AKI Alerts for Acute Kidney Injury

Overseen By Francis P Wilson, MD MSCE

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Yale University

Disqualifiers: Dialysis, ESKD, Kidney transplant, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Approved in 1 Jurisdiction This treatment is already approved in other countries

Compensation: Varies

Number of Visits: Unknown

4092 Participants Needed

Trial Summary

What is the purpose of this trial?

The primary objective of this study is to determine whether the use of uplift (also known as Conditional Average Treatment Effect - CATE) modeling to empirically identify patients expected to benefit the most from AKI alerting and to target AKI alerts to these patients will reduce the rates of AKI progression, dialysis, and mortality.

Do I have to stop taking my current medications for the AKI Alerts trial?

The trial protocol does not specify whether you need to stop taking your current medications.

What data supports the idea that AKI Alerts for Acute Kidney Injury is an effective treatment?

The available research shows mixed results about the effectiveness of AKI Alerts for Acute Kidney Injury. Some studies suggest that these alerts can help in recognizing the condition early, which is crucial for better outcomes. However, other studies, like the one conducted at Brandenburg Medical School, found that the alerts did not significantly improve important outcomes like reducing the need for dialysis or lowering in-hospital death rates. This suggests that while AKI Alerts might help in early detection, they may not always lead to better treatment results unless they are well-integrated with a clinical response plan. ^{1 2 3 4 5}

What safety data exists for AKI alert systems?

The safety data for AKI alert systems, also known as electronic alerts for acute kidney injury, is primarily focused on their impact on patient outcomes, recognition, and management of AKI. While these systems have been implemented in various electronic health records worldwide, the evidence of their benefit on outcomes remains uncertain. Studies have shown feasibility and some changes in AKI demographics and outcomes following their implementation, but major randomized trials have yet to conclusively demonstrate significant improvements in patient safety or outcomes. ^{1 4 6 7 8}

Is the treatment called AKI Alerts for Acute Kidney Injury a promising treatment?

Yes, AKI Alerts for Acute Kidney Injury are promising because they help doctors recognize kidney problems earlier, which can lead to better patient care and outcomes. ^{1 4 6 7 9}

Research Team

Francis Wilson, MD

Principal Investigator

Yale University

Eligibility Criteria

This trial is for adults over 18 who are hospitalized and have acute kidney injury (AKI) as shown by a significant rise in creatinine levels. It's not open to those already on dialysis, with very high initial creatinine, previous participation, hospice care, recent kidney transplant or opted out of health record research.

Inclusion Criteria

Admitted to a participating hospital

Your kidney function has declined based on specific levels of creatinine in your blood during a short period of time.

Exclusion Criteria

I was prescribed dialysis before my acute kidney injury.

I am currently enrolled in hospice care or receiving comfort-only treatments.

I had a kidney transplant less than 6 months ago.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Randomization and Intervention

Participants are randomized into 'recommended' or 'anti-recommended' groups based on uplift scores, and alerts are generated accordingly

14 days

Inpatient monitoring

Follow-up

Participants are monitored for AKI progression, dialysis, or mortality

14 days

Extended Follow-up

Participants are monitored for secondary outcomes such as AKI best practices and readmission rates

Up to one year

Treatment Details

Interventions

• Alert

Trial Overview The study tests if targeting AKI alerts using uplift modeling to patients most likely to benefit can reduce the worsening of AKI, need for dialysis, or death. The alert aims to prompt timely medical response when a patient's condition indicates risk.

Participant Groups

Group I: Recommended Experimental Treatment 1 Intervention

Those whose uplift score represents a probability of benefit greater than 0.5 will generate an alert, while those whose uplift score represents a probability of benefit less than 0.5 will not generate an alert.

Group II: Anti-recommended Experimental Treatment 1 Intervention

Those whose uplift score represents a probability of benefit greater than 0.5 will not generate an alert, while those whose uplift score represents a probability of benefit less than 0.5 will generate an alert.

Who Is Running the Clinical Trial?

Yale University

Lead Sponsor

Trials

1,963

Recruited

3,046,000+

National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)

Collaborator

Trials

2,513

Recruited

4,366,000+

Findings from Research

Recent advances in electronic alerts (e-alerts) for acute kidney injury (AKI) have shown promise, particularly with the implementation of a standardized detection algorithm in England that has demonstrated good diagnostic performance.

However, a recent randomized trial indicated that simply using text message e-alerts did not significantly change clinician behavior or improve patient outcomes, highlighting the need for effective communication methods and further research on interventions that can influence clinician actions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Recent developments in electronic alerts for acute kidney injury. Horne, KL., Selby, NM.[2022]

In a study involving 2413 hospitalized patients with acute kidney injury, the implementation of an automated electronic alert system did not lead to improved clinical outcomes, such as changes in creatinine levels, dialysis rates, or mortality, compared to usual care.

The results showed no significant differences in the severity of kidney injury or patient outcomes at 7 days, indicating that the alert system may not be effective in enhancing the management of acute kidney injury in a hospital setting.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automated, electronic alerts for acute kidney injury: a single-blind, parallel-group, randomised controlled trial. Wilson, FP., Shashaty, M., Testani, J., et al.[2023]

The implementation of a digitally enabled intervention for detecting and managing acute kidney injury (AKI) in hospitalized patients did not improve the primary outcome of renal function recovery by discharge, indicating that the intervention may need further refinement to enhance clinical effectiveness.

