UW-Madison Critical Care Medicine Data Science Lab
@UW_ICU_DataSci
Followers
194
Following
41
Media
8
Statuses
139
Drs. Matthew Churpek, Anoop Mayampurath, and Majid Afshar lead our integrated data science lab, working to improve the care of hospitalized patients.
Madison, WI
Joined September 2020
We are excited to share our latest publication, 'Multivariate protein landscape of host response in hospitalised patients with suspected infection in the emergency department,' where we used 29 plasma proteins to map the multivariate host-response to infection. We discovered
0
0
3
0
0
1
Our Nature article "Current and future state of evaluation of LLMs for medical summarization tasks" https://t.co/5xClpaykV4 was spotlighted at @HeyEpic’s UGM 2025 Executive Address! 👏📷Shoutouts to @Majeans2011 of @uw_medicine Dr. Patterson @UWEmerMed, Emma Croxford UW BMI
nature.com
npj Health Systems - Current and future state of evaluation of large language models for medical summarization tasks
1
3
4
Sam Nycklemoe, mentor Dr. Anoop Mayampurath, team published in @AMIAinformatics on our pCART Explainer, a novel algorithm that highlights text within clinical notes to provide medically relevant context about deterioration alerts, improving explainability of the pCART model.
1
1
6
Come join us in the land of cheese and Epic! Applications are open now for our Clinical Informatics fellowship - work side by side with our team of >20 board certified Informaticists on a range of projects from AI to decision support. https://t.co/1S5MPwkDxe
medicine.wisc.edu
0
1
1
Grad Charlie Kotula, mentor Matt Churpek, & UW+ Loyola+UChicago team developed & compared novel multimodal deep learning models for early detection of deterioration in ward patients, illuminating potential utility of integrating clinical notes in deterioration prediction
0
1
2
Grad Sierra Strutz, mentor Anoop Mayampurath, UW + Loyola + UChicago +Northshore team developed a novel hospitalwide XGB model for the early detection of deterioration in children, thereby enabling a unified risk assessment throughout their hospital stays!
pubmed.ncbi.nlm.nih.gov
This retrospective cohort study describes the development of a novel hospitalwide model for continuously predicting the risk of critical events through the entirety of a child's stay. The model...
0
1
1
Pushing the boundaries of AI in medicine — from bedside implementation to continuous evaluation! #XGM2025 #AIinHealthcare #PDSQI9 #LLM #HealthIT
@Majeans2011 @UWInformatics @UWMadison @uw_medicine @UWEmerMed (4/4)
0
0
1
Even better? It’s open-source and automated — so health systems can scale trustworthy evaluation using an LLM-as-a-Judge. 🤖📷 https://t.co/UHiZpqwPN4
@Majeans2011 @UWInformatics @UWMadison
@uw_medicine @UWEmerMed (3/4)
github.com
Contribute to epic-open-source/evaluation-instruments development by creating an account on GitHub.
0
0
0
In less than a year, they’ve published three papers to address a critical gap in evaluating LLMs in healthcare - introducing the PDSQI-9, a validated instrument for LLM summarization. @Majeans2011 @UWInformatics @UWMadison
@uw_medicine @UWEmerMed
https://t.co/xklmgtwrSj (2/4)
git.doit.wisc.edu
GitLab Enterprise Edition
0
0
0
Big shoutout to Dr. Majid Afshar @Majeans2011 of @uw_medicine, Dr. Brian Patterson of @UWEmerMed, and PhD student Emma Croxford of UW BMI for representing @UWMadison at @HeyEpic’s XGM in front of hundreds at the Physician Advisory Council! 👏🎆 @UWInformatics (1/4)
3
2
7
Heading to XGM? We're happy to be sharing what we've been working on! @UW_ICU_DataSci @Majeans2011 @p_kleinschmidt @HamidEmamekhoo @uw_medicine @UWEmerMed @HeyEpic @heidi_twedt @DrJoelGordon @DrJasonDambach @NavinPathakMD
2
5
8
Way to go @Majeans2011 @NIDAnews
ICYMI: According to a new study led by @Majeans2011, associate professor, @uw_APCC, @UWInformatics, an #AI screening tool for #opioid use disorder helped reduce 30-day readmissions by 47% and over $100,000 in cost savings. Read the article: https://t.co/FgsRUsxzwk
0
0
1
See our @JAMA_current article by the @UW_ICU_DataSci, @PCCRG, @anzics! 2x RCTs + ML modeling = Individualized oxygenation targets -> improve survival of critically ill patients undergoing invasive mechanical ventilation.
jamanetwork.com
This cohort study examines whether peripheral oxygenation-saturation targets on mortality would differ by individual patient characteristics among 2 temporally and geographically distinct randomized...
0
1
1
See our @JMIR_AI article by Dr. Rahman & team! Chest X-rays hold hidden clues to patient deterioration. In a 22K-patient study, Densenet121 beat other models in predicting ICU transfer and patient mortality. Medical Imaging + AI = powerful early warning: https://t.co/jW0L5AbLY7
ai.jmir.org
Background: Early detection of clinical deterioration and timely intervention for hospitalized patients can improve patient outcomes. Existing early warning systems rely on variables from structured...
0
1
1
The latest @atscommunity Breathe Easy podcast features our own @uw_medicine Dr. Matthew Churpek MD, MPH, PhD, discussing "AI in Clinical Practice: The Future is Now": https://t.co/q2yjG0Ehck; and video: https://t.co/XpGQqvKVGH
@UWInformatics
0
3
7