M
Matthew M. Churpek
Researcher at University of Wisconsin-Madison
Publications - 179
Citations - 6189
Matthew M. Churpek is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Medicine & Internal medicine. The author has an hindex of 34, co-authored 127 publications receiving 3939 citations. Previous affiliations of Matthew M. Churpek include NorthShore University HealthSystem & University of Chicago.
Papers
More filters
Journal ArticleDOI
Quick Sepsis-related Organ Failure Assessment, Systemic Inflammatory Response Syndrome, and Early Warning Scores for Detecting Clinical Deterioration in Infected Patients outside the Intensive Care Unit.
Matthew M. Churpek,Ashley H. Snyder,Xuan Han,Sarah Sokol,Natasha N Pettit,Michael D. Howell,Dana P. Edelson +6 more
TL;DR: Commonly used early warning scores are more accurate than the qSOFA score for predicting death and ICU transfer in non‐ICU patients, and these results suggest that the qsoFA score should not replace general earlywarning scores when risk‐stratifying patients with suspected infection.
Journal ArticleDOI
Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards.
Matthew M. Churpek,Trevor C. Yuen,Christopher Winslow,David O. Meltzer,Michael W. Kattan,Dana P. Edelson +5 more
TL;DR: It is found that several machine learning methods more accurately predicted clinical deterioration than logistic regression and use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.
Journal ArticleDOI
Incidence and Prognostic Value of the Systemic Inflammatory Response Syndrome and Organ Dysfunctions in Ward Patients.
TL;DR: The findings suggest that screening ward patients using SIRS criteria for identifying those with sepsis would be impractical, and almost half of patients hospitalized on the wards developed SirS at least once during their ward stay.
Journal ArticleDOI
The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model
TL;DR: Readily available electronic health record data can be used to predict impending acute kidney injury prior to changes in serum creatinine with excellent accuracy across different patient locations and admission serum creat inine.
Journal ArticleDOI
Multicenter Development and Validation of a Risk Stratification Tool for Ward Patients
Matthew M. Churpek,Trevor C. Yuen,Christopher Winslow,Ari Robicsek,David O. Meltzer,Robert D. Gibbons,Dana P. Edelson +6 more
TL;DR: An accurate ward risk stratification tool using commonly collected electronic health record variables in a large multicenter dataset was developed and validated and was more accurate than the MEWS in the validation dataset for all outcomes.