Jason Poulos

Postdoctoral Fellow, Brigham and Women's Hospital and Harvard Medical School

poulos [AT] berkeley.edu

Bio

I am a postdoctoral fellow at Brigham and Women's Hospital and Harvard Medical School, developing predictive models in medicine using electronic health records (EHRs). Specifically, I am working on a Patient-Centered Outcomes Research Institute (PCORI) funded project to create advanced deep learning models for analyzing EHR data to better predict patients at risk for diabetes treatment failure. This work involves developing transformer neural networks for prediction on static patient features and temporal measurements, with the goal of identifying patients at risk of poor glycemic control and uncovering temporal patterns predictive of adverse outcomes.

Beyond predictive modeling, my research spans multiple areas at the intersection of machine learning and causal inference. I work on extending causal inference methods for multi-valued treatments, developing Bayesian frameworks for adversarial machine learning, and applying recurrent neural networks to panel data for causal impact estimation. My work also includes evaluating deep learning approaches for missing data imputation in large-scale survey data.

Publications

Most recent publications on Google Scholar.

Revisiting Diabetes Risk of Olanzapine versus Aripiprazole for Serious Mental Illness Care

Denis Agniel, Sharon-Lise Normand, John Newcomer, Katya Zelevinsky, Jason Poulos, Jeannette Tsuei, Marcela Horvitz-Lennon

BJPsych Open, 2024

State-Building through Public Land Disposal? An Application of Matrix Completion for Counterfactual Prediction

Jason Poulos

Statistics and Public Policy, 2024

Targeted Learning in Observational Studies with Multi-Level Treatments: An Evaluation of Antipsychotic Drug Treatment Safety

Jason Poulos, Marcela Horvitz-Lennon, Katya Zelevinsky, Thomas Huijskens, Pooja Tyagi, Jiaju Yan, Jordi Diaz, Tudor Cristea-Platon, Sharon-Lise Normand

Statistics in Medicine, 2024

Antipsychotics and the Risk of Diabetes and Death among Adults with Serious Mental Illnesses

Jason Poulos, Sharon-Lise Normand, Katya Zelevinsky, John Newcomer, Denis Agniel, Haley Abing, Marcela Horvitz-Lennon

Psychological Medicine, 2023

Adversarial Machine Learning: Bayesian Perspectives

David Rios Insua, Roi Naveiro, Víctor Gallego, Jason Poulos

Journal of the American Statistical Association, 2023

Are Deep Learning Models Superior for Missing Data Imputation in Surveys? Evidence from an Empirical Comparison

Zhenhua Wang, Olanrewaju Akande, Jason Poulos, Fan Li

Survey Methodology, 2022

RNN-Based Counterfactual Prediction, with an Application to Homestead Policy and Public Schooling

Jason Poulos, Shuxi Zeng

Journal of the Royal Statistical Society (C), 2021

Character-Based Handwritten Text Transcription with Attention Networks

Rafael Valle, Jason Poulos

Neural Computing & Applications, 2021

Estimating Population Average Treatment Effects from Experiments with Noncompliance

Kellie Ottoboni, Jason Poulos

Journal of Causal Inference, 2020

Missing Data Imputation for Supervised Learning

Rafael Valle, Jason Poulos

Applied Artificial Intelligence, 2018

Revisiting Diabetes Risk of Olanzapine versus Aripiprazole for Serious Mental Illness Care

Denis Agniel, Sharon-Lise Normand, John Newcomer, Katya Zelevinsky, Jason Poulos, Jeannette Tsuei, Marcela Horvitz-Lennon

BJPsych Open, 2024

State-Building through Public Land Disposal? An Application of Matrix Completion for Counterfactual Prediction

Jason Poulos

Statistics and Public Policy, 2024

Targeted Learning in Observational Studies with Multi-Level Treatments: An Evaluation of Antipsychotic Drug Treatment Safety

Jason Poulos, Marcela Horvitz-Lennon, Katya Zelevinsky, Thomas Huijskens, Pooja Tyagi, Jiaju Yan, Jordi Diaz, Tudor Cristea-Platon, Sharon-Lise Normand

Statistics in Medicine, 2024

Antipsychotics and the Risk of Diabetes and Death among Adults with Serious Mental Illnesses

Jason Poulos, Sharon-Lise Normand, Katya Zelevinsky, John Newcomer, Denis Agniel, Haley Abing, Marcela Horvitz-Lennon

Psychological Medicine, 2023

Adversarial Machine Learning: Bayesian Perspectives

David Rios Insua, Roi Naveiro, Víctor Gallego, Jason Poulos

Journal of the American Statistical Association, 2023

Gender Gaps in Frontier Entrepreneurship? Evidence from 1901 Oklahoma Land Lottery Winners

Jason Poulos

Journal of Historical Political Economy, 2023

Are Deep Learning Models Superior for Missing Data Imputation in Surveys? Evidence from an Empirical Comparison

Zhenhua Wang, Olanrewaju Akande, Jason Poulos, Fan Li

Survey Methodology, 2022

RNN-Based Counterfactual Prediction, with an Application to Homestead Policy and Public Schooling

Jason Poulos, Shuxi Zeng

Journal of the Royal Statistical Society (C), 2021

Character-Based Handwritten Text Transcription with Attention Networks

Rafael Valle, Jason Poulos

Neural Computing & Applications, 2021

Amnesty Policy and Elite Persistence in the Postbellum South: Evidence from a Regression Discontinuity Design

Jason Poulos

Journal of Historical Political Economy, 2021

Estimating Population Average Treatment Effects from Experiments with Noncompliance

Kellie Ottoboni, Jason Poulos

Journal of Causal Inference, 2020

Land Lotteries, Long-Term Wealth, and Political Selection

Jason Poulos

Public Choice, 2019

Missing Data Imputation for Supervised Learning

Rafael Valle, Jason Poulos

Applied Artificial Intelligence, 2018

Vitæ

Full CV: PDF.

Design by Martin Saveski.