Improving lung cancer risk stratification leveraging whole transcriptome RNA sequencing and machine learning across multiple cohorts

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.

Analytical validation of the Percepta genomic sequencing classifier; an RNA next generation sequencing assay for the assessment of Lung Cancer risk of suspicious pulmonary nodules

“…The Percepta GSC score is used to refine a patient's pre-test risk stratification and a patient report is produced with the post-test risk. Assay performance was analyzed through reproducibility experiments and other studies demonstrating analytical sensitivity and analytical specificity using four clinical features (age, pack year, inhaled medication usage, and specimen collection timing) and 1232 gene features as inputs [14].…”

“…Based on annotated Ensembl genes, uniquely mapped reads were summarized using HTSeq [19]. The sequencing data was further filtered and normalized as described in [14].…”

“…Twelve percent of intermediate pre-test risk patients were reclassified as having high post-test risk of malignancy, with a positive predictive value of 65% (95% CI 44-82%). Additionally, 27% of high pre-test risk patients were reclassified to very high posttest risk with a positive predictive value of 91% (95% CI 78-97%) [14]. The clinical utility of up-classification of patients should be evident in decreased time to treatment or surgical resection.…”

Percepta Genomic Sequencing Classifier and decision-making in patients with high-risk lung nodules: a decision impact study

“…Percepta GSC provides functionality in all three categories of pretest risk, low (< 10%), intermediate (10-60%) and high (> 60%). It has the ability to risk re-stratify from low risk to very low risk of malignancy with an NPV of 100% and risk re-stratify from high risk to very high risk of malignancy with a positive predictive value (PPV) of 91.5% [14].…”

Percepta Genomic Sequencing Classifier And Decision-Making In Patients With High-Risk Lung Nodules: A Decision Impact Study

“…The Percepta Genomic Sequencing Classi er (Percepta GSC, Veracyte, Inc.) utilizes RNA sequencing of transcripts from 1,232 genes, as well as clinical factors, to improve classi er performance with both down-classi cation and up-classi cation of pre-test risk of malignancy. Percepta GSC provides functionality in all three categories of pre-test risk, low (< 10%), intermediate (10-60%) and high (> 60%), and has the ability to risk re-stratify from low risk to very low risk of malignancy with an NPV of 100% and risk re-stratify from high risk to very high risk of malignancy with a positive predictive value (PPV) of 91.5% (14).…”