Imad El Badisy, PhD
Health Data Scientist & Computational Methodologist
I am a health data scientist and computational methodologist building software for machine learning and computational biostatistics.
My focus is turning advanced statistical and machine learning methods into reliable, open-source tools that researchers can use. Learn more from the software packages I build.
Get in touch at elbadisyimad@gmail.com or ielbadisy@cm6.ma.
About me
I hold a PhD in Biomedical Sciences from Aix-Marseille University (SESSTIM laboratory) on missing data and machine learning methods for survival analysis. I develop software and design agentic workflows that bridge statistical rigor with modern computation. See the full list in the software section.
Moroccan and French national, husband and father.
See my education and experience or download my CV (PDF).
Research
My methodological research centers on four areas:
- Scientific machine learning: machine learning methods grounded in statistical and scientific structure, with an emphasis on interpretability and reliable inference.
- Survival analysis: survival machine learning, including individualized prediction, neural survival models, RMST summaries, and trajectory phenotyping.
- Missing data imputation: machine learning imputation methods and their evaluation, particularly for survival outcomes.
- Agentic data science: LLM-based agents that plan and run statistical analysis workflows, and software designed so that these agents can use it correctly, reproducibly, and safely.
Consulting
I provide independent methodological and statistical consulting for health research teams, from study design through publication.
- Study design and analysis plan review
- Statistical methodology (survival analysis, functional data, predictive modeling)
- Evidence synthesis
- Machine learning prediction for health outcomes
- Health economics and cost-effectiveness studies
- Custom R package and tool development
Background
Professional experience and education. The full record is in the CV (PDF).
Experience
| Position | Institution | Period |
|---|---|---|
| Head of AI and Data Science Service | CM6RI, Rabat, Morocco | Jan. 2026 – Present |
| Research Engineer in Health Data Science | CM6RI, Rabat, Morocco | Nov. 2021 – Jan. 2026 |
| Data Science Education Officer | The GRAPH Network, Switzerland | Sep. 2023 – Dec. 2023 |
| Research and Development Engineer | IMT Atlantique, Brest, France | Sep. 2019 – Sep. 2021 |
| Biostatistician | INSERM, Clermont-Ferrand, France | Jan. 2019 – Jun. 2019 |
| Health Economist Intern | Université de Sherbrooke, Quebec, Canada | Feb. 2017 – Sep. 2017 |
Education
| Degree | Institution | Period |
|---|---|---|
| PhD in Biomedical Sciences | Aix-Marseille University, SESSTIM, Marseille, France | 2021 – 2025 |
| Master 2, Quantitative Methods for Health Research | Aix-Marseille University, SESSTIM, Marseille, France | 2018 – 2019 |
| Master 1, Applied Mathematics and Statistics | Université Clermont Auvergne, Clermont-Ferrand, France | 2017 – 2018 |
| Master 2, Health Economics | Université Clermont Auvergne, CERDI, Clermont-Ferrand, France | 2016 – 2017 |
Teaching
University courses and independent training in biostatistics, machine learning, and health data science.
University courses
| Course | Institution | Period |
|---|---|---|
| AI for Public Health (ML, NLP, applied AI) | Aix-Marseille University, SESSTIM, Marseille, France | 2022 – present |
| Introduction to Biostatistics | University Mohammed VI of Health Sciences (UM6SS), Casablanca, Morocco | 2021 – present |
| Quantitative Epidemiology and Machine Learning | Institut Mines-Télécom, IMT Atlantique, Brest, France | 2020 – present |
MHDSR: Methods in Health Data Science with R
Outside working hours I organize MHDSR, an independent training pathway covering applied biostatistics, survival analysis, and machine learning with R, delivered live to research teams and open cohorts:
- BIOSTATR: Applied Biostatistics with R (foundations)
- ML4HOR: Machine Learning for Health Outcomes with R (prediction)
Software
Open-source software for survival analysis, machine learning, and functional data analysis in health research.
functionals
Functional programming utilities.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2025). functionals: Functional Programming with Parallelism and Progress Tracking. R package version 0.5.1. doi:10.32614/CRAN.package.functionals
unsurv
Unsupervised clustering of individualized survival curves.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). unsurv: Unsupervised Clustering of Individualized Survival Curves. R package version 0.7.2. doi:10.32614/CRAN.package.unsurv
tvrmst
Time-varying RMST tooling.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). tvrmst: Time-Varying Restricted Mean Survival Time from Survival Matrices. R package version 0.0.6. doi:10.32614/CRAN.package.tvrmst
mcstatsim
Monte Carlo statistical simulation.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2024). mcstatsim: Monte Carlo Statistical Simulation Tools Using a Functional Approach. R package version 0.5.1. doi:10.32614/CRAN.package.mcstatsim
missCforest
Missing-data random forest methods.
