Inpatient Hospitalization, Intensive Care Unit Admission, Inpatient Mortality, Sepsis and Septic Shock
Conditions
Brief summary
The primary objective of this study is to validate the use of an electronic clinical decision support (CDS) tool, TriageGO with Monocyte Distribution Width (TriageGO-MDW), in the emergency department (ED). TriageGO-MDW is non-device CDS designed to support emergency clinicians (nurses, physicians and advanced practice providers) in performing risk-based assessment and prioritization of patients during their ED visit. This study will follow an effectiveness-implementation hybrid design via the following three aims (phases), to be executed sequentially: (Aim 1) Validate the TriageGO-MDW algorithm locally using retrospective data at ED study sites. (Aim 2) Deploy TriageGO-MDW integrated with the electronic medical record (EMR) and perform user assessment. (Aim 3) Evaluate TriageGO-MDW in steady state with respect to clinical, process, and perceived utility outcomes.
Interventions
OTHERTriageGO-MDW Clinical Decision Support
TriageGO-MDW is non-device clinical decision support that provides patient-level clinical risk estimates based on clinical data derived from the electronic health record
OTHERUsual Care
Clinical care without decision support provided by TriageGo-MDW
Sponsors
University of Kansas
Beckman Coulter, Inc.
Truman Medical Center
Stocastic, LLC
Study design
Observational model
COHORT
Time perspective
OTHER
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
Adult patients receiving care at a study site ED
Exclusion criteria
None
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Viral Infection | baseline (pre-intervention) | Testing positive for influenza or Covid-19 (SARS-CoV-2) infection within 24 hours of ED arrival; Prediction performance of machine learning algorithms that underly TriageGO-MDW for this outcome will be measured |
| In-Hospital Mortality | baseline (pre-intervention) | Death during index hospital encounter; Prediction performance of machine learning algorithms that underly TriageGO-MDW for this outcome will be measured |
| Emergent Surgery | baseline (pre-intervention) | procedure in the operating room within 12 hours of ED arrival; Prediction performance of machine learning algorithms that underly TriageGO-MDW for this outcome will be measured |
| Sepsis | baseline (pre-intervention) | Prediction performance of machine learning algorithms that underlie TriageGO-MDW for this outcome will be measured |
| Septic Shock | baseline (pre-intervention) | Meeting septic shock criteria within 24 hours of ED arrival; Prediction performance of machine learning algorithms that underly TriageGO-MDW for this outcome will be measured |
| Critical Care | baseline (pre-intervention) | Admission to an intensive care unit within 24 hours of ED disposition; Prediction performance of machine learning algorithms that underly TriageGO-MDW for this outcome will be measured |
Other
| Measure | Time frame | Description |
|---|---|---|
| Hospital admission triage capture rate | baseline (pre-intervention) | Proportion of patients requiring hospital admission identified as moderate or high acuity at ED triage |
| ED patient flow metrics | baseline (pre-intervention) | Intervals between major ED care events, including arrival to disposition, arrival to treatment space, arrival to treatment provider, arrival to intensive care unit transfer, arrival to ED departure will be measured |
| Sepsis care quality metrics | baseline (pre-intervention) | Standard sepsis care quality metrics including time to diagnosis and treatment and rates of compliance with the Centers for Medicare and Medicaid Services (CMS) Sepsis-1 (SEP-1) Core Measure and its components will be measured |
| Critical care triage capture rate | baseline (pre-intervention) | Proportion of patients with critical care admission, emergency surgery or in-hospital mortality identified as high acuity at ED triage |
Countries
United States
Contacts
Primary ContactEric Hamrock
Outcome results
None listed