lab

LU Causal Intelligence & Data Lab (LUCID Lab)

The LUCID Lab is based at Yale, jointly housed across the Section of General Internal Medicine (Yale School of Medicine) and the Department of Chronic Disease Epidemiology (Yale School of Public Health). We are also affiliated with the Yale Program in Addiction Medicine and the Yale Institute for Foundations of Data Science.

Research focus

Our work develops and applies methods at the intersection of causal inference, pharmacoepidemiology / real-world evidence, and data science — with the goal of making reliable causal inferences from observational health data and generating high-quality evidence for clinical decision-making.

Methodological areas:

• Target trial emulation and estimand-first thinking
• Selection bias, generalizability, and representativeness
• Heterogeneous treatment effects and precision medicine
• Machine learning for propensity-score estimation and causal inference
• Bayesian spatiotemporal analysis

Substantive areas:

• Medications for opioid use disorder and other substance-use conditions
• HIV/AIDS and antiretroviral effectiveness
• Comparative safety and effectiveness of medications (e.g., GLP-1 receptor agonists, anti-CGRP agents, ACEI/ARB)
• Veteran health, using VA Corporate Data Warehouse and VACS data

Current funding

• NIH/NIDA R00 (K99/R00 Pathway to Independence Award) — Evaluating and Optimizing Care for Opioid Use Disorder using a Structured Data-Science Approach (PI; 2025–2028).
• Interagency Agreement, VA–FDA (BOOST) — Buprenorphine dosing for OUD outcomes and studying treatment episodes (Co-I; 2024–2027).

Join us

We welcome inquiries from prospective PhD students, postdoctoral fellows, and research collaborators interested in causal inference for health data. Please reach out by email with a short note on your background and interests, along with a current CV.

People

The lab is actively growing. Current trainees and collaborators will be listed here soon.