Juste Goungounga

Lecturer-researcher (Associate prof.)

Ecole des Hautes Etudes en Santé Publique

ERL Inserm U 1309 - Recherche sur les services et le management en santé (RSMS)

Arènes (UMR 6051 Arènes)

Biography

Juste GOUNGOUNGA is an Associate Professor of Biostatistics and Health Data Science at the Ecole des Hautes Etudes en Santé Publique ( EHESP) and a researcher at the ARENES Laboratory (UMR CNRS 6051), affiliated with the INSERM U1309 team on “Research on Health Services and Management in Health” (RSMS). He has held this position since October 2022.

At EHESP, Dr. GOUNGOUNGA teaches courses on various topics, including French hospital discharge databases ( PMSI), and supervises students. He is also a member of the CENSUR working survival group. His research specializes in statistical methods for epidemiology, particularly non-communicable diseases like cancer, with a focus on identifying and quantifying health inequalities.

He received his medical degree from the University of Ouagadougou in 2012 and transitioned from clinical practice to biostatistics. He completed a Master’s in Public Health, specializing in quantitative and econometric methods for health research, and a Ph.D. in Clinical Research and Public Health with a focus on biostatistics from the University of Aix-Marseille in 2018. His Ph.D. thesis contributed to the extension of relative survival methods in the field of clinical research. While with the Joint Research Unit 1252 SESSTIM (Inserm / IRD / Aix Marseille Université), Dr. GOUNGOUNGA developed the xhaz R package for excess hazard modeling with inappropriate mortality rates. In January 2020, he joined the Burgundy Digestive Cancer Registry/University of Burgundy ( EPICAD team - UMR 1231) as a postdoctoral researcher, supported by the ARC Foundation for Cancer Research. His postdoctoral research focused on estimating time-to-cure for cancer patients, considering disparities in credit and insurance access.

His current research explores inequalities in cancer risk and mortality according to smoking status in patients with chronic kidney disease. Here is a link to my updated list of publications: Updated Publications LIST.

Interests

Relative survival methods
Multistate models
Causal inference
Statistical methods for disease mapping (e.g., cluster detection methods, Bayesian hierarchical modeling, multivariate disease mapping).
Statistical Software Development in R

Education

Postdoctoral research, 2020

Burgundy University/Burgundy Digestive Cancer registry
PhD in Clinical research and public Health (option biostatistics), 2018

Aix Marseille University
Master of Public Health (quantitative and econometric methods in health research), 2014

Aix Marseille University
Doctor of Medicine, 2012

Université de Ouagadougou

Experience

Lecturer-Researcher

Ecole des Hautes Etudes en Santé Publique

2022-10-01 – Present Rennes/Paris

Responsibilities include:

Teaching courses on various topics, including hospital epidemiology using the French hospital discharge databases (PMSI)
Supervises students (various level).
Implement research projects based on statistical methods for epidemiology, particularly non-communicable diseases like cancer, with a focus on identifying and quantifying health inequalities.

Biostatistician researcher

Dijon Teaching University Hospital

2022-01-01 – 2022-09-30 Dijon

Responsibilities include:

Perform statistical analysis using French cancer registies data
Data management

Postdoctoral research fellow

Université de Bourgogne/Burgundy Digestive Cancer Registry

2020-01-01 – 2021-12-31 Dijon

Responsibilities include:

Propose new cure model accounting for inaccurate life tables
Model validation (Simulation study)
Packaging the R-code

Biostatistician

Aix Marseille University

2019-01-01 – 2019-12-31 Marseille, France

Developing adaptative statistical learning platform for statistical learning

Responsibilities include:

Automatic generation of simulated statistical exercices
Packaging R code

Accomplishments

Causal inference for time-to-event outcomes – with practical applications in R

ISCB Apr 2024 – Apr 2024

The primary goal of this course was to provide a comprehensive overview of the concepts and methods used to estimate the causal effects of treatments on time-to-event outcomes. The course covered a range of topics, including time-dependent treatments and confounding, inverse probability of treatment weighting and marginal structural models, the g-formula, as well as techniques for handling censoring and competing risks.

PH559x: Causal Diagrams: Draw Your Assumptions Before Your Conclusions

edX Aug 2023 – Sep 2023

See certificate

Infection Prevention and Control (IPC) for Novel Coronavirus (COVID-19)

WHO Mar 2020

Data Science: Productivity Tools

edX Apr 2019 – Jun 2019

See certificate

Projects

External Project

using Rpubs to present differences betwenn chisq.test() and prop.test() R functions via external_link.

Internal Project

See talks page.

Recent & Upcoming Talks and Posts

Quickly discover relevant content by filtering publications.

Leave one out

Packages utiles library("parallel") library("foreach") library("microbenchmark") library("tidyverse") Contexte Supposons que l’on souhaite estimer la qualité de prédiction d’un modèle linéaire, ici un modèle linéaire pour la régression de la largeur d’une pétale sur une longueur sur le jeu de données iris de R.

Dec 5, 2019 R

Webinar on 'Estimation de la survie nette dans les essais cliniques - Intérêts des méthodes utilisées dans les études populationnelles'.

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Juste Goungounga

Jun 17, 2016

Featured Publications

Juste Goungounga, Nathalie Grafféo, Hadrien Charvat, Roch Giorgi

Sat, Apr 1, 2023 Biometrical Journal, 65(4):e2100210

Correcting for heterogeneity and non-comparability bias in multicenter clinical trials with a rescaled random-effect excess hazard model

In the presence of competing causes of event occurrence (e.g., death), the interest might not only be in the overall survival but also in the so-called net survival, that is, the hypothetical survival that would be observed if the disease under study were the only possible cause of death. Net survival estimation is commonly based on the excess hazard approach in which the hazard rate of individuals is assumed to be the sum of a disease-specific and expected hazard rate, supposed to be correctly approximated by the mortality rates obtained from general population life tables. However, this assumption might not be realistic if the study participants are not comparable with the general population. Also, the hierarchical structure of the data can induce a correlation between the outcomes of individuals coming from the same clusters (e.g., hospital, registry). We proposed an excess hazard model that corrects simultaneously for these two sources of bias, instead of dealing with them independently as before. We assessed the performance of this new model and compared it with three similar models, using an extensive simulation study, as well as an application to breast cancer data from a multicenter clinical trial. The new model performed better than the others in terms of bias, root mean square error, and empirical coverage rate. The proposed approach might be useful to account simultaneously for the hierarchical structure of the data and the non-comparability bias in studies such as long-term multicenter clinical trials, when there is interest in the estimation of net survival.

PDF DOI