Blood-based screening panel for lung cancer based on clonal hematopoietic mutations

Abstract

Abstract Background Early detection can significantly reduce mortality due to lung cancer. However, financial, and other barriers for the currently approved screening protocol (low dose computed tomography (CT) scan) have limited its uptake. Presented here is a blood-based screening panel based on clonal hematopoietic mutations. Mutations in tumor cells that inhibit immune destruction have been extensively studied. However, mutations in immune cells that may prevent an effective anti-tumor immune response remain relatively unstudied. Animal model studies suggest that clonal hematopoietic (CH) mutations in tumor infiltrating immune (TII) cells can modulate cancer progression, representing potential predictive biomarkers. The goal of this study was to determine if the clonal expansion of these mutations in blood samples could predict the occurrence of lung cancer. Methods A set of 98 potentially pathogenic CH mutations in TII cells were identified using sequencing data from lung cancer samples. These mutations were used as predictors to develop a logistic regression machine learning model. The model was tested on a set of 578 lung cancer and 545 non-cancer samples from 18 independent cohorts. Results The logistic regression model correctly classified lung cancer and non-cancer blood samples with 94.12% sensitivity (95% Confidence Interval: 92.20-96.04%) and 85.96% specificity (95% Confidence Interval: 82.98–88.95%). In addition, the model correctly classified 89.98% of lung cancer and 74.86% of non-cancer blood samples with high confidence (prediction probabilities of > 0.9 and < 0.1 for cancer, respectively). Conclusions Our results suggest that it may be possible to develop an accurate blood-based lung cancer screening panel. Unlike most other “liquid biopsies” currently under development, the assay presented here is based on standard sequencing protocols and uses a relatively small number of rationally selected mutations as predictors.