Not provided
| ID | Type | Description | Link |
|---|---|---|---|
| 1R01DK113191-01A1 | U.S. NIH Grant/Contract | View source |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) | NIH |
Not provided
Not provided
Not provided
Not provided
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.
Acute kidney injury (AKI) carries a significant, independent risk of mortality among hospitalized patients, but despite its association with poor clinical outcomes, AKI is asymptomatic and frequently overlooked by clinicians, with fewer than half of all AKI patients with documentation of the syndrome in the electronic medical record, which was associated with decreased rates of AKI clinical best practices.
Our research group recently conducted a large-scale multicenter randomized controlled trial of electronic alerts for AKI throughout the Yale New Haven Health System from 2018 to 2020 (ELAIA-1). Our study showed that, overall, alerting physicians to the presence of AKI did not demonstrate a difference in the rate of our primary outcome of progression of AKI, dialysis, or death, despite the alert leading to some process of care changes such as measurement of creatinine and urinalysis. There was, however, substantial heterogeneity among the study sites. The proliferation of alerting systems that are ineffective can lead to the phenomenon of alert fatigue, whereby providers tend to ignore alerts in a high-alert environment, and can have deleterious effects on patient care. Further, given the highly heterogenous nature of AKI, a more personalized approach to AKI alerting may be warranted.
Uplift modeling, commonly used in marketing, is a novel concept in the medical field and aims to determine phenotypic characteristics that predict a response (benefit or harm) to a given intervention. In this way, patients who are predicted to benefit most from an intervention are identified and preferentially targeted. Uplift modeling of alerting systems has the potential to both improve alert effectiveness through intelligent targeting, and reduce alert fatigue.
In this study, we will expand upon our prior AKI alert trial to determine prospectively whether the use of uplift modeling to preferentially target patients expected to benefit from an AKI alert will reduce the rates of AKI progression, dialysis and death among hospitalized patients with AKI. Inpatients at 4 teaching hospitals within the YNHH system with AKI, based on the Kidney Disease: Improving Global Outcomes (KDIGO) creatinine criteria, will be randomized to a "recommended" group (with higher scores receiving alerts and lower scores not receiving alerts as recommended) versus an "anti-recommended" group (with higher scores not receiving alerts and lower scores receiving alerts as anti-recommended). The primary outcome will be a composite of AKI progression, dialysis, or mortality within 14 days of randomization. Secondary outcomes will focus on AKI-specific process measures.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Recommended | Experimental | 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. |
|
| Anti-recommended | Experimental | 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. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Alert | Other | An alert informing the provider of the presence of acute kidney injury will be fired. |
|
| Measure | Description | Time Frame |
|---|---|---|
| Proportion of Patients With Progression to a Higher Stage of AKI OR Dialysis OR Death | Progression of AKI is defined as the increase in KDIGO stage from the time of randomization to the present. For patients who are discharged, we will impute 14-day creatinine using the last observation carried forward method. Dialysis is defined as the receipt of hemodialysis, continuous renal replacement therapy, or peritoneal dialysis. Isolated ultrafiltration treatments will not be included. Mortality will be determined from hospital administrative records. | Within 14 days from randomization |
| Measure | Description | Time Frame |
|---|---|---|
| 14-day Mortality | Proportion of patients who expire from any cause | Assessed from point of randomization to date of death within 14 days of randomization |
| Inpatient Mortality | Proportion of patients who expire from any cause |
Not provided
Inclusion Criteria:
Adults ≥ 18 years
Admitted to a participating hospital
Has AKI as defined by creatinine criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Affiliation | Role |
|---|---|---|
| Francis P Wilson, MD MSCE | Yale University | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Yale New Haven Hospital | New Haven | Connecticut | 06510 | United States |
Deidentified data underlying results for publication will be made available upon publication of results.
Upon publication of results; indefinitely
Not provided
Not provided
Not provided
Recruitment occurred at 4 hospital sites across the Yale New Haven Hospital System. Identification of eligible patient subjects was performed within the Epic electronic medical record system based on inclusion and exclusion criteria by an algorithm embedded into the best practice alert. Randomization occurred the moment the best practice build identified a patient as being eligible.
Not provided
| ID | Title | Description |
|---|---|---|
| FG000 | Recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
| FG001 | Anti-recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
| Title | Milestones | Reasons Not Completed | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Overall Study |
|
Not provided
Not provided
| ID | Title | Description |
|---|---|---|
| BG000 | Recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
| BG001 |
| Units | Counts |
|---|---|
| Participants |
|
| Title | Description | Population Description | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Denominator Units Selected | Denominators | Classes |
|---|---|---|---|---|---|---|---|---|---|
| Age, Continuous | Median |
| Type | Title | Description | Population Description | Reporting Status | Anticipated Posting Date | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Time Frame | Units Analyzed | Denominator Units Selected | Arm/Group Information | Denominators | Classes | Analyses | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Primary | Proportion of Patients With Progression to a Higher Stage of AKI OR Dialysis OR Death | Progression of AKI is defined as the increase in KDIGO stage from the time of randomization to the present. For patients who are discharged, we will impute 14-day creatinine using the last observation carried forward method. Dialysis is defined as the receipt of hemodialysis, continuous renal replacement therapy, or peritoneal dialysis. Isolated ultrafiltration treatments will not be included. Mortality will be determined from hospital administrative records. | Posted | Count of Participants | Participants | Within 14 days from randomization |
|
Adverse events were collected over the course of the enrollment period and data collection follow-up, out to one year post-randomization.
