Model for predicting chronic kidney disease after cisplatin treatment for solid cancers

Cisplatin is a widely used treatment for cancer that can permanently damage the kidneys. The incidence and predictability of chronic kidney disease (CKD) following cisplatin treatment are poorly understood. A prognostic study in Ontario included 9010 patients receiving cisplatin for solid cancer. 1228 of these patients (13.6%) developed CKD, and estimated glomerular filtration rate (eGFR) decreased by a mean of 8.1 ml/min/1.73 m². A simple spline-based regression model based solely on the pretreatment eGFR achieved a similar predictive performance (AUC 0.80) as complex machine learning models incorporating many clinical features. The model was validated in an external cohort. The authors conclude that cisplatin treatment is associated with a predictable decrease in eGFR and that patients with lower baseline kidney function are most likely to develop CKD.