Nephrologist | Internal Medicine Specialist | Clinical Research & Real-World Data Analytics | Bioinformatics (MSc)
I am a practicing nephrologist and internal medicine specialist with a strong focus on clinical data science and translational bioinformatics.
My work is centered on integrating real-world clinical data with high-dimensional molecular datasets to better understand kidney disease progression, improve clinical decision-making, and explore biologically meaningful patterns that may not be evident through traditional analysis.
I am particularly interested in the intersection between clinical nephrology, epidemiology, and multi-omics, with an emphasis on generating insights that are both scientifically robust and clinically interpretable.
• Chronic Kidney Disease (CKD) and progression modeling • Diabetic Kidney Disease (DKD) and metabolic-fibrotic pathways • Glomerular diseases (FSGS, lupus nephritis) • Hemodialysis outcomes and risk stratification • Translational bioinformatics (RNA-seq, single-cell, multi-omics integration) • Real-world clinical data analysis in low-resource settings
Analysis of CKD burden in primary care settings integrating clinical and sociodemographic data. Highlights challenges and opportunities of working with real-world, imperfect datasets in resource-limited environments.
Real-world hemodialysis data analysis focused on intradialytic hypotension, clinical risk patterns, and patient-level hemodynamic phenotyping.
Reproducible bioinformatics pipeline for transcriptomic analysis of chronic kidney disease (CKD) using public microarray data (GSE12682), developed as part of the Master's in Bioinformatics (UAX).
Cross-compartment analysis exploring whether transcriptomic signals in kidney tissue are reflected at the protein level in urine. Addresses the potential for non-invasive biomarker discovery.
Single-cell RNA-seq analysis focused on epithelial injury, inflammation, and repair programs in human kidney tissue. Emphasizes cellular heterogeneity and pathophysiological mechanisms at single-cell resolution.
Integration of transcriptomic, proteomic, and clinical data from TCGA to identify molecular patterns associated with survival in renal cell carcinoma. Demonstrates multi-omics integration and survival analysis in a clinically relevant context.
Hemodialysis Survival Prediction (ML + SHAP)
Clinical machine learning model for 1-year mortality prediction in hemodialysis patients, with interpretable feature attribution using SHAP.
Synthetic clinically grounded dataset. Methodological demonstration. Not a clinical prediction tool. Not externally validated. Not intended for patient-level decisions.
• R: limma, DESeq2, Bioconductor ecosystem • Python: data analysis, machine learning workflows • SQL: clinical data querying • Power BI: data visualization and dashboarding • Reproducible research pipelines (Git, scripting, structured workflows)
My goal is to develop a clinically grounded data science profile, capable of bridging:
• Patient-level clinical insight • Population-level epidemiology • Molecular-level bioinformatics
with a strong emphasis on interpretability, reproducibility, and real-world applicability.
LinkedIn: https://www.linkedin.com/in/cristian-arias-healthcare-data