Not provided
Not provided
| ID | Title | Description | Deaths (Affected) | Deaths (At Risk) | Serious Events (Affected) | Serious Events (At Risk) | Other Events (Affected) | Other Events (At Risk) |
|---|---|---|---|---|---|---|---|---|
| EG000 | Recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
Not provided
Not provided
This trial was randomized at the patient level, introducing the possibility of bias towards the null. It was conducted within a single health system, limiting generalizability. The alert was largely informational with no patient-specific recommendations (not accounting for AKI heterogeneity).
| Title | Organization | Phone | Extension | |
|---|---|---|---|---|
| F. Perry Wilson | Yale University | 203-737-1704 | francis.p.wilson@yale.edu |
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot_SAP | Yes | Yes | No | Study Protocol and Statistical Analysis Plan | Feb 26, 2025 | Aug 12, 2025 | Prot_SAP_000.pdf |
Not provided
| ID | Term |
|---|---|
| D058186 | Acute Kidney Injury |
| ID | Term |
|---|---|
| D051437 | Renal Insufficiency |
| D007674 | Kidney Diseases |
| D014570 | Urologic Diseases |
| D052776 | Female Urogenital Diseases |
Not provided
Not provided
| ID | Term |
|---|---|
| D002110 | Caffeine |
| ID | Term |
|---|---|
| D014970 | Xanthines |
| D000470 | Alkaloids |
| D006571 | Heterocyclic Compounds |
| D011688 | Purinones |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Assessed from point of randomization to date of death from any cause, up to one year post-randomization |
| 14-day Dialysis | Proportion of patients who receive dialysis (hemodialysis, continuous renal replacement therapy, or peritoneal dialysis) | Assessed from point of randomization to date of first documented dialysis order, within 14 days of randomization |
| Inpatient Dialysis | Proportion of patients who receive dialysis (hemodialysis, continuous renal replacement therapy, or peritoneal dialysis) | Assess from point of randomization to date of first documented dialysis order during index hospitalization, up to one year post-randomization |
| Discharge on Dialysis | Assessed as active orders for dialysis at point of discharge from index hospitalization | Assessed at point of discharge from index hospitalization, up to one year post-randomization |
| Progression to Stage 2 AKI | Progression to Stage 2 AKI is defined as a doubling of serum creatinine between randomization and 14 days post randomization, and is considered a worsening of AKI. | Assessed from the date of randomization to 14 days post randomization |
| Progression to Stage 3 AKI | Progression to Stage 3 AKI is defined as a tripling of serum creatinine between the date of randomization and 14 days post randomization, and is considered a worsening of AKI. | Assessed from the date of randomization to 14 days post randomization |
| Duration of AKI | Defined as the time in hours between AKI onset and AKI cessation during index hospitalization | Assessed from the date of randomization to the cessation of AKI during index hospitalization, up to one year |
| 30 Day Readmission Rate | Proportion of patients with readmission within 30 days of index hospitalization discharge | Assessed from discharge date of index hospitalization to 30 days post discharge date |
| Index Hospitalization Cost | Total cost of index hospitalization | Assessed from point of randomization to date of discharge from index hospitalization, up to one year |
| Chart Documentation of AKI | Proportion of patients with chart documentation of AKI as assessed by post-discharge ICD-10 codes | Assessed from date of randomization to date of discharge from index hospitalization, up to one year |
| Proportion of AKI "Best Practices" Achieved Per Subject During Index Hospitalization | Contrast administration (de novo order of IV contrast agent within 24 hours of randomization), fluid administration (within 24 hours of randomization), aminoglycoside administration (de novo order within 24 hours of randomization), NSAID administration/cessation (de novo order or cessation of order/absence of de novo order of NSAID within 24 hours of randomization), ACE inhibitor administration/cessation, urinalysis order (with or without microscopy within 24 hours of randomization), documentation of AKI (by ICD-9 and ICD-10 codes during index hospitalization), monitoring of creatinine (at least one serum creatinine measurement within 36 hours of randomization), documentation of urine output (within 24 hours of randomization), renal consult order during index hospitalization. Each metric is binary. Outcome is reported as a composite best practice outcome representing the proportion of best practices achieved per subject. | 24 hours from randomization to discharge, up to one year post randomization |
| Anti-recommended |
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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
| BG002 | Total | Total of all reporting groups |
| Years |
|
| Sex/Gender, Customized | Count of Participants | Participants |
|
| Race/Ethnicity, Customized | Count of Participants | Participants |
|
| Creatinine mg/dL | Median | Inter-Quartile Range | mg/dL |
|
| Diastolic blood pressure (mmHg) | Median | Inter-Quartile Range | mmHg |
|
| Pulse (bpm) | Median | Inter-Quartile Range | beats per minute |
|
| Peripheral Capillary Oxygen Saturation (SpO2, %) | Median | Inter-Quartile Range | percent oxygen saturation |
|
