Acute Kidney Injury (AKI)
Conditions
Keywords
Acute Kidney Injury, Decision Support Systems, Clinical, Artificial Intelligence
Brief summary
Acute kidney injury (AKI) affects up to 20% of hospitalized Veterans and is strongly associated with morbidity and death. AKI is a diverse condition and timely and accurate diagnosis of the type of AKI is critical to begin appropriate therapies, especially those causes that require specific treatments beyond general supportive care. Yet, there are still significant gaps in the initial evaluation of AKI among hospitalized patients. Clinical decision support systems (CDSS) have shown promise to address these barriers, but most consist of simple alerting schemes and general care recommendations provided at a single point in time. The goal of this proposal is to develop and test the feasibility and usability of a rule-based and Artificial Intelligence-assisted precision CDSS tool (PRECISE-AKI) that can provide cognitive support to improve timely initial diagnostic evaluation of AKI.
Detailed description
Acute kidney injury (AKI), defined as a sudden loss of kidney function, affects up to 20% of hospitalized Veterans and is strongly associated with chronic kidney disease, poor quality of life, and death. Clinical practice guidelines recommend timely identification of the cause of AKI, but gaps remain in conducting the initial and subsequent diagnostic evaluation. Some causes of AKI also require specific treatments beyond supportive care, can be challenging to diagnose, and can require even more detailed evaluation including kidney biopsies. This clinical trial will evaluate the usability and feasibility of an Artificial Intelligence (AI)-assisted automated and comprehensive precision CDSS tool (PRECISE-AKI) to provide iterative cognitive support of general and nephrology-based providers in the diagnostic evaluation of hospitalized patients experiencing AKI within the Tennessee Valley Health Systems (TVHS). The investigators hypothesize that PRECISE-AKI will be acceptable, appropriate, and feasible to a variety of users and improve the diagnostic evaluation of hospitalized patients AKI.
Interventions
OTHERPRECISE-AKI Clinical Decision Support Tool
The Intervention arm will consist of Clinical Decision Diagnostic Support (CDS) provided by the PRECISE-AKI tool
Sponsors
VA Tennessee Valley Health Care System
Vanderbilt University Medical Center
VA Office of Research and Development
Study design
Allocation
NON_RANDOMIZED
Intervention model
CROSSOVER
Primary purpose
OTHER
Masking
SINGLE (Outcomes Assessor)
Masking description
It is not possible to blind clinicians. Study data will be extracted by staff blinded to assignment.
Intervention model description
Pre-/Post- design
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Eligible providers will be those that have at least 4 weeks of inpatient ward team or consultation team activity during a 12-month period. * Case inclusion criteria will consist of hospitalizations that meet criteria for Kidney Disease Improving Global Outcomes Stage 2 injury or persistent Stage 1 injury seen by eligible providers.
Exclusion criteria
* Ineligible providers will be those that have \< 4 weeks of inpatient ward team of consultative team activity during a 12 month period. * Hospitalizations with non-persistent (\<48 hours) stage 1 injury or less.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Rates of Appropriate Diagnostic Testing | Up to 30 days | Based on the presenting context, the investigators will compare rates of appropriate diagnostic testing between intervention and control patients among those meeting the AKI case definition |
Other
| Measure | Time frame | Description |
|---|---|---|
| Exploratory Clinical Outcome: Peak Kidney Disease Improving Global Outcomes (KDIGO) AKI Stage during hospitalization. | During Index Hospitalization through 30 days | For this exploratory clinical outcome, we will compare differences in the peak KDIGO AKI Stage (creatinine-based criteria) during hospitalization after meeting the case definition of AKI between intervention and control cases. |
| Exploratory Clinical Outcome: Discharge serum creatinine | Last serum creatinine during index hospitalization through 30 days | The investigators will compare differences in the hospital discharge serum creatinine after meeting the case definition of AKI between intervention and control cases. |
| Exploratory Clinical Outcome: Major Adverse Kidney Events (MAKE) 90 | 90 days | For this exploratory clinical outcome, the investigators will compare the rates of the major adverse kidney events experienced by eligible AKI cases in the intervention compared with the control arm. Major Adverse Kidney Events will be defined as kidney replacement therapy, death, or an increase in baseline serum creatinine of 150% of baseline using the last serum creatinine available up to 90 days. |
Countries
United States
Contacts
Primary ContactEdward D Siew, MD MSc
Backup ContactMichael E Matheny, MD MS MPH
Outcome results
None listed