CRAN | PDF docs | R-universe
Cite: El Badisy, I. (2023). missCforest: Ensemble Conditional Trees for Missing Data Imputation. R package version 0.0.8. doi:10.32614/CRAN.package.missCforest
survalis
Survival machine learning framework.
CRAN | PDF docs | R-universe
Cite: El Badisy, I. (2026). survalis: Interpretable Survival Machine Learning Framework. R package version 1.0.0. doi:10.32614/CRAN.package.survalis
funcml
Functional machine learning framework.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). funcml: Functional Machine Learning Framework. R package version 0.9.0. doi:10.32614/CRAN.package.funcml
survdnn
Deep neural networks for right-censored survival analysis.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). survdnn: Deep Neural Networks for Survival Analysis with R 'torch'. R package version 1.0.0. doi:10.32614/CRAN.package.survdnn
mimar
Compact multiple imputation, assessment, and reporting.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). mimar: Compact Multiple Imputation, Assessment, and Reporting. R package version 1.0.0. doi:10.32614/CRAN.package.mimar
testflow
Statistical testing, interpretation, and ggplot2-based visualization.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). testflow: A Workflow for Statistical Testing, Interpretation, and 'ggplot2'-Based Visualization. R package version 1.0.0. doi:10.32614/CRAN.package.testflow
densemlp
Dense neural networks for tabular classification and regression.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). densemlp: Dense Neural Networks for Tabular Classification and Regression. R package version 0.7.1. doi:10.32614/CRAN.package.densemlp
CEACT
Cost-effectiveness analysis toolkit for clinical trials.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). CEACT: Cost-Effectiveness Analysis Toolkit for Clinical Trials. R package version 0.5.0. doi:10.32614/CRAN.package.CEACT
missknn
Fast masked k-nearest neighbor imputation.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). missknn: Fast Masked K-Nearest Neighbor Imputation. R package version 1.1.2. doi:10.32614/CRAN.package.missknn
basetable
Fast and memory-efficient base R table manipulation.
CRAN | PDF docs | R-universe
Cite: EL BADISY, I. (2026). basetable: Fast and Memory-Efficient Base R Table Manipulation. R package version 1.4.2. doi:10.32614/CRAN.package.basetable
Publications
Selected peer-reviewed articles, software papers, and conference talks.
Selected articles
2026
- El Badisy I. (2026). unsurv: Clustering Individualized Survival Curves. Bioinformatics Advances, vbag218. doi:10.1093/bioadv/vbag218
- El Badisy I. (2026). SurvDNN: Survival Deep Learning Models for Tabular Data. The R Journal, 18(1):384-399. doi:10.32614/RJ-2026-008
- El Badisy I. (2026). funcml: Functional Machine Learning Software for R. Zenodo. doi:10.5281/zenodo.20707605
- El Badisy I., Assarag B., Belrhiti Z. (2026). Interpretable clinical decision support systems in high-risk pregnancy: a scoping review of models, methods, and implementation. BMC Pregnancy and Childbirth, 26(1):125. doi:10.1186/s12884-025-08614-9
- Bnimoussa J., Bouaddi O., El Badisy I., Khalis M. (2026). Drivers of youth mental health and wellbeing: a large-scale cross-sectional study in Morocco. BMJ Open, 16(6):e110683. doi:10.1136/bmjopen-2025-110683
- Lamchabbek N., Huybrechts I., El Badisy I., et al. (2026). Global assessment of the relationship between breast cancer risk and dietary intake: an ecological study. American Journal of Health Promotion, 40(5):591-600. doi:10.1177/08901171251389792
- Bouaddi O., El Badisy I., Charaka H., et al. (2026). Leveraging the positive deviance approach to drive behavior change in noncommunicable diseases: a scoping review. Public Health Challenges, 5(1):e70074. doi:10.1002/puh2.70074
- Lamchabbek N., Mrah S., Mane N., El Badisy I., et al. (2026). Adherence to WCRF/AICR cancer prevention recommendations and reduction in breast cancer risk: results of a large-scale case-control study in Morocco. British Journal of Nutrition. doi:10.1017/S0007114526106527
