Comparison of DNA methylation based classification models for precision diagnostics of central nervous system tumors.

Autor: Tran QT; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Breuer A; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Lin T; Clinical Biomarkers Lab, St. Jude Children's Research Hospital, Memphis, TN, USA., Tatevossian R; Clinical Biomarkers Lab, St. Jude Children's Research Hospital, Memphis, TN, USA., Allen SJ; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Clay M; Department of Pathology, University of Colorado School of Medicine, Aurora, CO, USA., Furtado LV; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Chen M; Department of Laboratory Medicine, Cleveland Clinic, Cleveland, OH, USA., Hedges D; Aster Insights, Tampa, FL, USA., Michael T; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Robinson G; Department of Oncology, St. Jude Children's Research Hospital, Memphis, TN, USA., Northcott P; Department of Developmental Neurobiology, St. Jude Children's Research Hospital, Memphis, TN, USA., Gajjar A; Department of Pediatric Medicine, St. Jude Children's Research Hospital, Memphis, TN, USA., Azzato E; Section of Molecular Genetic Pathology, Department of Laboratory Medicine, Robert J. Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic, Cleveland, OH, USA., Shurtleff S; Section of Molecular Genetic Pathology, Department of Laboratory Medicine, Robert J. Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic, Cleveland, OH, USA., Ellison DW; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA., Pounds S; Department of Biostatistics, St. Jude Children's Research Hospital, Memphis, TN, USA., Orr BA; Department of Pathology, St. Jude Children's Research Hospital, Memphis, TN, USA. brent.orr@stjude.org.
Jazyk: angličtina
Zdroj: NPJ precision oncology [NPJ Precis Oncol] 2024 Oct 02; Vol. 8 (1), pp. 218. Date of Electronic Publication: 2024 Oct 02.
DOI: 10.1038/s41698-024-00718-3
Abstrakt: As part of the advancement in therapeutic decision-making for brain tumor patients at St. Jude Children's Research Hospital (SJCRH), we developed three robust classifiers, a deep learning neural network (NN), k-nearest neighbor (kNN), and random forest (RF), trained on a reference series DNA-methylation profiles to classify central nervous system (CNS) tumor types. The models' performance was rigorously validated against 2054 samples from two independent cohorts. In addition to classic metrics of model performance, we compared the robustness of the three models to reduced tumor purity, a critical consideration in the clinical utility of such classifiers. Our findings revealed that the NN model exhibited the highest accuracy and maintained a balance between precision and recall. The NN model was the most resistant to drops in performance associated with a reduction in tumor purity, showing good performance until the purity fell below 50%. Through rigorous validation, our study emphasizes the potential of DNA-methylation-based deep learning methods to improve precision medicine for brain tumor classification in the clinical setting.
(© 2024. The Author(s).)
Databáze: MEDLINE