PROJECTS
- All
- Future Healthcare
- Lifestyle Recommendation
- Large Language Models
- Personal Health Models
- Population Models
- Translation and Practice
- Health State Estimation
Clinical Trial Adherence: Intelligent Systems for Monitoring and Support
This project develops intelligent systems to improve patient adherence in clinical trials, addressing one of the major causes of trial…
Clinical Trial Enrichment: Intelligent Agent Systems for Patient–Trial Matching
This project develops intelligent agent systems that match patients to clinical trials by integrating EHR data with trial eligibility criteria.…
Reducing Interdataset Covariate Shift in Sleep EEG of Traumatic Brain Injury Using Transfer Euclidean Alignment
This project introduces Transfer Euclidean Alignment (TEA), a transfer learning technique that reduces variability across sleep EEG datasets to improve…
Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots
This project advances the safety of mental health chatbots by adapting Constitutional AI (CAI) with domain-specific principles tailored to psychological…
MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering
This project develops MedCoT-RAG, a domain-specific framework that enhances medical question answering by combining causal-aware retrieval with structured chain-of-thought prompting.…
Linkage Attacks Expose Identity Risks in Public ECG Data Sharing
This project investigates privacy threats in publicly shared electrocardiogram (ECG) data, where biometric features make individuals vulnerable to re-identification. Unlike…
Personalized Counterfactual Framework: Generating Potential Outcomes from Wearable Data
This project introduces a framework that uses wearable sensor data to generate personalized counterfactuals — answering “what if” questions about…
FairTabGen: Unifying Counterfactual and Causal Fairness in Synthetic Tabular Data Generation
This project develops FairTabGen, a fairness-aware LLM-based framework for generating synthetic tabular data. By unifying counterfactual and causal fairness definitions…
REACT: Reinforcement Learning-Based Adaptive ECG Anonymization and Privacy Threat Mitigation
This project introduces REACT, a reinforcement learning framework that protects sensitive electrocardiogram (ECG) data against re-identification threats. By dynamically injecting…
Conversational Health Agents: A Personalized Large Language Model-Powered Framework
This project develops openCHA, an open-source framework for building next-generation conversational health agents (CHAs). Unlike traditional chatbots, openCHA enables multistep…
FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation
This project develops FairCauseSyn, the first LLM-augmented framework for generating synthetic health data with causal fairness. Unlike existing methods that…
Circadian Rhythm of Heart Rate and Heart Rate Variability in Pregnancy
This project explores how pregnancy shapes the circadian rhythms of heart rate (HR) and heart rate variability (HRV), key biomarkers…
CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
This project introduces CDF-RAG, a novel framework that enhances retrieval-augmented generation (RAG) with causal reasoning. Unlike conventional RAG systems that…
Multitask Learning for PPG Applications: Signal Quality Assessment and Physiological Parameter Estimation
This project advances wearable health monitoring by applying multitask learning (MTL) to photoplethysmography (PPG) signals. Instead of training separate models…
DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care
This project develops DEMENTIA-PLAN, an agent-based framework that uses large language models and multiple knowledge graphs to support patients with…
HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations
This project introduces HealthQ, a framework that evaluates how effectively large language model (LLM) chains ask questions in digital healthcare…
TransECG: Leveraging Transformers for Explainable ECG Re-identification Risk Analysis
This project develops TransECG, a Vision Transformer–based framework that analyzes ECG signals for re-identification risks while providing explainability. By applying…
Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations
This project develops a framework that empowers large language models to reason over personalized causal graphs built from longitudinal health…
An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation
This project builds an intelligent agent that combines large language models with analytical tools to interpret physiological signals. Using the…
PERFECT: Personalized Exercise Recommendation Framework and Architecture
This project develops a personalized exercise recommendation system that adapts to each individual’s health profile and daily context. By integrating…
Skewed Memorization in Large Language Models: Quantification and Decomposition
This project investigates how large language models memorize data in a skewed way, where some sequences are far more likely…
Evaluation of LLMs Accuracy and Consistency in the Registered Dietitian Exam
This project evaluates how leading large language models — GPT-4o, Claude 3.5, and Gemini 1.5 — perform on 1,050 Registered…
Large Language Models in Healthcare
Large Language Models (LLMs) have great potential to transform healthcare, providing a range of services including symptom assessment, health recommendations,…
ZotCare: A Flexible, Personalizable, and Affordable mHealth Service Provider
The proliferation of Internet-connected health devices and the widespread availability of mobile connectivity have resulted in a wealth of reliable…
Loneliness and College Students’ Health
