Prediction of Nephrotoxicity Associated With Cisplatin-Based Chemotherapy in Testicular Cancer Patients

Abstract

Background Cisplatin-based chemotherapy may induce nephrotoxicity. This study presents a random forest predictive model that identifies testicular cancer patients at risk of nephrotoxicity before treatment. Methods Clinical data and DNA from saliva samples were collected for 433 patients. These were genotyped on Illumina HumanOmniExpressExome-8 v1.2 (964 193 markers). Clinical and genomics-based random forest models generated a risk score for each individual to develop nephrotoxicity defined as a 20% drop in isotopic glomerular filtration rate during chemotherapy. The area under the receiver operating characteristic curve was the primary measure to evaluate models. Sensitivity, specificity, and positive and negative predictive values were used to discuss model clinical utility. Results Of 433 patients assessed in this study, 26.8% developed nephrotoxicity after bleomycin-etoposide-cisplatin treatment. Genomic markers found to be associated with nephrotoxicity were located at NAT1, NAT2, and the intergenic region of CNTN6 and CNTN4. These, in addition to previously associated markers located at ERCC1, ERCC2, and SLC22A2, were found to improve predictions in a clinical feature–trained random forest model. Using only clinical data for training the model, an area under the receiver operating characteristic curve of 0.635 (95% confidence interval [CI] = 0.629 to 0.640) was obtained. Retraining the classifier by adding genomics markers increased performance to 0.731 (95% CI = 0.726 to 0.736) and 0.692 (95% CI = 0.688 to 0.696) on the holdout set. Conclusions A clinical and genomics-based machine learning algorithm improved the ability to identify patients at risk of nephrotoxicity compared with using clinical variables alone. Novel genetics associations with cisplatin-induced nephrotoxicity were found for NAT1, NAT2, CNTN6, and CNTN4 that require replication in larger studies before application to clinical practice.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

“…14,15 15 (44%) of 34 studies assessed the performance of a single AI model. 13,14,16,17,20,26,[30][31][32]34,36,37,41,42,44 The other studies compared the performance of multiple models with neural networks and tree-based algorithms demonstrating the best performance based on accuracy and AUC-ROC, or other metrics reported in the studies. One study showed similar performance between federated learning (ie, training algorithms using multiple decentralised databases) and centralised approaches for development of AI-based ADE prediction models.…”

“…13 (19%) of 67 studies included genetic variables to develop prediction models. [41][42][43][44][45][47][48][49][50][74][75][76][77] Most studies including genetic information (nine [69%] of 13) were conducted using secondary research data and compared the performance of multiple AI algorithms. Genetic information was extracted from genetic variant genotyping data and expression profiles.…”

“…41,76 In eight studies, both genetic and clinical factors were combined as model input variables. [42][43][44][45]47,[74][75][76] In most cases, genetic factors were found to be associated with outcomes and contributed to the model performance. In two studies, the value of adding genetic variables was evaluated.…”

“…In two studies, the value of adding genetic variables was evaluated. 42,43 In a study predicting nephrotoxicity, adding genetic variables increased the AUC-ROC from 0•64 to 0•73. 42 Although genetic features often improved model performance, non-significant results were also reported.…”

“…42,43 In a study predicting nephrotoxicity, adding genetic variables increased the AUC-ROC from 0•64 to 0•73. 42 Although genetic features often improved model performance, non-significant results were also reported. 43 Multiple studies used machine learning methods to identify genetic factors associated with ADEs, including single nucleotide polymorphisms (SNPs) and related genes.…”