Lung cancer is the leading cause of malignancy-related mortality worldwide due to its heterogeneous features and diagnosis at a late stage. Artificial intelligence (AI) is good at handling a large volume of computational and repeated labor work and is suitable for assisting doctors in analyzing image-dominant diseases like lung cancer. Scientists have shown long-standing efforts to apply AI in lung cancer screening via CXR and chest CT since the 1960s. Several grand challenges were held to find the best AI model. Currently, the FDA have approved several AI programs in CXR and chest CT reading, which enables AI systems to take part in lung cancer detection. Following the success of AI application in the radiology field, AI was applied to digitalized whole slide imaging (WSI) annotation. Integrating with more information, like demographics and clinical data, the AI systems could play a role in decision-making by classifying EGFR mutations and PD-L1 expression. AI systems also help clinicians to estimate the patient’s prognosis by predicting drug response, the tumor recurrence rate after surgery, radiotherapy response, and side effects. Though there are still some obstacles, deploying AI systems in the clinical workflow is vital for the foreseeable future.

Lung cancer is the leading cause of cancer-related mortality worldwide, and its tumorigenesis involves the accumulation of genetic and epigenetic events in the respiratory epithelium. Epigenetic modifications, such as DNA methylation, RNA modification, and histone modifications, have been widely reported to play an important role in lung cancer development and in other pulmonary diseases. Whereas the functionality of DNA and chromatin modifications referred to as epigenetics is widely characterized, various modifications of RNA nucleotides have recently come into prominence as functionally important. N6-methyladosine (m6A) is the most prevalent internal modification in mRNAs, and its machinery of writers, erasers, and readers is well-characterized. However, several other nucleotide modifications of mRNAs and various noncoding RNAs have also been shown to play an important role in the regulation of biological processes and pathology. Such epitranscriptomic modifications play an important role in regulating various aspects of RNA metabolism, including transcription, translation, splicing, and stability. The dysregulation of epitranscriptomic machinery has been implicated in the pathological processes associated with carcinogenesis including uncontrolled cell proliferation, migration, invasion, and epithelial-mesenchymal transition. In recent years, with the advancement of RNA sequencing technology, high-resolution maps of different modifications in various tissues, organs, or disease models are being constantly reported at a dramatic speed. This facilitates further understanding of the relationship between disease development and epitranscriptomics, shedding light on new therapeutic possibilities. In this review, we summarize the basic information on RNA modifications, including m6A, m1A, m5C, m7G, pseudouridine, and A-to-I editing. We then demonstrate their relation to different kinds of lung diseases, especially lung cancer. By comparing the different roles RNA modifications play in the development processes of different diseases, this review may provide some new insights and offer a better understanding of RNA epigenetics and its involvement in pulmonary diseases.

Lung cancer (LC) causes the majority of cancer-related deaths. Circular RNAs (circRNAs) were reported to play roles in cancers by targeting pro- and anti-oncogenic miRNAs. However, the mechanisms of circRNAs in LC progression and their prognostic value of treatment response remain unclear. By using next generation sequencing (NGS) of LC cell lines’ transcriptomes, we identified highly overexpressed hsa_circ_0000190 and hsa_circ_000164 as potential biomarkers. By using the highly sensitive RT-ddPCR method, these circRNAs were shown to be secreted by cell lines and were detected in human blood. Clinical validation by RT-ddPCR was carried out on 272 (231 LC patients and 41 controls) blood samples. Higher hsa_circ_0000190 levels were associated with larger tumor size (p < 0.0001), worse histological type of adenocarcinoma (p = 0.0028), later stage (p < 0.0001), more distant metastatic organs (p = 0.0039), extrathoracic metastasis (p = 0.0004), and poor survival (p = 0.047) and prognosis. Using liquid biopsy-based RT-ddPCR, we discovered the correlation between increased hsa_circ_0000190 plasma level (p < 0.0001) and higher programmed death-ligand 1 (PD-L1) level in tumor (p = 0.0283). Notably, long-term follow-up of the immunotherapy treated cases showed that upregulated plasma hsa_circ_0000190 level correlated with poor response to systemic therapy and immunotherapy (p = 0.0002, 0.0058, respectively). Secretory circRNAs are detectable in blood by LB-based RT-ddPCR and may serve as blood-based biomarkers to monitor disease progression and treatment efficacy.

The possible association between pulmonary tuberculosis (TB) and lung cancer development has been studied for several decades. However, the association between epidermal growth factor receptor (EGFR) mutation status and pulmonary TB in patients with adenocarcinoma of the lungs is unknown. We reviewed the data of our patients with adenocarcinoma of the lungs who had a clinical history of pulmonary TB or old TB lesions shown on chest computed tomography scan and evaluated the association between tumor EGFR mutation status and pulmonary TB. From June 1999 to January 2011, there were 275 patients with pulmonary adenocarcinoma with tumor EGFR mutation data available for analysis. Of them, 191 patients had EGFR mutations, 17 had a clinical history of pulmonary TB infection, 72 had old TB lesions on chest computed tomography scans, and 14 had scar cancer. Patients with old TB lesions had a higher incidence of EGFR mutation than those without (p = 0.018). Exon 19 deletions occurred more frequently in patients with old TB lesions than in patients without (p < 0.001). Those patients with old TB lesions who had EGFR mutations or exon 19 mutations survived longer than those who did not (p = 0.014 and 0.001, respectively). Patients with exon 19 deletions and old TB lesions showed no survival difference compared with those with exon 19 deletions and without old TB lesions (p = 0.271). Patients with pulmonary adenocarcinoma who had scar cancer or had old TB lesions had a higher probability of having EGFR mutations, especially exon 19 deletions.