Assistant Professor of Medicine and Informatics

University of Pennsylvania

Biography

I am a pulmonary and critical care physician at the University of Pennsylvania Perelman School of Medicine, and core faculty member at the Palliative and Advanced Illness Research (PAIR) Center. My work seeks to translate innovations in artificial intelligence methods into bedside clinical decision support systems that alleviate uncertainty in critical clinical decisions. My research interests include clinical informatics, artificial intelligence, natural language processing, machine learning, population health, and pragmatic trials. I am also a Senior Fellow at the Leonard Davis Institute of Health Economics and the Penn Institute of Bioinformatics.

Interests
  • Pulmonary and Critical Care Medicine
  • Artificial Intelligence
  • Clinical Informatics
  • Natural Language Processing
  • Human-Machine Collaborative Decision Support
Education

  • MS in Health Policy Research, 2017

    University of Pennsylvania

  • MD, 2011

    Jefferson Medical College

  • AB in Physics, 2002

    Dartmouth College

Recent Posts

Net Benefit and Decision Curve Analysis in R - Some helpful functions
Background One of the challenges of developing clinical prediction models is deciding which one is best. Sometimes traditional performance measures such as the Brier score or C-statistic might be used to quantify to what extent one model performs better than another.
Last updated on Nov 30, 2022 9 min read r, gmish
Using MetaMap with Python to access the UMLS MetaThesaurus - A Quick Start Guide
The National Library of Medicine (NLM) created a tremendous resource called the Unified Medical Language Systems (UMLS). The UMLS is a suite of data and software resources that offers several tools for processing, representing, and analyzing biomedical text data.
Last updated on Feb 25, 2022 4 min read python, nlp
Comparison of bootstrapping approaches for identifying variance of predictive performance
Background Bootstrapping is a helpful technique for identifying the variance of an estimate in a given sample when no other data are available. In the case of the evaluation of clinical prediction models, bootstrapping can be used to estimate confidence intervals around performance metrics such as the Brier score, the c-statistic, and others.
Apr 25, 2019 4 min read blog, r, bootstrapping, predictive modeling
Evaluating the equivalence of different formulations of the scaled Brier score
Background The Brier Score is a composite measure of discrimination and calibration for a prediction model. The Brier Score is defined as \[ BS = \frac{1}{N} \sum (y_i - \hat y_i)^2, \]
Apr 23, 2019 4 min read brier score, predictive modeling
Building a recurrent neural network to predict time-series data with Keras in Python
Recurrent neural networks and their variants are helpful for extracting information from time series. Here’s an example using sample data to get up and running. I found the following other websites helpful in reading up on code examples:
Feb 15, 2018 2 min read keras, rnn, python
See all posts

Recent Publications

Quickly discover relevant content by filtering publications.
Alexander T. Moffett, Cole Bowerman, Sanja Stanojevic, Nwamaka D. Eneanya, Scott D. Halpern, Gary E. Weissman (2023). Global, Race-Neutral Reference Equations and Pulmonary Function Test Interpretation. JAMA Network Open 2023;6(6):e2316174..

PDF Cite DOI

Jacob Martin, Andrew Crane-Droesch, Folasade Lapite, Joseph Puhl, Tyler Kmiec, Jasmine Silvestri, Lyle Ungar, Bruce Kinosian, Blanca Himes, Rebecca Hubbard, Joshua Diamond, Vivek Ahya, Michael Sims, Scott Halpern, Gary Weissman (2021). Development and validation of a prediction model for actionable aspects of frailty in the text of clinicians’ encounter notes. Journal of the American Medical Informatics Association 2021;29(1):109-119..

PDF Cite DOI

Anica Law, Gary Weissman, Jack Iwashyna (2020). A Dangerous Myth: Does Speaking Imply Breathing?. Annals of Internal Medicine 2020;173(9):754-755..

PDF Cite DOI

Gary Weissman, Andrew Crane-Droesch, Corey Chivers, ThaiBinh Luong, Asaf Hanish, Michael Levy, Jason Lubken, Michael Becker, Michael Draugelis, George Anesi, PJ Brennan, Jason Christie, Bill Hanson, Mark Mikkelsen, Scott Halpern (2020). Locally Informed Simulation to Predict Hospital Capacity Needs During the COVID-19 Pandemic. Annals of Internal Medicine 2020;173(9):754-755..

PDF Cite DOI

Gary Weissman, Lyle Ungar, Michael Harhay, Katherine Courtright, Scott Halpern (2019). Construct validity of six sentiment analysis methods in the text of encounter notes of patients with critical illness. Journal of Biomedical Informatics 2019;89:114-121..

PDF Cite DOI

See all publications

Popular Topics