Development and Validation of a Risk Model for Predicting Contrast-Associated Acute Kidney Injury in Patients With Cancer: Evaluation in Over 46,000 CT Scans.

Background: Patients with cancer undergo frequent CT examinations using iodinated contrast media and may be uniquely predisposed to contrast-associated acute kidney injury (CA-AKI). Objective: To develop and validate a model for predicting the risk of CA-AKI after contrast-enhanced CT in patients with cancer. Methods: This retrospective study included 25,184 adult patients (mean age, 62.3±13.7 years; 12,153 men, 13,031 women) with cancer who underwent 46,593 contrast-enhanced CT scans between January 1, 2016 and June 20, 2020 at one of three academic medical centers. Information was recorded regarding demographics, malignancy type, medication use, baseline laboratory values, and comorbidities. CA-AKI was defined as a ≥0.3-mg/dl increase in serum creatinine from baseline within 48 hours after CT or a ≥1.5-fold increase to the peak measurement within 14 days after CT. Multivariable models accounting for correlated data were used to identify risk factors for CAAKI. A risk score for predicting CA-AKI was created in a development set (n=30,926) and tested in a validation set (n=15,667). Results: CA-AKI occurred after 5.8% (2682/46,593) of scans. The final multivariable model for predicting CA-AKI included hematologic malignancy, diuretic use, angiotensin-converting enzyme inhibitor or angiotensin receptor blocker use, chronic kidney disease (CKD) stage IIIa, CKD stage IIIb, CKD stage IV or V, serum albumin <3.0 g/dl, platelet count <150 K/mm3, ≥1+ proteinuria on baseline urinalysis, diabetes mellitus, heart failure, and contrast media volume ≥100 ml. A risk score (range, 0-53 points) was created using these variables [most points (13) for CKD stage IV or V, or albumin <3 g/dl]. CA-AKI progressively increased in frequency at higher risk categories. For example, in the validation set, CA-AKI occurred after 2.2% of scans in the lowest risk category (score ≤4) and after 32.7% of scans in the highest risk category (score ≥30). Hosmer-Lemeshow test indicated that the risk score was a good fit (p=.40). Conclusion: This study demonstrates the development and validation of a risk model using readily available clinical data to predict the likelihood of CA-AKI after contrast-enhanced CT in patients with cancer. Clinical Impact: The model may help facilitate appropriate implementation of preventive measures among patients at high risk for CA-AKI.