Transparent methods
Cohort definitions, preprocessing choices, assumptions, endpoints, and evaluation criteria are documented so readers can understand how conclusions were produced.
Open science
Research outputs and practices for transparent, reproducible work.
This page gathers selected publications, preprints, public profiles, and information about reproducible workflows and responsible data access. Materials are shared when public release is appropriate; sensitive or credentialed data remain subject to institutional and platform requirements.
Public research outputs
Selected places to inspect the work.
These links provide the clearest public record of publications, preprints, and methods. The page does not imply that every collaborative dataset or analysis repository is publicly distributable.
Publication record
Google Scholar
Peer-reviewed articles, preprints, and citation information spanning applied mathematics, computational biology, causal modeling, and clinical AI.
View public profile ↗ Curated bibliographyPublications and preprints
A selected record of published work, open manuscripts, and clearly labeled studies in preparation, with links to available articles.
Review selected work → Open preprintBaMANI
Bayesian multi-algorithm causal-network inference with ensemble structure learning, bootstrap stability, and edge-level uncertainty.
Read on arXiv ↗Data access and availability
Open where appropriate, controlled where required.
Clinical and biomedical research often combines public resources with sensitive, credentialed, or collaboration-governed data. Access statements should reflect those differences rather than treating every dataset as open.
- Credentialed clinical data: MIMIC-IV and MIMIC-CXR are accessed through PhysioNet credentialing and are not redistributed.
- Collaborative data: study-specific datasets remain subject to institutional agreements, data-use terms, and the decisions of the collaborating research team.
- Publication-linked materials: public preprints, articles, methods, documentation, and selected computational artifacts are linked when release is permitted and useful.
Open science practices
Reproducibility is built into the analysis, not added at the end.
My workflows emphasize traceable decisions, documented environments, careful model evaluation, and responsible sharing across clinical AI, causal inference, cross-dataset harmonization, and multiscale biomedical modeling.
Reproducible environments
Versioned code, configuration files, package specifications, containers, and cluster instructions are used where they improve repeatability across local and HPC settings.
Evaluation discipline
Calibration, uncertainty, subgroup performance, bootstrap inference, sensitivity analysis, and leakage checks are treated as core parts of model assessment.
Reusable workflows
Analyses are organized as modular pipelines for clinical prediction, causal-network inference, optimal-transport alignment, and uncertainty-aware simulation.
Responsible sharing
Public release is used for non-sensitive outputs when appropriate. Controlled-access and collaborative data remain governed by privacy, credentialing, and study agreements.
Clear availability statements
Materials are described precisely as public, selected, publication-linked, credentialed, restricted, or available through the relevant study team.
Common reproducibility tools
PythonRMATLABJupyterGitDockerSLURM/HPCPhysioNet