Understanding real life behavior of individuals and populations by collecting large volumes of data and selecting appropriate sets using right control parameters.
We are excited to announce that our dataset — “Loneliness and well-being in Finnish immigrants: A multimodal dataset from wearables and passive data collection” — is now publicly available via Dryad.
The openCHA framework allows LLMs to connect with external data sources, enabling the collection of information and the creation of customized responses.
AI is a powerful force in technology, offering both optimism and concern. It should be seen as a partner, not a replacement for human intellect, augmenting our capabilities responsibly to maximize benefits and mitigate risks.
AI can predict if people develop dementia within two years. The prediction accuracy is 92 percent, obtained in a largescale study conducted on more than 15,400 patients in the U.S.
October 17, 2025, at 12:00–1:00 PM (PDT)
Zoom
September 9, 2025
Sue & Bill Gross School of Nursing, University of California, Irvine
This project develops intelligent systems to improve patient adherence in clinical trials, addressing one of the major causes of trial…
This project develops intelligent agent systems that match patients to clinical trials by integrating EHR data with trial eligibility criteria.…
This project introduces Transfer Euclidean Alignment (TEA), a transfer learning technique that reduces variability across sleep EEG datasets to improve…
This project advances the safety of mental health chatbots by adapting Constitutional AI (CAI) with domain-specific principles tailored to psychological…
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.…
This project investigates privacy threats in publicly shared electrocardiogram (ECG) data, where biometric features make individuals vulnerable to re-identification. Unlike…
This project introduces a framework that uses wearable sensor data to generate personalized counterfactuals — answering “what if” questions about…
This project develops FairTabGen, a fairness-aware LLM-based framework for generating synthetic tabular data. By unifying counterfactual and causal fairness definitions…
This project introduces REACT, a reinforcement learning framework that protects sensitive electrocardiogram (ECG) data against re-identification threats. By dynamically injecting…
