Baseline eGFR underpins the prediction of chronic kidney disease after cisplatin treatment in patients with non-haematological cancers, researchers report.

A Canadian study, published in JAMA Oncology [link here], extracted data on 9,521 patients who started cisplatin treatment between July 1, 2014, and June 30, 2020. Weekly cisplatin treatment with radiotherapy was the most common treatment regimen.

In a development cohort of half the patients, it found 13.6% of patients developed CKD after cisplatin treatment, with 380 (4.2%) progressing to grade 3b or worse and 81 (0.9%) progressing to grade 4 or worse.

“Compared with matched controls receiving other cancer treatments, cisplatin treatment was associated with an odds ratio of 2.46 (95% CI, 2.24-2.70; P < .001) for CKD and 2.63 (95% CI, 2.25-3.09; P < .001) for stage 3b or worse CKD,” it said.

“The mean decrease in the eGFR after cisplatin treatment was 8.1 mL/min/1.73 m 2 (95% CI, 7.8-8.4 mL/min/1.73 m 2 ) compared with 1.1 mL/min/1.72 m2 (95% CI, 0.8-1.4 mL/min/1.73 m2) in controls (P < .001.”

The study then used the data to train simple regressions and complex machine learning models to predict CKD and evaluated them in two cohorts – the other half of the original cohort and an external cohort.

In all models, pretreatment eGFR was the most influential factor – as those with the lowest pretreatment EGFR were mostly likely to develop CKD. Other variables such as creatine, cisplatin dosage, erythrocytes or line of therapy contributed little.

“In the temporal-test cohort, the AUROC of the univariable regression was 0.80 (95% CI, 0.78-0.82) for CKD, 0.78 (95% CI, 0.75-0.82) for grade 3b or worse CKD, and 0.72 (95% CI, 0.63-0.80) for grade 4 or worse CKD.”

“More complex ensemble machine learning models provided no meaningful gains over univariable regression, with AUROCs of 0.82 (95% CI, 0.80-0.84) for CKD, 0.80 (95% CI, 0.77-0.84) for grade 3b or worse CKD, and 0.76 (95% CI, 0.70-0.83) for grade 4 or worse CKD,” it said.

The investigators said their findings suggest that novel predictors beyond clinical characteristics, such as genetic variation, will be required to improve the prediction of CKD after cisplatin treatment.

“Despite a large sample size and extensive availability of predictive features, machine learning models did not outperform the simpler model based on the pretreatment eGFR alone.”

They concluded that pretreatment EGFR should be used in clinical practice to inform the consent process and guide cisplatin-induced nephrotoxicity prevention strategies.