About

I lead AI/ML & Data Science at Bold — a digital health platform combining virtual lifestyle medicine care and exercise programs to help older adults live healthier, more independent lives. My work there spans designing and building production AI systems — including a Transformer-based content recommendation system, generative AI for clinical care plan creation, and agentic AI systems for personalized health coaching — as well as data science across risk modeling and revenue forecasting. I’ve spent my career at the intersection of machine learning and human health.

Previously, I was an AI/ML scientist at Optum AI (UnitedHealth Group) where I led a team of scientists building ML models for trend forecasting, and developed Transformer-based models across diverse clinical data modalities — culminating in CHIRon, a generative foundation model for structured sequential medical data.

My PhD research at UCLA, under the guidance of Professor Eran Halperin, focused on applying machine learning to clinical and genomic data, leveraging electronic health records, physiological waveform signals, genomics, medical imaging data, and clinical text, with a particular interest in sequence modeling, causal inference, and imputation of missing data.

My prior industry experience includes an internship at Microsoft Research working with Daniel McDuff, four continuous years as an intern at Intel (full-time summers, part-time during the school year) under the mentorship of Gans Srinivasa, and three years as the founding engineer at Omics Data Automation (now dātma) working with Gans Srinivasa. I earned my undergraduate degree in Electrical and Computer Engineering from Oregon State University.

Selected Publications

*- denotes joint authorship

“CHIRon: A Generative Foundation Model for Structured Sequential Medical Data” - Deep Generative Models for Health (DGM4H) Workshop, NeurIPS (2023) - Brian L. Hill, Melika Emami, Vijay S. Nori, Aldo Cordova-Palomera, Robert Tillman, Eran Halperin; [paper]

“Extend and Explain: Interpreting Very Long Language Models” - Proceedings of the 2nd Machine Learning for Health (ML4H) symposium (2022) - Joel Stremmel, Brian L. Hill, Jeffrey Hertzberg, Jaime Murillo, Llewelyn Allotey, Eran Halperin; [paper] [preprint] [code]

“Methylation risk scores are associated with a collection of phenotypes within electronic health record systems” - npj Genomic Medicine (2022) - Mike Thompson*, Brian L. Hill*, Nadav Rakocz, Jeffrey N. Chiang, Daniel Geschwind, Sriram Sankararaman, Ira Hofer, Maxime Cannesson, Noah Zaitlen, Eran Halperin; [paper] [preprint] [code]

“Imputation of the continuous arterial line blood pressure waveform from non-invasive measurements using deep learning” - Scientific Reports (2021) - Brian L. Hill, Nadav Rakocz, Akos Rudas, Jeffrey N. Chiang, Sidong Wang, Ira Hofer, Maxime Cannesson*, Eran Halperin*; [paper] [code]

“An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data” - British Journal of Anaesthesia (2019) - Brian L. Hill*, Robert Brown*, Eilon Gabel, Nadav Rakocz, Christine Lee, Maxime Cannesson, Pierre Baldi, Loes Olde Loohuis, Ruth Johnson, Brandon Jew, Uri Maoz, Aman Mahajan, Sriram Sankararaman, Ira Hofer, Eran Halperin; [paper] [preprint] [code]