Purpose: Personalized treatments such as targeted therapy and immunotherapy have revolutionized the predominantly therapeutic paradigm for non-small cell lung cancer (NSCLC). However, these treatment decisions require the determination of targetable genomic and molecular alterations through invasive genetic or immunohistochemistry (IHC) tests. Numerous previous studies have demonstrated that artificial intelligence can accurately predict the single-gene status of tumors based on radiologic imaging, but few studies have achieved the simultaneous evaluation of multiple genes to reflect more realistic clinical scenarios. Methods: We proposed a multi-label multi-task deep learning (MMDL) system for non-invasively predicting actionable NSCLC mutations and PD-L1 expression utilizing routinely acquired computed tomography (CT) images. This radiogenomic system integrated transformer-based deep learning features and radiomic features of CT volumes from 1096 NSCLC patients based on next-generation sequencing (NGS) and IHC tests. Results: For each task cohort, we randomly split the corresponding dataset into training (80%), validation (10%), and testing (10%) subsets. The area under the receiver operating characteristic curves (AUCs) of the MMDL system achieved 0.862 (95% confidence interval (CI), 0.758–0.969) for discrimination of a panel of 8 mutated genes, including EGFR, ALK, ERBB2, BRAF, MET, ROS1, RET and KRAS, 0.856 (95% CI, 0.663–0.948) for identification of a 10-molecular status panel (previous 8 genes plus TP53 and PD-L1); and 0.868 (95% CI, 0.641–0.972) for classifying EGFR / PD-L1 subtype, respectively. Conclusions: To the best of our knowledge, this study is the first deep learning system to simultaneously analyze 10 molecular expressions, which might be utilized as an assistive tool in conjunction with or in lieu of ancillary testing to support precision treatment options.

Lung cancer accounts for the majority of malignancy-related mortalities worldwide. The introduction of epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) has revolutionized the treatment and significantly improved the overall survival (OS) of lung cancer. Nevertheless, almost all EGFR-mutant patients invariably acquire TKI resistance. Accumulating evidence has indicated that noncoding RNAs (ncRNAs), such as microRNAs (miRNAs), long noncoding RNAs (lncRNAs) and circular RNAs (circRNAs), have a central role in the tumorigenesis and progression of lung cancer by regulating crucial signaling pathways, providing a new approach for exploring the underlying mechanisms of EGFR-TKI resistance. Therefore, this review comprehensively describes the dysregulation of ncRNAs in EGFR TKI-resistant lung cancer and its underlying mechanisms. We also underscore the clinical application of ncRNAs as prognostic, predictive and therapeutic biomarkers for EGFR TKI-resistant lung cancer. Furthermore, the barriers that need to be overcome to translate the basic findings of ncRNAs into clinical practice are discussed.

Background: Coronavirus disease 2019 (COVID-19) has spread almost all regions of the world and caused great loss to the whole body of mankind. Thus, numerous clinical trials were conducted to find specific medicine for COVID-19 recently. However, it remains unanswered whether they are beneficial. Objective: This study aimed to evaluate the efficiency and safety of the COVID-19 medicine. Methods: Studies were determined through searching PubMed, Embase, Cochrane Library and Medline. The clinical trials of COVID-19 medicine were involved with eligible end points containing mortality, discharge rate, rate of clinical improvement and rate of serious adverse events. The risk ratio (RR) was adopted for variables as effect magnitude with 95% confidence intervals (CI), and the random‐effects model was adopted for analysis. Results: A total of eleven RCTs and eleven Non-RCTs involving 12,796 patients were included in our study, whose intervening measures contained three major types of COVID-19 medicine, ACEI/ARB, antiviral medicine and chloroquine/hydroxychloroquine. Compared to control group, COVID-19 medicine has the obvious advantage in reducing discharge rate (RR, 1.18; 95% CI, 1.07-1.29, p<0. 05) and clinical improvement rate (RR, 1.15; 95% CI, 1.05-1.26, p<0. 05), no distinct effect on mortality (RR, 0.79; 95% CI, 0.53-1.17, p=0. 24). In addition, the serious adverse events rate (RR, 0.74; 95% CI, 0.62-0.88, p<0. 05) of COVID-19 medicine is lower than control group. Among different types of medicine, significant benefits in lowering the mortality seem to only occur in antiviral medicine. Conclusion: The results indicated antiviral medicine was potential drug of first choice recommended for COVID-19 treatment. Chloroquine/hydroxychloroquine therapy was not recommended for COVID-19 patients. Additionally, the ACEI/ARB could be adopted for COVID-19 treatment when combined with standard treatment.