Imad EL BADISY

• About
• Research
• Consulting
• Teaching
• Software
• Publications
• Notes
• Contact
• CV

Research Engineer in Health Data Science, PhD

Mohammed VI Center for Research and Innovation · AI & Data Science

Email · GitHub · Google Scholar · LinkedIn · CV

About

Research Engineer in Health Data Science, PhD, working at the interface of biostatistics, machine learning, and applied health data analytics. Moroccan and French national, husband and father. I hold a PhD in Biomedical Sciences from Aix-Marseille University (SESSTIM laboratory) on missing data and machine learning methods for survival analysis. My work focuses on developing algorithms and reproducible workflows for health data analysis and decision support, spanning survival analysis, predictive modeling, interpretable machine learning, and large-scale administrative health data. I develop open-source R packages for survival analysis, missing data, and interpretable machine learning, and contribute as a consultant and trainer in biostatistics and health data science.

Research

• Survival machine learning: Individualized survival prediction | neural survival models | RMST-based summaries, and trajectory phenotyping.
• Missing data: Evaluation of imputation strategies
• Interpretable ML: Explanation workflows aligned with clinical reasoning, including SHAP-style attributions, PDP/ICE/ALE, and stability diagnostics.
• Agentic data science: Increasingly focused on the agentic data science paradigm: building systems where autonomous agents orchestrate analytical workflows for health research.

Consulting

I provide independent methodological and statistical consulting for health research teams, from study design through publication.

• Study design and analysis plan review
• Survival analysis, functional data analysis, and predictive modeling
• Reproducible R/Quarto reporting pipelines
• Custom R package or tool development

Engagements are scoped individually: short advisory sessions, analysis support on a specific study, or longer-term collaboration. Get in touch →

Teaching

Outside working hours: I organize Methods in Health Data Science with R (MHDSR), an independent training pathway covering applied biostatistics, survival analysis, machine learning, and meta-analysis 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)
• METAR: Conducting Meta-Analysis with R (evidence synthesis)

Software

All packages on CRAN · also available via R-universe

Selected Publications

• El Badisy I. (2026). SurvDNN: Survival Deep Learning Models for Tabular Data. The R Journal, 18(1):384-399.

• El Badisy I. (2026). unsurv: Clustering Individualized Survival Curves. Bioinformatics Advances, vbag218.

• El Badisy I. (2026). funcml: Functional Machine Learning Software for R. Zenodo.

• 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.

• 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.

• 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.

• 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.

• 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.

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.

Full publication list →

Notes

Short PDF notes: elegant write-ups tied to the projects and packages I’m working on, published whenever there’s something worth explaining.

View all notes →

Contact

For collaboration, methodological support, or consulting requests, please reach out by email.