To the Editor When contrast agents are used in radiological examinations, there is a risk of contrast-induced nephropathy. To address this, Choi et al. developed a prediction model for contrast-induced nephropathy using machine learning technology (1). They included novel parameters, such as base excess and troponin, along with traditional clinical parameters. However, several concerns have been raised regarding this issue.
Most parameters used to calculate the risk model were blood test data, such as the hematocrit, with no urine parameters included (1). The renal tubule is a target of contrast-induced nephropathy, and urine parameters, such as liver-type fatty acid-binding proteins, have been shown to be helpful in assessing the vulnerability of the renal tubule and predicting the risk of contrast-induced nephropathy (2).
Volume expansion with normal saline or sodium bicarbonate is the mainstay of contrast-induced nephropathy (3). Whether or not these prophylactic procedures were performed before the present study is unclear.
The authors provided a risk model for estimating the risk of contrast-induced nephropathy on their website (http://52.78.230.235:8081/) (1). The upper limit of the N-terminal pro B-type natriuretic peptide was set at 999.9 pg/mL. However, many heart failure patients often have N-terminal pro B-type natriuretic peptide levels above this limit. Age appears to be the dominant determinant of this risk model; however, alteration of age for therapeutic intervention is deemed unfeasible. For scheduled procedures, we can attempt to reduce the contrast dose or avoid performing unnecessary procedures in high-risk patients, but we cannot avoid using contrast in urgent cases, such as those involving acute coronary syndrome. Thus, it is recommended to exclude urgent cases and assess only scheduled cases to construct a risk model.
The authors state that they have no Conflict of Interest (COI).
References
- 1. Choi H, Choi B, Han S, et al. Applicable machine learning model for predicting contrast-induced nephropathy based on pre-catheterization variables. Intern Med 63: 773-780, 2024. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2. Nakamura T, Sugaya T, Node K, Ueda Y, Koide H. Urinary excretion of liver-type fatty acid-binding protein in contrast medium-induced nephropathy. Am J Kidney Dis 47: 439-444, 2006. [DOI] [PubMed] [Google Scholar]
- 3. van der Molen AJ, Reimer P, Dekkers IA, et al. Post-contrast acute kidney injury. part 2: risk stratification, role of hydration and other prophylactic measures, patients taking metformin and chronic dialysis patients: recommendations for updated ESUR Contrast Medium Safety Committee guidelines. Eur Radiol 28: 2856-2869, 2018. [DOI] [PMC free article] [PubMed] [Google Scholar]