7
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Most cited references30

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Bias in error estimation when using cross-validation for model selection

          Background Cross-validation (CV) is an effective method for estimating the prediction error of a classifier. Some recent articles have proposed methods for optimizing classifiers by choosing classifier parameter values that minimize the CV error estimate. We have evaluated the validity of using the CV error estimate of the optimized classifier as an estimate of the true error expected on independent data. Results We used CV to optimize the classification parameters for two kinds of classifiers; Shrunken Centroids and Support Vector Machines (SVM). Random training datasets were created, with no difference in the distribution of the features between the two classes. Using these "null" datasets, we selected classifier parameter values that minimized the CV error estimate. 10-fold CV was used for Shrunken Centroids while Leave-One-Out-CV (LOOCV) was used for the SVM. Independent test data was created to estimate the true error. With "null" and "non null" (with differential expression between the classes) data, we also tested a nested CV procedure, where an inner CV loop is used to perform the tuning of the parameters while an outer CV is used to compute an estimate of the error. The CV error estimate for the classifier with the optimal parameters was found to be a substantially biased estimate of the true error that the classifier would incur on independent data. Even though there is no real difference between the two classes for the "null" datasets, the CV error estimate for the Shrunken Centroid with the optimal parameters was less than 30% on 18.5% of simulated training data-sets. For SVM with optimal parameters the estimated error rate was less than 30% on 38% of "null" data-sets. Performance of the optimized classifiers on the independent test set was no better than chance. The nested CV procedure reduces the bias considerably and gives an estimate of the error that is very close to that obtained on the independent testing set for both Shrunken Centroids and SVM classifiers for "null" and "non-null" data distributions. Conclusion We show that using CV to compute an error estimate for a classifier that has itself been tuned using CV gives a significantly biased estimate of the true error. Proper use of CV for estimating true error of a classifier developed using a well defined algorithm requires that all steps of the algorithm, including classifier parameter tuning, be repeated in each CV loop. A nested CV procedure provides an almost unbiased estimate of the true error.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            International Germ Cell Consensus Classification: a prognostic factor-based staging system for metastatic germ cell cancers. International Germ Cell Cancer Collaborative Group.

            Cisplatin-containing chemotherapy has dramatically improved the outlook for patients with metastatic germ cell tumors (GCT), and overall cure rates now exceed 80%. To make appropriate risk-based decisions about therapy and to facilitate collaborative trials, a simple prognostic factor-based staging classification is required. Collaborative groups from 10 countries provided clinical data on patients with metastatic GCT treated with cisplatin-containing chemotherapy. Multivariate analyses of prognostic factors for progression and survival were performed and models were validated on an independent data set. Data were available on 5,202 patients with nonseminomatous GCT (NSGCT) and 660 patients with seminoma. Median follow-up time was 5 years. For NSGCT the following independent adverse factors were identified: mediastinal primary site; degree of elevation of alpha-fetoprotein (AFP), human chorionic gonadotropin (HCG), and lactic dehydrogenase (LDH); and presence of nonpulmonary visceral metastases (NPVM), such as liver, bone, and brain. For seminoma, the predominant adverse feature was the presence of NPVM. Integration of these factors produced the following groupings: good prognosis, comprising 60% of GCT with a 91% (89% to 93%) 5-year survival rate; intermediate prognosis, comprising 26% of GCT with a 79% (75% to 83%) 5-year survival rate; and poor prognosis, comprising 14% of GCT (all with NSGCT) with a 48% (42% to 54%) 5-year survival rate. An easily applicable, clinically based, prognostic classification for GCT has been agreed on between all the major clinical trial groups who are presently active worldwide. This should be used in clinical practice and in the design and reporting of clinical trials to aid international collaboration and understanding.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              DNA repair pathways and cisplatin resistance: an intimate relationship

              The main goal of chemotherapeutic drugs is to induce massive cell death in tumors. Cisplatin is an antitumor drug widely used to treat several types of cancer. Despite its remarkable efficiency, most tumors show intrinsic or acquired drug resistance. The primary biological target of cisplatin is genomic DNA, and it causes a plethora of DNA lesions that block transcription and replication. These cisplatin-induced DNA lesions strongly induce cell death if they are not properly repaired or processed. To counteract cisplatin-induced DNA damage, cells use an intricate network of mechanisms, including DNA damage repair and translesion synthesis. In this review, we describe how cisplatin-induced DNA lesions are repaired or tolerated by cells and focus on the pivotal role of DNA repair and tolerance mechanisms in tumor resistance to cisplatin. In fact, several recent clinical findings have correlated the tumor cell status of DNA repair/translesion synthesis with patient response to cisplatin treatment. Furthermore, these mechanisms provide interesting targets for pharmacological modulation that can increase the efficiency of cisplatin chemotherapy.
                Bookmark

                Author and article information

                Journal
                JNCI Cancer Spectr
                JNCI Cancer Spectr
                jncics
                JNCI Cancer Spectrum
                Oxford University Press
                2515-5091
                June 2020
                23 April 2020
                23 April 2020
                : 4
                : 3
                : pkaa032
                Affiliations
                [p1 ]Department of Health Technology, Technical University of Denmark , Kgs. Lyngby, Denmark
                [p2 ]Department of Oncology, Copenhagen University Hospital , Copenhagen, Denmark
                [p3 ]Key Laboratory of Genetic Network Biology, Institute of Genetics and Developmental Biology, University of Chinese Academy of Sciences , Beijing, China
                [p4 ]Sino-Danish Center for Education and Research, Eastern Yanqihu campus, University of Chinese Academy of Sciences , Beijing, China
                Author notes
                Correspondence to: Jakob Lauritsen, MD, Department of Oncology, Copenhagen University Hospital, Copenhagen, Blegdamsvej 9, Copenhagen 2100, Denmark (e-mail: jakob.lauritsen@ 123456regionh.dk ).

                Sara L Garcia, Jakob Lauritsen and Zeyu Zhang contributed equally to this work.

                Author information
                http://orcid.org/0000-0002-2784-2318
                http://orcid.org/0000-0002-9985-174X
                http://orcid.org/0000-0002-8352-0663
                http://orcid.org/0000-0003-3475-9675
                http://orcid.org/0000-0002-4036-6408
                http://orcid.org/0000-0003-0173-2134
                http://orcid.org/0000-0002-9618-9180
                http://orcid.org/0000-0001-6841-6676
                Article
                pkaa032
                10.1093/jncics/pkaa032
                7315098
                32617516
                228e6e20-c33b-45dd-b483-5a1ff24e2215
                © The Author(s) 2020. Published by Oxford University Press.

                This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                Page count
                Pages: 8
                Funding
                Funded by: Idella Foundation;
                Funded by: Sino-Danish Center;
                Categories
                Article

                Comments

                Comment on this article