- Bichri K., Chihab Eddine M., Sqalli Houssaini M., Rghioui M., El Badisy I., Ghazi B. (2026). DZIP3 is associated with the cytoskeletal dynamics in glioblastoma and mitochondrial machinery regulation. Frontiers in Bioinformatics, 6:1878616. doi:10.3389/fbinf.2026.1878616
2025
- Houdou A., Khomsi K., Delle Monache L., El Badisy I., et al. (2025). Enhancing 5-day particulate matter (PM10) forecasts in Morocco using U-net: a deep learning approach. Atmospheric Research, 328:108439. doi:10.1016/j.atmosres.2025.108439
- Kadi C., Ahmadi N., Houdou A., El Badisy I., et al. (2025). Differentiating latent tuberculosis from active tuberculosis through activation phenotypes and chemokine markers HLA-DR, CD38, MCP-1, and RANTES: a systematic review and meta-analysis. Biomarker Insights, 20:11772719241312776. doi:10.1177/11772719241312776
2024
- Houdou A., El Badisy I., Khomsi K., et al. (2024). Interpretable machine learning approaches for forecasting and predicting air pollution: a systematic review. Aerosol and Air Quality Research, 24(1):230151. doi:10.4209/aaqr.230151
- El Badisy I., BenBrahim Z., Khalis M., et al. (2024). Risk factors affecting patient survival with colorectal cancer in Morocco: survival analysis using an interpretable machine learning approach. Scientific Reports, 14(1):3556. doi:10.1038/s41598-024-51304-3
- El Badisy I., Graffeo N., Khalis M., Giorgi R. (2024). Multi-metric comparison of machine learning imputation methods with application to breast cancer survival. BMC Medical Research Methodology, 24(1):191. doi:10.1186/s12874-024-02305-3
- Zbiri S., Belghiti Alaoui A., El Badisy I., et al. (2024). Private hospitals in low- and middle-income countries: a typology using the cluster method, the case of Morocco. BMC Health Services Research, 24(1):1231. doi:10.1186/s12913-024-11660-2
- Abdala S.A., Khomsi K., Houdou A., El Badisy I., et al. (2024). Emission reduction strategies and health: a systematic review on the tools and methods to assess co-benefits. BMJ Open, 14(12):e083214. doi:10.1136/bmjopen-2023-083214
Selected talks
- El Badisy I. et al. (2023). Comparison of missing data imputation methods in Cox regression with time-varying and non-linear covariate effects. ISCB 2023, Rome.
- El Badisy I. et al. (2023). Missing data imputation using a meta-algorithm, metaCART: A simulation study under MCAR. EpiClin 2023, Nancy.
Notes
Methodological notes connected to my R packages and current projects, written up as short PDFs with equations, code, rendered results, and references.
| Date | Note | Tags |
|---|---|---|
| 2026-08-22 | Deep neural networks for survival analysis with survdnn |
Survival Analysis Deep Learning survdnn |
| 2026-07-27 | Survival-trajectory phenotypes with unsurv |
Survival Analysis Clustering unsurv |
| 2026-07-02 | Masked k-NN imputation with missknn |
Missing Data Imputation missknn |
| 2026-06-10 | Generating time-varying and non-linear covariate effects with rpsurv |
Survival Analysis Simulation rpsurv |
Blog
Notes and write-ups on the R packages and methods I build, mostly biostatistics, survival analysis, and machine learning for health data.
Hazards, p-values and hybrid models: notes from ISCB GMDS 2026
API Design in the Era of LLMs
What I Learned from the GMDS Biostatistics Competition 2026
survalis is now on CRAN
survdnn: Deep Neural Networks for Survival Analysis in R
Contact
Feel free to reach out about collaborations, consulting, or simply to say hello.
I also welcome feedback on my educational materials and R packages, whether something was helpful or could be improved.
License
Content on this site, including the notes, is released under a Creative Commons Attribution-ShareAlike 4.0 International License unless stated otherwise. Software released under my packages is licensed independently; see each package’s repository for its specific license.
Accessibility
This site uses a color palette meeting WCAG 2.1 AA contrast, alternative text for informative images, readable font faces, and light and dark themes. If you encounter any accessibility barriers, please get in touch.