Harnessing Bronchoalveolar Lavage Metagenomics for Distinguishing Lung Cancer from Pulmonary Infectious Diseases

Recent progress in unbiased metagenomic next-generation sequencing (mNGS) allows simultaneous examination of microbial and host genetic material in a single test. Leveraging affordable bronchoalveolar lavage fluid (BALF) mNGS data, we employed machine learning to create a diagnostic approach distinguishing lung cancer from pulmonary infections, conditions prone to misdiagnosis in clinical settings. This prospective study analyzed BALF-mNGS data from lung cancer and pulmonary infection patients, delineating differences in DNA/RNA microbial composition, bacteriophage abundances, and host responses, including gene expression, transposable element levels, immune cell composition, and tumor fraction derived from copy number variation (CNV). Integrating these metrics into a host/microbe metagenomics-driven machine learning model (Model VI) demonstrated robustness, achieving an AUC of 0.87 (95% CI = 0.857-0.883), sensitivity = 73.8%, and specificity = 84.5% in the training cohort, and an AUC of 0.831 (95% CI = 0.819-0.843), sensitivity = 67.1%, and specificity = 94.4% in the validation cohort for distinguishing lung cancer from pulmonary infections. The application of a rule-in and rule-out strategy-based composite predictive model significantly enhances accuracy (ACC) in distinguishing between lung cancer and tuberculosis (ACC=0.913), fungal infection (ACC=0.955), and bacterial infection (ACC=0.836). These findings highlight the potential of cost-effective mNGS-based analysis as a valuable tool for early differentiation between lung cancer and pulmonary infections, offering significant benefits through a single comprehensive testing. This observational study assessed adults admitted to the First Affiliated Hospital, Zhejiang University School of Medicine, suspected of lung cancer or pulmonary infections. Enrollment occurred between March 8, 2020, and May 27, 2023, for patients aged ≥18, requiring BALF samples within 72 hours of intubation to establish the etiology. Exclusions involved cases with underlying leukemia, no definitive diagnosis post-extensive follow-up, or lacking matching DNA and RNA mNGS data from BALF samples. A total of 123 lung cancer, 279 pulmonary infections including tuberculosis, fungal, and bacterial infections. The diagnosis of lung cancer relies on clinical suspicion and positive laboratory results from tests cytology, flow cytometry and/or tissue biopsy. The diagnosis of pulmonary infections is based on clinical suspicion and determination of the causative pathogen through standard microbiological diagnostics (cultures, antigen/antibody tests, PCR, sequencing).