Comparing an Automated to a Conventional Sepsis Clinical Prediction Rule

Status

Withdrawn

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT01505478

Enrollment

Registered

2012-01-06

Start date

2012-07-31

Completion date

Unknown

Last updated

2017-04-05

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Sepsis

Keywords

Sepsis, Clinical Prediction Rule, Clinical Informatics, Machine Learning

Brief summary

The investigators will conduct a prospective cohort study to compare an automated sepsis severity score to a conventional clinical prediction rule to risk stratify patients admitted from the emergency department (ED) with suspected infection for 28 day in-hospital mortality.

Interventions

None listed

Study design

Observational model

COHORT

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Inclusion criteria

* All consecutive adult (age 18 or older) Emergency Department (ED) patients during the study period that have been admitted from the ED and identified by the treating clinician to have a suspected infection at the time of ED disposition will comprise our study population.

Exclusion criteria

* No patients will be excluded from the study.

Design outcomes

Primary

Measure	Time frame	Description
28 day in-hospital mortality	—	The primary endpoint is the AUC of a model to predict 28 day all cause in-hospital mortality. Patients discharged or transferred to another hospital before 28 days will be assumed to be alive at 28 days.

Secondary

Measure	Time frame	Description
ICU Admission	—	The secondary endpoint is ICU admission from the ED or within 24 hours from the floor.

Countries

United States

Outcome results