Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation
Standard
Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation. / Leitheiser, Maximilian; Capper, David; Seegerer, Philipp; Lehmann, Annika; Schüller, Ulrich; Müller, Klaus-Robert; Klauschen, Frederick; Jurmeister, Philipp; Michael, Bockmayr.
In: J PATHOL, Vol. 256, No. 4, 04.2022, p. 378-387.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation
AU - Leitheiser, Maximilian
AU - Capper, David
AU - Seegerer, Philipp
AU - Lehmann, Annika
AU - Schüller, Ulrich
AU - Müller, Klaus-Robert
AU - Klauschen, Frederick
AU - Jurmeister, Philipp
AU - Michael, Bockmayr
N1 - This article is protected by copyright. All rights reserved.
PY - 2022/4
Y1 - 2022/4
N2 - In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic work-up for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models [random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), and support vector machine (SVM)] that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF = 83%, NN = 88%, LOGREG = SVM = 89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites, and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic work-up of HNSC-CUP. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
AB - In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic work-up for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models [random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), and support vector machine (SVM)] that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF = 83%, NN = 88%, LOGREG = SVM = 89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites, and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic work-up of HNSC-CUP. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
U2 - 10.1002/path.5845
DO - 10.1002/path.5845
M3 - SCORING: Journal article
C2 - 34878655
VL - 256
SP - 378
EP - 387
JO - J PATHOL
JF - J PATHOL
SN - 0022-3417
IS - 4
ER -