What question did this study set out to answer?

To assess the predictive performance of a locally trained sepsis model using different sepsis definitions.

April 10, 2026Open Access

Performance of a Sepsis Prediction Model Across Different Sepsis Definitions

Key Points

To assess the predictive performance of a locally trained sepsis model using different sepsis definitions.
Cohort study design
Utilized a locally trained sepsis prediction model
Evaluated model performance across various sepsis definitions
Analyzed metrics of discrimination, precision, and lead time
Model demonstrated moderate predictive performance
Discrimination, precision, and lead time varied significantly by sepsis definition
High false-positive rate observed, impacting clinical utility

Abstract

This cohort study found that the locally trained sepsis model showed moderate predictive performance, with discrimination, precision, and lead time varying considerably by the sepsis definition applied. Although the model provided some advance warning before sepsis onset, a high false-positive rate may limit its clinical utility without careful threshold selection and tailored implementation.

Connected Papers

Building similarity graph...

Analyzing shared references across papers

Discussion

Authors

S. Dutta

Reid McMurry

Michael C. Tasi

Journals

JAMA Network Open

Actions

Institutions

Harvard University

Brigham and Women's Hospital

Massachusetts General Hospital

References and Citations

Connected Papers

Building similarity graph...

Analyzing shared references across papers

Performance of a Sepsis Prediction Model Across Different Sepsis Definitions

Key Points

Abstract

Citation Network

Connected Papers

Discussion

Authors

Journals

Actions

Institutions

References and Citations

Citation Network

Connected Papers

Discussion

Cite this study