| Systolic blood pressure (mmHg) | Median | Inter-Quartile Range | mmHg |
|
| OG001 | Anti-recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. |
|
|
| Secondary | 14-day Mortality | Proportion of patients who expire from any cause | Posted | Count of Participants | Participants | Assessed from point of randomization to date of death within 14 days of randomization |
|
|
|
| Secondary | Inpatient Mortality | Proportion of patients who expire from any cause | Posted | Count of Participants | Participants | Assessed from point of randomization to date of death from any cause, up to one year post-randomization |
|
|
|
| Secondary | 14-day Dialysis | Proportion of patients who receive dialysis (hemodialysis, continuous renal replacement therapy, or peritoneal dialysis) | Posted | Count of Participants | Participants | Assessed from point of randomization to date of first documented dialysis order, within 14 days of randomization |
|
|
|
| Secondary | Inpatient Dialysis | Proportion of patients who receive dialysis (hemodialysis, continuous renal replacement therapy, or peritoneal dialysis) | Posted | Count of Participants | Participants | Assess from point of randomization to date of first documented dialysis order during index hospitalization, up to one year post-randomization |
|
|
|
| Secondary | Discharge on Dialysis | Assessed as active orders for dialysis at point of discharge from index hospitalization | Posted | Count of Participants | Participants | Assessed at point of discharge from index hospitalization, up to one year post-randomization |
|
|
|
| Secondary | Progression to Stage 2 AKI | Progression to Stage 2 AKI is defined as a doubling of serum creatinine between randomization and 14 days post randomization, and is considered a worsening of AKI. | Posted | Count of Participants | Participants | Assessed from the date of randomization to 14 days post randomization |
|
|
|
| Secondary | Progression to Stage 3 AKI | Progression to Stage 3 AKI is defined as a tripling of serum creatinine between the date of randomization and 14 days post randomization, and is considered a worsening of AKI. | Posted | Count of Participants | Participants | Assessed from the date of randomization to 14 days post randomization |
|
|
|
| Secondary | Duration of AKI | Defined as the time in hours between AKI onset and AKI cessation during index hospitalization | Posted | Median | Inter-Quartile Range | Hours | Assessed from the date of randomization to the cessation of AKI during index hospitalization, up to one year |
|
|
|
| Secondary | 30 Day Readmission Rate | Proportion of patients with readmission within 30 days of index hospitalization discharge | Posted | Count of Participants | Participants | Assessed from discharge date of index hospitalization to 30 days post discharge date |
|
|
|
| Secondary | Index Hospitalization Cost | Total cost of index hospitalization | The data for this outcome were not collected and will not be accessed in the future. During outcome assessment, PIs were unable to get access to financial data to assess this outcome due to lack of institutional approval, therefore, no participants were analyzed. As this is the only financial-based outcome of the trial, this is the only outcome affected by this circumstance. | Posted | Assessed from point of randomization to date of discharge from index hospitalization, up to one year |
|
|
| Secondary | Chart Documentation of AKI | Proportion of patients with chart documentation of AKI as assessed by post-discharge ICD-10 codes | Posted | Count of Participants | Participants | Assessed from date of randomization to date of discharge from index hospitalization, up to one year |
|
|
|
| Secondary | Proportion of AKI "Best Practices" Achieved Per Subject During Index Hospitalization | Contrast administration (de novo order of IV contrast agent within 24 hours of randomization), fluid administration (within 24 hours of randomization), aminoglycoside administration (de novo order within 24 hours of randomization), NSAID administration/cessation (de novo order or cessation of order/absence of de novo order of NSAID within 24 hours of randomization), ACE inhibitor administration/cessation, urinalysis order (with or without microscopy within 24 hours of randomization), documentation of AKI (by ICD-9 and ICD-10 codes during index hospitalization), monitoring of creatinine (at least one serum creatinine measurement within 36 hours of randomization), documentation of urine output (within 24 hours of randomization), renal consult order during index hospitalization. Each metric is binary. Outcome is reported as a composite best practice outcome representing the proportion of best practices achieved per subject. | Posted | Median | Inter-Quartile Range | Proportion achieved per subject | 24 hours from randomization to discharge, up to one year post randomization |
|
|
|
| 169 |
| 1,002 |
| 0 |
| 1,002 |
| 0 |
| 1,002 |
| EG001 | Anti-recommended | 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. Alert: An alert informing the provider of the presence of acute kidney injury will be fired. | 185 | 1,044 | 0 | 1,044 | 0 | 1,044 |
Not provided
Not provided
Not provided
| D005261 |
| Female Urogenital Diseases and Pregnancy Complications |
| D000091642 | Urogenital Diseases |
| D052801 | Male Urogenital Diseases |
| D011687 |
| Purines |
| D006574 | Heterocyclic Compounds, 2-Ring |
| D000072471 | Heterocyclic Compounds, Fused-Ring |