The Informatics Lab

My Research

Stay updated with the latest insights from my research journey, technical discoveries, and thoughts on the future of digital health innovation.

June 26, 2025

Digital Twin Framework for Personalized Care Planning

Digital Twin (DT) technology has emerged as a transformative approach in healthcare, but its application in personalized patient care remains limited. This paper aims to present a practical implementation of DT in the management of chronic diseases. We introduce a general DT framework for personalized care planning (DT4PCP), with the core components being a real-time virtual representation of a patient’s health and emerging predictive models to enable adaptive, personalized care. We implemented the DT4PCP framework for managing Type 2 Diabetes (DT4PCP-T2D), enabling real-time collection of behavioral data from patients with T2D, predicting emergency department (ED) risks, simulating the effects of different interventions, and personalizing care strategies to reduce ED visits. The DT4PCP-T2D also integrates social determinants of health (SDoH) and other contextual data, offering a comprehensive view of the patient's health to ensure that care recommendations are tailored to individual needs. Through retrospective simulations, we demonstrate that integrating DTs in T2D management can lead to significant advancements in personalized medicine. This study underscores the potential of DT technology to revolutionize chronic disease care.

December 12, 2024

Predicting Emergency Department Visits for Patients with Type II Diabetes

Over 30 million Americans are affected by Type II diabetes (T2D), a treatable condition with significant health risks. This study aims to develop and validate predictive models using machine learning (ML) techniques to estimate emergency department (ED) visits among patients with T2D. Data for these patients was obtained from the HealthShare Exchange (HSX), focusing on demographic details, diagnoses, and vital signs. Our sample contained 34,151 patients diagnosed with T2D which resulted in 703,065 visits overall between 2017 and 2021. A workflow integrated EMR data with SDoH for ML predictions. A total of 87 out of 2,555 features were selected for model construction. Various machine learning algorithms, including CatBoost, Ensemble Learning, K-nearest Neighbors (KNN), Support Vector Classification (SVC), Random Forest, and Extreme Gradient Boosting (XGBoost), were employed with tenfold cross-validation to predict whether a patient is at risk of an ED visit. The ROC curves for Random Forest, XGBoost, Ensemble Learning, CatBoost, KNN, and SVC, were 0.82, 0.82, 0.82, 0.81, 0.72, 0.68, respectively. Ensemble Learning and Random Forest models demonstrated superior predictive performance in terms of discrimination, calibration, and clinical applicability. These models are reliable tools for predicting risk of ED visits among patients with T2D. They can estimate future ED demand and assist clinicians in identifying critical factors associated with ED utilization, enabling early interventions to reduce such visits. The top five important features were age, the difference between visitation gaps, visitation gaps, R10 or abdominal and pelvic pain, and the Index of Concentration at the Extremes (ICE) for income.

About Me

I am Javad M Alizadeh, a PhD student in Health Informatics at Temple University who bridges the gap between healthcare research and digital innovation. With a background in Industrial Engineering, I bring both analytical rigor and practical problem-solving to healthcare challenges.

Technical Skills

My technical toolkit spans the full spectrum from research to implementation:

Programming: Python, R

Machine Learning: Scikit-learn, XGBoost, CatBoost

Data Visualization: Matplotlib, Seaborn, Plotly Dash, Folium

Database Management: SQL Server, MySQL, MongoDB

Web Development: Django, Streamlit, Tkinter

Optimization: GAMS, AMPL, CPLEX

Download CV

From Industrial Engineering to Healthcare Systems: My path began in industrial engineering, where I developed expertise in mathematical modeling, optimization, and system design. I applied these skills to pharmaceutical supply chains and healthcare logistics before transitioning to health informatics, where I discovered my passion for using data to directly improve patient outcomes.

Health Informatics Research: My current research focuses on chronic diseases, such as Type 2 diabetes and hypertension, where I combine medical records with social determinants of health to predict emergency department visits. I've successfully developed machine learning models achieving over 80% AUC ROC scores, demonstrating that healthcare insights can be both academically rigorous and clinically actionable.
Also, I am working on data-driven solutions that assist social workers in providing targeted information and resources to individuals experiencing homelessness, addressing critical gaps in healthcare accessibility for vulnerable populations.

Digital Solution Development: To bridge the research-to-practice gap, I build the digital tools that bring my findings to life. I believe that impactful health informatics research must extend beyond academic publications to create tangible solutions that healthcare providers, social workers, and patients can actually use in real-world settings. My development approach combines rigorous data science with user-centered design principles to ensure that complex algorithms become accessible, intuitive tools. I've developed:

· Digital twin framework for personalized care planning applied to type 2 diabetes management
· AI-powered clinical decision support systems
· Interactive data visualization tools
· Conversational AI chatbot for individuals experiencing homelessness

Each solution is designed with end-user workflow integration in mind, ensuring that technological innovation enhances rather than disrupts existing healthcare delivery processes. I focus on creating tools that are not only technically sophisticated but also clinically relevant and operationally feasible.

Research Impact: I've presented my work at major conferences including AMIA, APHA, College of Physicians of Philadelphia, and CHASE, with publications focusing on digital twin in healthcare and emergency department visit prediction.

Vision: My goal is to transform every healthcare research insight into practical digital solutions. I believe the most impactful health informatics research is research that healthcare providers can actually use to improve patient care. Whether it's a predictive model, a decision support tool, or an interactive dashboard, I'm committed to building technology that makes healthcare more effective, accessible, and equitable.

THE INFORMATICS LAB

My Applications

Choropleth Map Generator