Predicting Chronic Kidney Disease After Cisplatin Treatment Using Population-Level Data

Area of Science:

• Nephrology
• Oncology
• Clinical Epidemiology

Background:

• Cisplatin is a vital chemotherapy agent with known nephrotoxicity.
• Chronic kidney disease (CKD) risk and predictability post-cisplatin are not well understood.
• Early identification of at-risk patients is crucial for intervention.

Purpose of the Study:

• To determine the incidence of CKD following cisplatin treatment.
• To evaluate the effectiveness of prediction models for post-cisplatin CKD.
• To identify key predictors of cisplatin-induced nephrotoxicity.

Main Methods:

• A population-based prognostic study utilizing retrospective and prospective cohorts.
• Development and validation of prediction models using demographics, clinical data, and patient-reported symptoms.
• Analysis of estimated glomerular filtration rate (eGFR) to assess kidney function outcomes.

Main Results:

• 13.6% of patients without pre-existing CKD developed CKD after cisplatin treatment.
• A simple spline regression model using only pre-treatment eGFR accurately predicted CKD risk.
• Complex machine learning models did not outperform the basic eGFR-based model.

Conclusions:

• Cisplatin treatment leads to a predictable decline in kidney function.
• Lower baseline eGFR is the primary risk factor for developing CKD post-cisplatin.
• An eGFR-based prediction model can guide clinical management and personalize patient care.