However, the intervention was associated with a significant reduction in healthcare costs by £2123 per patient and a notable decrease in the hospital-wide cardiac arrest rate, suggesting potential benefits in patient safety and cost efficiency.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Implementation of a Digitally Enabled Care Pathway (Part 1): Impact on Clinical Outcomes and Associated Health Care Costs. Connell, A., Raine, R., Martin, P., et al.[2023]

The implementation of a national electronic alert system for acute kidney injury (AKI) led to a significant decrease in 30-day mortality rates over four years, with a notable reduction in mortality from Year 1 to Year 4, indicating improved patient outcomes.

The study, which analyzed 193,838 AKI episodes in 132,599 patients, found that the alert system was particularly effective in community-acquired AKI cases, resulting in increased hospitalizations and better management of patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Acute kidney injury demographics and outcomes: changes following introduction of electronic acute kidney injury alerts-an analysis of a national dataset. Holmes, J., Donovan, K., Geen, J., et al.[2021]

The implementation of an AKI alert system at Brandenburg Hospital did not significantly improve key outcomes such as in-hospital mortality or kidney function recovery in patients with acute kidney injury, despite a higher rate of correct alerts in the second period.

However, the need for kidney replacement therapy increased significantly from 14% in the first period to 34.4% in the second period, suggesting that while the alert system did not improve overall outcomes, it may have led to more aggressive management of AKI cases.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Electronic acute kidney injury alert at the Brandenburg Medical School - implementation and follow-up. Assem, A., Safi, W., Ritter, O., et al.[2023]

The introduction of electronic alerts for Acute Kidney Injury (AKI) significantly reduced the progression to higher AKI stages, emergency readmissions, and in-hospital deaths, indicating improved patient safety.

Following the e-alert implementation, there was an increase in the appropriate management of AKI, including more frequent stopping of high-risk drug prescriptions and increased ICU admissions, suggesting enhanced clinical management.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Does acute kidney injury alerting improve patient outcomes? Atia, J., Evison, F., Gallier, S., et al.[2023]

A systematic review of six studies involving 10,165 hospitalized patients found that electronic alerts (e-alerts) for acute kidney injury (AKI) did not significantly improve patient mortality or reduce the need for renal replacement therapy.

While some isolated studies showed improvements in specific care processes, the overall impact of e-alerts on patient outcomes was minimal, indicating a need for further research to enhance their effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Association between e-alert implementation for detection of acute kidney injury and outcomes: a systematic review. Lachance, P., Villeneuve, PM., Rewa, OG., et al.[2022]

Current randomized trials indicate that electronic alerts (eAlerts) for acute kidney injury (AKI) do not significantly reduce mortality rates, suggesting that while they are useful, they may not directly save lives.

However, eAlerts have shown potential in reducing the incidence, progression, and duration of AKI, indicating that they can improve the overall management and care of patients with this condition.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Electronic alerts in acute kidney injury: why does evidence of benefit remain elusive? Horne, K., Noble, R., Karelia, S., et al.[2023]

The introduction of automated acute kidney injury (AKI) electronic alerts in the Tayside region did not significantly change the rate or severity of AKI, nor did it improve 30-day mortality rates among patients with AKI, based on an analysis of 32,320 episodes over four years.

However, there was a small reduction in the number of occupied hospital bed days per patient, suggesting that while the alerts did not enhance clinical outcomes, they may have contributed to more efficient hospital resource use.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Impact of electronic alerts for acute kidney injury on patient outcomes: interrupted time-series analysis of population cohort data. Baird, D., De Souza, N., Logan, R., et al.[2022]

References

1. United States pubmed.ncbi.nlm.nih.gov

Recent developments in electronic alerts for acute kidney injury. [2022]

2. England pubmed.ncbi.nlm.nih.gov

Automated, electronic alerts for acute kidney injury: a single-blind, parallel-group, randomised controlled trial. [2023]

3. Canada pubmed.ncbi.nlm.nih.gov

Implementation of a Digitally Enabled Care Pathway (Part 1): Impact on Clinical Outcomes and Associated Health Care Costs. [2023]

4. England pubmed.ncbi.nlm.nih.gov

Acute kidney injury demographics and outcomes: changes following introduction of electronic acute kidney injury alerts-an analysis of a national dataset. [2021]

5. Switzerland pubmed.ncbi.nlm.nih.gov

Electronic acute kidney injury alert at the Brandenburg Medical School - implementation and follow-up. [2023]

6. England pubmed.ncbi.nlm.nih.gov

Does acute kidney injury alerting improve patient outcomes? [2023]

7. England pubmed.ncbi.nlm.nih.gov

Association between e-alert implementation for detection of acute kidney injury and outcomes: a systematic review. [2022]

8. England pubmed.ncbi.nlm.nih.gov

Electronic alerts in acute kidney injury: why does evidence of benefit remain elusive? [2023]

9. England pubmed.ncbi.nlm.nih.gov

Impact of electronic alerts for acute kidney injury on patient outcomes: interrupted time-series analysis of population cohort data. [2022]