About me
Hello and welcome!
I am a Measurement Scientist and Machine Learning Researcher dedicated to building and evaluating high-stakes AI systems. Currently, as a Postdoctoral Researcher at Truveta, I develop clinical AI and foundation models designed to transform the patient journey through longitudinal data analysis and predictive modeling.
My approach is defined by a rigorous foundation in Measurement & Statistics (Ph.D., University of Washington) and advanced Causal Inference training (Postdoc, Harvard University). My background is uniquely multidisciplinary; I have pivoted from a deep focus on psychometrics and human behavior to high-dimensional healthcare analytics. This evolution allows me to treat AI evaluation as a rigorous scientific discipline—applying psychometric theory, latent variable modeling, and validity frameworks to ensure that modern AI systems are reliable, calibrated, and impactful.
🚀 Core Expertise & Impact
- Scientific AI Evaluation: I develop frameworks to validate complex AI outputs. By establishing the validity and reliability of automated metrics, I ensure that “model-as-judge” systems and automated benchmarks are psychometrically sound. At Harvard, I developed the ‘rcttext’ R package to integrate NLP into randomized controlled trials (RCTs) and led comparative research on LLMs versus traditional ML for high-stakes assessment tasks.
- Foundation Models & Longitudinal Systems: I architect longitudinal ML/LLM systems to predict state transitions in high-dimensional data. This includes building Chain-of-Agents frameworks for oncology risk prediction and developing automated frameworks for clinical outcome estimation, such as predicting KCCQ scores in heart failure.
- Advanced Statistical Methodology: Rooted in my doctoral research on factor analysis and prediction algorithms, I bridge the gap between classical statistics and modern AI. My focus is on improving model interpretability and building scalable infrastructure, such as Model Context Protocol (MCP) tools, to integrate predictive models into real-world production workflows.
💡 My Mission
My mission is to advance the frontier of AI by bringing measurement rigor to technical innovation. Whether identifying patterns in educational equity or predicting health-state transitions in oncology, I aim to ensure that algorithms are not only high-performing but also grounded in scientific evidence to drive positive societal change.
I am always eager to collaborate with peers dedicated to the intersection of data science, measurement, and human behavior.
Current Research Projects
Developing large-scale foundation models using longitudinal EHR data to characterize complex health-state transitions
Building predictive models for high-stakes clinical decision support (Oncology & Cardiology)
Designing tools to bridge the gap between AI predictive models and production-ready clinical workflows
Previous Research Projects
Developing Statistical Methods for Text Analysis in RCTs (see the related projects)
Investigating Large Language Models vs. Machine Learning for Automated Essay Scoring (see the project slides)
Extending Factor Analysis with Machine/Deep Learning Insights (see the project slides)
Examining International Students’ Professional Development, Well-being, and Experiences with Racism & Discrimination
Comparing the relative benefits of exponential random graph models with latent space models – two different approaches for predicting the formation of a tie in a network – including missing data handling (see the project slides)