Predictors of Recurrent AKI

Abstract

Recurrent AKI is common among patients after hospitalized AKI and is associated with progressive CKD. In this study, we identified clinical risk factors for recurrent AKI present during index AKI hospitalizations that occurred between 2003 and 2010 using a regional Veterans Administration database in the United States. AKI was defined as a 0.3 mg/dl or 50% increase from a baseline creatinine measure. The primary outcome was hospitalization with recurrent AKI within 12 months of discharge from the index hospitalization. Time to recurrent AKI was examined using Cox regression analysis, and sensitivity analyses were performed using a competing risk approach. Among 11,683 qualifying AKI hospitalizations, 2954 patients (25%) were hospitalized with recurrent AKI within 12 months of discharge. Median time to recurrent AKI within 12 months was 64 (interquartile range 19-167) days. In addition to known demographic and comorbid risk factors for AKI, patients with longer AKI duration and those whose discharge diagnosis at index AKI hospitalization included congestive heart failure (primary diagnosis), decompensated advanced liver disease, cancer with or without chemotherapy, acute coronary syndrome, or volume depletion, were at highest risk for being hospitalized with recurrent AKI. Risk factors identified were similar when a competing risk model for death was applied. In conclusion, several inpatient conditions associated with AKI may increase the risk for recurrent AKI. These findings should facilitate risk stratification, guide appropriate patient referral after AKI, and help generate potential risk reduction strategies. Efforts to identify modifiable factors to prevent recurrent AKI in these patients are warranted.

Keywords: acute renal failure; clinical epidemiology; outcomes.

Figure 1.

Cohort selection enriching for common causes of AKI and non-worsening AKI at discharge.

Figure 2.

Choice of baseline creatinine for index and recurrent AKI. The baseline for an index AKI event was defined using the mean outpatient serum creatinine 7–365 days prior to hospitalization. To account for potential trajectories of recovery, we defined the baseline for recurrent AKI as the nadir of either the most recent inpatient or outpatient serum creatinine or the admission serum creatinine of the subsequent hospitalization in which recurrent AKI occurred.

Figure 3.

Cumulative Incidence of First Event Experienced Among Survivors of Hospitalized AKI. The y-axis denotes the cumulative proportion of AKI survivors experiencing the event and the x-axis represents time in days on the upper line with the number of patients who have not experienced any event below it. Once a patient experiences any event, they are censored. (A) Cumulative incidence of hospitalization with recurrent AKI (solid line) or death/hospice referral (dash-dotted line) as the first event experienced. The corresponding numbers and proportions of patients experiencing each event are shown in Table 2. (B) Cumulative incidence of hospitalization with recurrent AKI (solid line) or death/hospice referral (dash-dotted line) as the first event experienced stratified by AKI stage. The corresponding numbers and proportions of patients experiencing each event are shown in Table 3. (C) Cumulative incidence of hospitalization with recurrent AKI (solid line), hospitalization without recurrent AKI (dashed line), or death/hospice referral (dashed-dotted line) as a first event experienced. The corresponding numbers and proportions of patients experiencing each event are shown in Table 4.

Figure 4.

Risk factors identified for recurrent AKI. (A) Forest plot indicating the aHR of risk factors for recurrent AKI using a Cox proportional hazards model. Confidence intervals that do not cross 1 denote statistical significance. The model was also adjusted for the following additional covariates whose associations with recurrent AKI were not statistically significant: (1) Demographics and comorbid conditions: hypertension, peripheral vascular disease, HIV infection, multiple myeloma, malignancy, and (2) Inpatient factors/discharge diagnoses: AKI severity, diabetic ketoacidosis/hyperosmotic nonketotic coma, rhabdomyolysis, multiple myeloma, severe sepsis, left heart catheterization, vascular surgeries, mechanical ventilation, intensive care unit stay, and length of stay. (B) Forest plot indicating the aHR of risk factors for recurrent AKI when recurrent AKI is defined using KDIGO stage II and III injury using a Cox proportional hazards model. Confidence intervals that do not cross 1 denote statistical significance. The model was also adjusted for the following additional covariates whose associations with recurrent AKI were not statistically significant: (1) Demographic and comorbid conditions: age, gender, race, baseline eGFR, coronary artery disease, diabetes mellitus, hypertension, peripheral vascular disease, multiple myeloma, malignancy, and (2) Inpatient factors/discharge diagnoses: congestive heart failure (primary diagnosis), diabetic ketoacidosis/hyperosmotic nonketotic coma, rhabdomyolysis, multiple myeloma, severe sepsis , left heart catheterization, cardiac surgeries, vascular surgeries, inpatient chemotherapy, mechanical ventilation, intensive care unit stay, and length of stay.