A Noninvasive Multianalytical Approach for Lung Cancer Diagnosis of Patients with Pulmonary Nodules

Abstract

Addressing the high false-positive rate of conventional low-dose computed tomography (LDCT) for lung cancer diagnosis, the efficacy of incorporating blood-based noninvasive testing for assisting practicing clinician's decision making in diagnosis of pulmonary nodules (PNs) is investigated. In this prospective observative study, next generation sequencing- (NGS-) based cell-free DNA (cfDNA) mutation profiling, NGS-based cfDNA methylation profiling, and blood-based protein cancer biomarker testing are performed for patients with PNs, who are diagnosed as high-risk patients through LDCT and subsequently undergo surgical resections, with tissue sections pathologically examined and classified. Using pathological classification as the gold standard, statistical and machine learning methods are used to select molecular markers associated with tissue's malignant classification based on a 98-patient discovery cohort (28 benign and 70 malignant), and to construct an integrative multianalytical model for tissue malignancy prediction. Predictive models based on individual testing platforms have shown varying levels of performance, while their final integrative model produces an area under the receiver operating characteristic curve (AUC) of 0.85. The model's performance is further confirmed on a 29-patient independent validation cohort (14 benign and 15 malignant, with power > 0.90), reproducing AUC of 0.86, which translates to an overall sensitivity of 80% and specificity of 85.7%.

Keywords: cfDNA methylation; cfDNA mutations; circulating tumor DNA; lung cancer diagnosis; machine learning; protein cancer biomarkers; pulmonary nodules.

Figure 1

Overview of the patient cohort used in our study.

Figure 2

Performance of various predictive models in forms of receiver operating characteristic (ROC) curves and area under curve (AUC) scores. The performance of various predictive models based on different feature sets, namely clinical features, protein biomarkers, cfDNA mutations, cfDNA methylation, and integrated multianalytical model, respectively. The ROC curves of models are shown as lines of different colors. AUC and the 95% CI of each model are shown in the legend. a) Models’ performance on the 98‐patient discovery cohort. b) Models’ performance on the 29‐patient independent validation cohort.

Figure 3

cfDNA methylation profiles of all patients in the discovery cohort and the independent validation cohort, represented using the 30‐MCB feature set. Colored bars indicate the average methylation level for the corresponding MCB.

Figure 4

Predictive outcome of various models in comparison to the gold standard pathology assessment on the independent validation cohort. Samples were sorted according to nodule length.

Figure 5

Performance comparison between PET/CT and our integrative multianalytical model, in forms of receiver operating characteristic (ROC) curves and area under curve (AUC) scores.