in RCD infrastructures). Decentralized and remote trials with RCD. Pragmatic trials with RCD. Learning care systems with digital tools. Analyse d’un essai randomisé : 10% de la note, travail individuel (en plus des 10% travail de groupe) | David TORGERSON - Lars HEMKENS - Antoine DUCLOS |
| UE3 Methods in systematic reviews and meta-analysis I | Methods of systematic reviews: development of the protocol, search and selection of studies, data extraction and assessment of risk of bias, GRADE, reporting guidelines. Meta-analysis: statistical analysis (combined estimation, heterogeneity evaluation, investigation of heterogeneity, reporting biases, use of software). Principle of IPD meta-analyses | Sally HOPEWELL - Lina EL CHALL - Sally YAACOUB |
| UE4 Methods in diagnostic tests, biomarkers, and screening evaluation | Methodological aspects of evaluating diagnostic tests and of biomarkers. Implementation and evaluation of screening | Patrick BOSSUYT - Jérémie COHEN |
| UE5 Methods of observational studies in CER | General principles of causal inference: counterfactual model, types of causal effects, and causal assumptions. Principles, theory and application of causal methods using regression (g-computation), propensity scores, inverse probability of treatment weighting, and instrumental variables. | Raphaël PORCHER - Els GOETGHEBEUR - Saskia LE CESSIE - Ingeborg WAERNBAUM |
| UE6 Target trial emulation and routinely collected data in CER | Methods of target trial emulation. | Viet-Thi TRAN |
| UE7 Methods in systematic reviews and meta-analysis II | Methods for systematic review and meta-analysis of diagnostic tests accuracy studies. Systematic review and meta-analysis of observational studies: challenges and benefits. Meta-analysis of non-standard designs (cross-over studies, cluster randomised studies). Missing data in meta-analysis: imputation methods and pattern mixture models. | Mariska LEEFLANG - Gerald GARTLEHNER - Joerg MEERPOHL |
| UE8 Network meta-analysis | Synthesis of multiple treatments: indirect and mixed comparison, network meta-analysis. Conceptual and statistical assumptions, different approaches for statistical synthesis, development of the protocol, critical appraisal of the results. Ranking of treatments: benefits and challenges. Discussion of published network meta-analysis and common mistakes in interpretation of the findings: reporting bias, heterogeneity and inconsistency, network structure and sparse networks. Software: R, CINeMA, NMAstudio. | Anna CHAIMANI - Dimitris MAVRIDIS |
| UE9 Personalised medicine | Principles and methods of the development of risk prediction models: study design, choice of a model, sample size considerations, handling of missing data, predictor selection, model specification, and model presentation. Principles and methods for the validation of risk prediction models: different kinds of validation, measures of performance (calibration, discrimination). Clinical trials for precision medicine: performance of a marker to guide treatment decision, individualised treatment effects, trial designs for personalised medicine (biomarker-strategy designs; umbrella, basket and platform trials; principles of adaptive designs; adaptive enrichment designs). | Gary COLLINS - Raphaël PORCHER |
| UE10 Internship | Late January - late July. |
Classes are full-time and will take place from mid/late October until mid-January (Monday to Friday, all day) with two weeks of holidays (detailed 2024/25 calendar here. The 2025/26 calendar is in the making). Exams are right after, followed by an internship. See the page “programme” for more details.