Elucidating the role of EPPK1 in lung adenocarcinoma development.

BACKGROUND: We recently found that epiplakin 1 (EPPK1) alterations were present in 12% of lung adenocarcinoma (LUAD) cases and were associated with a poor prognosis in early-stage LUAD when combined with other molecular alterations. This study aimed to identify a probable crucial role for EPPK1 in cancer development. METHODS: EPPK1 mRNA and protein expression was analyzed with clinical variables. Normal bronchial epithelial cell lines were exposed to cigarette smoke for 16 weeks to determine whether EPPK1 protein expression was altered after exposure. Further, we used CRISPR-Cas9 to knock out (KO) EPPK1 in LUAD cell lines and observed how the cancer cells were altered functionally and genetically. RESULTS: EPPK1 protein expression was associated with smoking and poor prognosis in early-stage LUAD. Moreover, a consequential mesenchymal-to-epithelial transition was observed, subsequently resulting in diminished cell proliferation and invasion after EPPK1 KO. RNA sequencing revealed that EPPK1 KO induced downregulation of 11 oncogenes, 75 anti-apoptosis, and 22 angiogenesis genes while upregulating 8 tumor suppressors and 12 anti-cell growth genes. We also observed the downregulation of MYC and upregulation of p53 expression at both protein and RNA levels following EPPK1 KO. Gene ontology enrichment analysis of molecular functions highlighted the correlation of EPPK1 with the regulation of mesenchymal cell proliferation, mesenchymal differentiation, angiogenesis, and cell growth after EPPK1 KO. CONCLUSIONS: Our data suggest that EPPK1 is linked to smoking, epithelial to mesenchymal transition, and the regulation of cancer progression, indicating its potential as a therapeutic target for LUAD.

Curating retrospective multimodal and longitudinal data for community cohorts at risk for lung cancer.

BACKGROUND: Large community cohorts are useful for lung cancer research, allowing for the analysis of risk factors and development of predictive models. OBJECTIVE: A robust methodology for (1) identifying lung cancer and pulmonary nodules diagnoses as well as (2) associating multimodal longitudinal data with these events from electronic health record (EHRs) is needed to optimally curate cohorts at scale. METHODS: In this study, we leveraged (1) SNOMED concepts to develop ICD-based decision rules for building a cohort that captured lung cancer and pulmonary nodules and (2) clinical knowledge to define time windows for collecting longitudinal imaging and clinical concepts. We curated three cohorts with clinical data and repeated imaging for subjects with pulmonary nodules from our Vanderbilt University Medical Center. RESULTS: Our approach achieved an estimated sensitivity 0.930 (95% CI: [0.879, 0.969]), specificity of 0.996 (95% CI: [0.989, 1.00]), positive predictive value of 0.979 (95% CI: [0.959, 1.000]), and negative predictive value of 0.987 (95% CI: [0.976, 0.994]) for distinguishing lung cancer from subjects with SPNs. CONCLUSION: This work represents a general strategy for high-throughput curation of multi-modal longitudinal cohorts at risk for lung cancer from routinely collected EHRs.

Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification.

The accuracy of predictive models for solitary pulmonary nodule (SPN) diagnosis can be greatly increased by incorporating repeat imaging and medical context, such as electronic health records (EHRs). However, clinically routine modalities such as imaging and diagnostic codes can be asynchronous and irregularly sampled over different time scales which are obstacles to longitudinal multimodal learning. In this work, we propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from routinely collected EHRs for SPN classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans. Our classifier is pretrained on 2,668 scans from a public dataset and 1,149 subjects with longitudinal chest CTs, billing codes, medications, and laboratory tests from EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs revealed a significant AUC improvement over a longitudinal multimodal baseline (0.824 vs 0.752 AUC), as well as improvements over a single cross-section multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741 AUC). This work demonstrates significant advantages with a novel approach for co-learning longitudinal imaging and non-imaging phenotypes with transformers. Code available at https://github.com/MASILab/lmsignatures.