๐ I work at the intersection of statistical theory, interpretable machine learning, and real-world clinical data.
Focus: Interpretable ML ยท Nonparametric Statistics ยท Clinical & Scientific AI
โModels should not only predict well โ they should explain well.โ
I approach modeling through three principles:
- Statistical validity before scale
- Interpretability before optimization
- Domain meaning before deployment
My research interests include:
- interpretable and explainable machine learning (post-hoc & intrinsic)
- permutation-based, resampling, and nonparametric inference
- dimensionality reduction with geometric and statistical intuition
- robustness, stability, and noise-aware modeling
- translating statistical theory into clinically actionable insights
Used primarily for statistical modeling, interpretability research, and reproducible scientific workflows.
๐ papersearch-mcp
An Model Context Protocol (MCP) server for searching, analyzing, and retrieving academic papers.
- Purpose: Integrates arXiv and Semantic Scholar directly into AI coding assistants (like Claude Code/Desktop).
- Features: Page-level text extraction from PDFs using PyMuPDF (fitz), citation graph traversal, and advanced search filters.
- Tech: FastMCP, Python, HTTPX, PyMuPDF.
Nonparametric Combination (NPC) and bootstrap-based risk stratification model.
- Purpose: Reproducible statistical analysis framework for our peer-reviewed research in Necrotizing Fasciitis.
- Tech: Python, NumPy, Pandas, Scipy.
End-to-end clinical NLP platform for medical entity extraction, clinical sentiment analysis, topic modeling, and automated ICD coding.
- Purpose: Privacy-preserving processing and deep learning pipelines for unstructured health records.
- Tech: Python, PyTorch, Transformers, FastAPI.
I actively participate in bug triaging, Q&A, and technical discussion forums across key scientific Python and developer libraries:
- scikit-learn: Contributing technical solutions for community questions on discussions (e.g. customized Gower's distance implementations, tree routing diagnostics).
- FastAPI / Next.js: Supporting developers in resolving configuration and execution issues in production settings.
Permutation-Based Analysis of Clinical Variables in Necrotizing Fasciitis Using NPC and Bootstrap
Mathematics, MDPI (2025)
This work introduces a permutation-based, nonparametric framework for analyzing clinical variables in necrotizing fasciitis. By combining Nonparametric Combination (NPC) methodology with bootstrap techniques, the study enables robust inference under small-sample and distribution-free conditions, with an emphasis on interpretability and clinical relevance.
The study demonstrates how permutation-based inference can outperform classical parametric approaches in rare-disease clinical settings.
๐ https://www.mdpi.com/2227-7390/13/17/2869
- permutation-based inference for small-sample biomedical studies
- interpretability under distribution shift
- robustness diagnostics for clinical ML models
- statistical foundations of explainable AI
- ๐ math and statistics-first explanations of ML & AI
- ๐งช reproducible experiments with robust inference
- ๐ real-world clinical and analytical datasets
- ๐ง research-oriented notebooks focused on why, not just how
โญ Thoughtful questions and rigorous discussions are always welcome.