Matthew Churpek
University of Wisconsin-Madison, WI·Medicine & Clinical Research
Sepsis is a life-threatening failure of organs caused by the body's response to infection. More than 1.7 million people in the United States develop it each year.
- Fields
Medicine & Clinical Research
Computer Science
Public Health & Epidemiology
- Topics
sepsis
infection
critical care
- Grants
- 1 known grant, through Feb 2027
What they work on
- Improve early identification and risk stratification of infected hospital patients by applying natural language processing and deep learning to structured and free-text electronic health record data from multiple centers.
- Discover sepsis subphenotypes, patient subgroups with distinct biology, by combining research biomarker data with clinical data from health records and trials.
- Develop personalized sepsis treatment algorithms with machine learning, building on the lab's eCART risk tool already deployed in over 20 hospitals.
More about the research
It may contribute to up to half of hospital deaths, and survivors often face lasting memory problems and disability. Care is held back by three problems: infected patients are often recognized late, doctors misjudge who will become critically ill, and treatment is one-size-fits-all even though patients differ widely. This research uses hospital data and machine learning to address all three.
Why it matters
Sepsis kills many hospitalized patients and costs more than $24 billion in U.S. health care each year. Earlier detection, more accurate risk prediction and treatment tailored to patient subgroups could reduce preventable illness and death from infection. Algorithms built here could be used in hospitals to help clinicians act sooner and choose care that fits each patient.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Gabriel Wardi
University of California-San Diego, CA·Medicine & Clinical Research·Early-career
Identify clinical phenotypes, or distinct patient subgroups, of sepsis that develops after hospital admission, using deep-learning analysis of electronic health record data.
Jennifer A Kim
Yale University, CT·Medicine & Clinical Research
Develop an algorithm that identifies post-traumatic epilepsy patients from electronic health records, and predict future PTE risk from the first seven days after TBI using structured data and natural language processing of clinical notes.
Yair Bannett
Stanford University, CA·Medicine & Clinical Research·Early-career
Develop guideline-based quality measures for primary care treatment of children aged 4–11 with ADHD, combining machine learning analysis of free-text clinical notes with structured electronic health record data.
The school
University of Wisconsin-Madison: 91 labs on PI Pages, $1.9B a year on research, 854 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.