1. Improving lung cancer risk stratification leveraging whole transcriptome RNA sequencing and machine learning across multiple cohorts
- Author
-
Jianchang Ning, Jon McAuliffe, P. Sean Walsh, Daniel G. Pankratz, Lori Lofaro, Jianghan Qu, Marc E. Lenburg, Joshua E. Babiarz, Jing Huang, Yoonha Choi, Xinwu Yang, Giulia C. Kennedy, Shuyang Wu, Ehab Billatos, Jiarui Zhang, and Yangyang Hao
- Subjects
0301 basic medicine ,Oncology ,Male ,Lung Neoplasms ,Transcriptome ,0302 clinical medicine ,Bronchoscopy ,Registries ,Whole transcriptome RNA sequencing ,Genetics (clinical) ,medicine.diagnostic_test ,Multilevel model ,High-Throughput Nucleotide Sequencing ,Middle Aged ,Specimen collection ,030220 oncology & carcinogenesis ,Cohort ,Female ,Sample collection ,Lung cancer ,medicine.medical_specialty ,lcsh:Internal medicine ,lcsh:QH426-470 ,03 medical and health sciences ,Internal medicine ,Republic of Korea ,Exome Sequencing ,Machine learning ,Genetics ,medicine ,Humans ,Genetic Predisposition to Disease ,lcsh:RC31-1245 ,Risk stratification ,Aged ,Molecular diagnostic test ,Models, Genetic ,business.industry ,Sequence Analysis, RNA ,Research ,Gene Expression Profiling ,medicine.disease ,Human genetics ,lcsh:Genetics ,030104 developmental biology ,Gene expression ,business - Abstract
Background Bronchoscopy for suspected lung cancer has low diagnostic sensitivity, rendering many inconclusive results. The Bronchial Genomic Classifier (BGC) was developed to help with patient management by identifying those with low risk of lung cancer when bronchoscopy is inconclusive. The BGC was trained and validated on patients in the Airway Epithelial Gene Expression in the Diagnosis of Lung Cancer (AEGIS) trials. A modern patient cohort, the BGC Registry, showed differences in key clinical factors from the AEGIS cohorts, with less smoking history, smaller nodules and older age. Additionally, we discovered interfering factors (inhaled medication and sample collection timing) that impacted gene expressions and potentially disguised genomic cancer signals. Methods In this study, we leveraged multiple cohorts and next generation sequencing technology to develop a robust Genomic Sequencing Classifier (GSC). To address demographic composition shift and interfering factors, we synergized three algorithmic strategies: 1) ensemble of clinical dominant and genomic dominant models; 2) development of hierarchical regression models where the main effects from clinical variables were regressed out prior to the genomic impact being fitted in the model; and 3) targeted placement of genomic and clinical interaction terms to stabilize the effect of interfering factors. The final GSC model uses 1232 genes and four clinical covariates – age, pack-years, inhaled medication use, and specimen collection timing. Results In the validation set (N = 412), the GSC down-classified low and intermediate pre-test risk subjects to very low and low post-test risk with a specificity of 45% (95% CI 37–53%) and a sensitivity of 91% (95%CI 81–97%), resulting in a negative predictive value of 95% (95% CI 89–98%). Twelve percent of intermediate pre-test risk subjects were up-classified to high post-test risk with a positive predictive value of 65% (95%CI 44–82%), and 27% of high pre-test risk subjects were up-classified to very high post-test risk with a positive predictive value of 91% (95% CI 78–97%). Conclusions The GSC overcame the impact of interfering factors and achieved consistent performance across multiple cohorts. It demonstrated diagnostic accuracy in both down- and up-classification of cancer risk, providing physicians actionable information for many patients with inconclusive bronchoscopy.
- Published
- 2020