External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients.¶
Wong, A., Otles, E., Donnelly, J. P., Krumm, A., McCullough, J., DeTroyer-Cooley, O., Pestrue, J., et al. (2021). External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients. JAMA Internal Medicine, 181(8), 1065-1070.
Cited by¶
3 citations across 3 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Shortcut Learning
- In clinical prediction it is the sepsis-risk model that fires whenever a clinician has already ordered a sepsis workup, predicting the chart rather than the patient.
This sourceExternal validation of the Epic Sepsis Model; discrimination assessed relative to clinician recognition (antibiotic/culture/lactate orders), highlighting how such early-warning models can key on documentation/workup artifacts that track clinician suspicion rather than the patient's underlying state.
Supported in partVerified against the work's full text
Wong et al. find Epic Sepsis Model alerts tend to come after clinicians already act (first lactate, timely antibiotics), but do not report the model keying on workup orders.
“suggesting that ESM-driven alerts reflect the presence of sepsis already apparent to clinicians”
- In clinical prediction it is the sepsis-risk model that fires whenever a clinician has already ordered a sepsis workup, predicting the chart rather than the patient.
- Training Serving Skew
- The structurally identical analysis applies to an infantry company meeting an unfamiliar opposing doctrine and degraded comms, and to a sepsis protocol piloted with research nurses and high-fidelity monitoring that reverses when rolled out to community hospitals without either.
This sourceThe Epic Sepsis Model, deployed at hundreds of hospitals, showed poor discrimination and calibration on external validation — degraded performance when carried from development to ordinary deployment sites.
- The structurally identical analysis applies to an infantry company meeting an unfamiliar opposing doctrine and degraded comms, and to a sepsis protocol piloted with research nurses and high-fidelity monitoring that reverses when rolled out to community hospitals without either.
Domain-specific¶
- Distributional Blind Spot
- Epic's proprietary early-warning model was deployed across hundreds of U.S. hospitals to flag patients at risk of sepsis, carried by strong vendor-reported validation
This sourceThe widespread implementation of the proprietary Epic Sepsis Model at hundreds of US hospitals for sepsis prediction. The external validation of the Epic Sepsis Model among patients admitted to Michigan Medicine, the academic health system of the University of Michigan.
Supported in partVerified against the publisher's abstract
“The Epic Sepsis Model (ESM), a proprietary sepsis prediction model, is implemented at hundreds of US hospitals.”
- Epic's proprietary early-warning model was deployed across hundreds of U.S. hospitals to flag patients at risk of sepsis, carried by strong vendor-reported validation
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 2 of 3 citations: 2 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:43e18d47905e · see in the full table