Patricia C. Torrell

# 🧬 Patricia C. Torrell ### Clinical Data Analyst **Machine Learning · Clinical Research · Reproducible Science**

📁 Portfolio of Clinical Data Science Projects

🧬 About Me

Clinical Data Analyst specializing in:

structured clinical datasets
reproducible analytical pipelines
machine learning for risk prediction
scientific communication and interpretability

My work focuses on building clinically meaningful, transparent and reproducible models that support decision‑making in healthcare.

📁 Featured Projects

### 🧩 Migraine Risk Prediction Machine‑learning framework for migraine risk assessment integrating clinical preprocessing, calibrated probability modeling, SHAP‑based insights, decision‑threshold tuning, and subgroup fairness evaluation to ensure reliable and equitable predictions.
👉 View project website
👉 GitHub repository

### ❤️ Cardiovascular Risk Prediction End‑to‑end machine learning pipeline for cardiovascular disease risk prediction, including clinical cleaning, feature engineering, robust preprocessing, model training, calibration, interpretability, and reporting.
👉 View project website
👉 GitHub repository

### 🧬 Kidney Stone Risk Prediction Machine learning pipeline for kidney stone risk prediction, featuring calibrated models, interpretability (Permutation Importance + PDPs), and a clean modular architecture for clinical decision support.
👉 View project website
👉 GitHub repository

### 🧠 Alzheimer’s Disease — Brain Morphology & Mental Health Clinically grounded analysis of brain morphology, daily functioning, and symptom severity across Alzheimer's disease diagnostic groups, featuring rigorous statistical analysis, baseline predictive modeling, and a fully modular pipeline structure.
👉 View project website
👉 GitHub repository

### 🦠 Antimicrobial Resistance in Spain Analysis of antimicrobial resistance (AMR) in Spain using EARS-Net data (2000–2018), exploring resistance patterns by age, gender, bacteria–antibiotic profiles, trends over time, and predictive modeling to support clinical and public health decisions.
👉 View project website
👉 GitHub repository

🧩 Skills

Clinical data preprocessing (missingness, outliers, encoding)
Statistical analysis (R, Python, SPSS)
Machine learning for risk prediction
Feature engineering guided by clinical knowledge
Model evaluation and interpretability
Reproducible pipelines (pandas, PySpark, sklearn)
Scientific communication and reporting

💼 Experience

Clinical Data Analyst

Analysis of structured clinical datasets
Development of reproducible analytical workflows
Risk prediction modeling in healthcare contexts
Preparation of technical and scientific reports

📬 Contact

Last updated: March 2026