Research ArticleCancer

Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases

See allHide authors and affiliations

Science Translational Medicine  11 Sep 2019:
Vol. 11, Issue 509, eaaw8513
DOI: 10.1126/scitranslmed.aaw8513

You are currently viewing the abstract.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution

Discriminating lung primary tumors and metastases

Pulmonary metastases of head and neck squamous cell carcinoma (HNSC) are currently difficult to distinguish from primary lung squamous cell carcinomas (LUSCs). Differentiating these tumor types has important clinical implications, as whether the lung tumor is primary or has spread can affect the treatment options offered to a patient. Here, Jurmeister et al. developed a machine learning algorithm that exploits the differential DNA methylation observed in primary LUSC and metastasized HNSC tumors in the lung. Their method was able to discriminate between these two tumor types with high accuracy across multiple cohorts, suggesting its potential as a clinical diagnostic tool.

Abstract

Head and neck squamous cell carcinoma (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we performed DNA methylation profiling of primary tumors and trained three different machine learning methods to distinguish metastatic HNSC from primary LUSC. We developed an artificial neural network that correctly classified 96.4% of the cases in a validation cohort of 279 patients with HNSC and LUSC as well as normal lung controls, outperforming support vector machines (95.7%) and random forests (87.8%). Prediction accuracies of more than 99% were achieved for 92.1% (neural network), 90% (support vector machine), and 43% (random forest) of these cases by applying thresholds to the resulting probability scores and excluding samples with low confidence. As independent clinical validation of the approach, we analyzed a series of 51 patients with a history of HNSC and a second lung tumor, demonstrating the correct classifications based on clinicopathological properties. In summary, our approach may facilitate the reliable diagnostic differentiation of pulmonary metastases of HNSC from primary LUSC to guide therapeutic decisions.

View Full Text