College students have been particularly negatively affected by the COVID-19 pandemic, due to social isolation causing loneliness. Targeted behavioral strategies…
Mental Health Navigator
Traditionally, the regime of mental healthcare has followed an episodic psychotherapy model wherein patients seek care from a provider through…
COVID-19 Long-Haulers
Emerging data suggest that the effects of infection with SARS-CoV-2 are far-reaching, extending beyond those with severe acute disease. Specifically,…
Smart, Connected & Coordinated Maternal Care for Underserved Communities
UNITE (UNderserved communITiEs) presents a community engagement model that is smart, deploying ubiquitous monitoring and lifelogging; connected, bringing together a…
Internet of Cognitive Things for Personalized Healthcare
Quality of Experience (QoE) is a key metric for the successful delivery of end-user services for IoT-enabled applications. Achieving consistent…
Building Personal Chronicle
Personicle is a Mobile App which in its current form collects and processes the location, place, mobile device-specific measures like…
Building Personal model for Health Navigation
Population based healthcare models, while helpful in treating diseases caused by external stimulus, have proven not so effective for chronic…
FoodLogging Platform
Models are built using data. Most successful search, social media, and recommendation systems are built using personal models to provide…
Developing estimation techniques for determining health states
Current Healthcare systems are focused on diseases, not health. We adopt and build on the perspective that a body is…
IoT-based Wearables for Antepartum and Intrapartum Assessment in the Home Setting to Promote Fetal and Maternal Care
This project develops novel tools and leverage cutting-edge technologies in bioelectronics and data science to improve fetal and maternal care…
Digital Health for Future of Community-Centered Care
The adhoc nature of the healthcare system in the USA necessitates an organized and affordable platform to increase the reach…
A Monitoring-Intervention System for Dementia Caregivers Using Wearable IoT
Our program aims to build caregiving and stress-management skills in family caregivers of persons with dementia or mild cognitive impairment.…
Supporting adolescents struggling with emotional regulation using wearable technologies
Emotion regulation skills are critical for adaptation to stressful life events and are particularly important in adolescence, as it is…
Holistic Stress Reduction in the Era of COVID-19 through Multimodal Personal Chronicles in College Students
The COVID-19 pandemic has introduced a variety of challenging circumstances on college campuses, including the need for social distancing (resulting…
Remote social interaction monitoring to predict the risk of novel coronavirus infection in the UCI community
In this project, we will investigate how COVID-19 risk is shaped by social contacts and geographic activity spaces in the…
Food Computing
Food determines the quality of life. Food is not only a major source of energy and nutrients essential for health…
Policy driven Privacy Enhanced Technologies (PET) enforcement on Internet of Things (IoT) data flows
IoT service provision commonly relies on environmental or user data from other data providers(e.g. network provider, water agency, building management).…
High-Dimensional Inference beyond Linear Models
This project concerns making proper statistical inference for high-dimensional parameters in three sets of widely used regression models: (i) generalized…
Using self-tracked data to design lightweight social support
People often struggle to receive the support they desire from friends and families around their health behavior goals. We are…
Optimizing Digital Interventions through Micro-Randomized Trials and Causal Modeling
The development in smartphone and wearable technology now makes it possible to deliver digital health interventions to individuals in real…
Understanding life events and transitions supported by fertility apps
Women’s health needs change over the course of life, transitioning between health stages and goals such as menarche, pregnancy or…
Examining and designing more useful mood tracking tools
People are widely adopting apps for tracking their moods and emotions. We aim to understand how and why these apps…
Examining a Multimodal Approach to Lowering the Burden of Food Journaling
People use personal journaling methods to develop better habits and make informed decisions about health and well-being. Activities such as…
The long-term impact of light intervention on sleep physiology and cognition in mild cognitive impairment
This application proposes to investigate the impact of a long-term lighting treatment on sleep physiology and sleep-dependent cognitive processes in…
Supporting Lifestyle Change in Obese Pregnant Mothers through Wearable Internet-of-Things
Pregnant women with obesity have indisputably increased risk for gestational diabetes mellitus, depression, miscarriage, and preterm birth, just to mention…
Preterm Birth Prevention in Everyday Settings
Preterm birth (PTB) is the most common cause of neonatal deaths. Due to the high rate of PTBs (15M/y), it…
Development of a Community-based TBI Treatment Completion Intervention Among Homeless Adults
Tuberculosis (TB) is a disease of poverty as it disproportionately affects impoverished communities. In the US, TB rates are unacceptably…
Improving Health and Nutrition of Indian Women with AIDS and their Children
The overall goal of this project is to enhance the physical and mental health of rural Indian women living with…
Prevention for Homeless At-Risk for HCV
Compared to the general population, homeless persons have a 26-fold increase in Hepatitis C Virus (HCV) prevalence, a diagnosis strongly…