ARID3A enhances chemoresistance of pancreatic cancer via inhibiting PTEN-induced ferroptosis.

Currently, chemotherapy remains occupying a pivotal place in the treatment of pancreatic ductal adenocarcinoma (PDAC). Nonetheless, the emergence of drug resistance in recent years has limited the clinical efficacy of chemotherapeutic agents, especially gemcitabine (GEM). Through bioinformatics analysis, AT-rich Interactive Domain-containing Protein 3A (ARID3A), one of transcription factors, is discovered to possibly participate in this progress. This study thoroughly investigates the potential role of ARID3A in the malignant progression and GEM chemoresistance of PDAC and explores the underlying mechanisms. The results indicate that ARID3A knockdown suppresses tumor development and enhances the sensitivity of PDAC cells to GEM in vitro and vivo. Mechanically, CUT&Tag profiling sequencing, RNA-sequencing and functional studies demonstrates that decreased ARID3A expression alleviates the transcriptional inhibition of phosphatase and tensin homolog (PTEN), consequently leading to glutathione peroxidase 4 (GPX4) depletion and increased lipid peroxidation levels. Activated ferroptosis induced by the inhibition of GPX4 subsequently restricts tumor progression and reduces GEM resistance in PDAC. This research identifies the ferroptosis regulatory pathway of ARID3A-PTEN-GPX4 axis and reveals its critical role in driving the progression and chemoresistance of pancreatic cancer. Notably, both inhibition of ARID3A and enhancement of ferroptosis can increase chemosensitivity to GEM, which offers a promising opportunity for developing therapeutic strategies to combat acquired chemotherapy resistance in pancreatic cancer.

Pirfenidone alleviates fibrosis by acting on tumour-stroma interplay in pancreatic cancer.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a malignancy with a 5-year survival rate of 12%. The abundant mesenchyme is partly responsible for the malignancy. The antifibrotic therapies have gained attention in recent research. However, the role of pirfenidone, an FDA-approved drug for idiopathic pulmonary fibrosis, remains unclear in PDAC. METHODS: Data from RNA-seq of patient-derived xenograft (PDX) models treated with pirfenidone were integrated using bioinformatics tools to identify the target of cell types and genes. Using confocal microscopy, qRT-PCR and western blotting, we validated the signalling pathway in tumour cells to regulate the cytokine secretion. Further cocultured system demonstrated the interplay to regulate stroma fibrosis. Finally, mouse models demonstrated the potential of pirfenidone in PDAC. RESULTS: Pirfenidone can remodulate multiple biological pathways, and exerts an antifibrotic effect through inhibiting the secretion of PDGF-bb from tumour cells by downregulating the TGM2/NF-kB/PDGFB pathway. Thus, leading to a subsequent reduction in collagen X and fibronectin secreted by CAFs. Moreover, the mice orthotopic pancreatic tumour models demonstrated the antifibrotic effect and potential to sensitise gemcitabine. CONCLUSIONS: Pirfenidone may alter the pancreatic milieu and alleviate fibrosis through the regulation of tumour-stroma interactions via the TGM2/NF-kB/PDGFB signalling pathway, suggesting potential therapeutic benefits in PDAC management.

PP2A complex disruptor SET prompts widespread hypertranscription of growth-essential genes in the pancreatic cancer cells.

Hyperactivation of the oncogenic transcription reflects the epigenetic plasticity of the cancer cells. Su(var)3-9, enhancer of zeste, Trithorax (SET) was described as a nuclear factor that stimulated transcription from the chromatin template. However, the mechanisms of SET-dependent transcription are unknown. Here, we found that overexpression of SET and CDK9 induced very similar transcriptome signatures in multiple cancer cell lines. SET localized in the transcription start site (TSS)-proximal regions and supported the RNA transcription. SET specifically bound the PP2A-C subunit and induced PP2A-A subunit repulsion from the C subunit, which indicated the role of SET as a PP2A-A/C complex disruptor in the TSS-proximal regions. Through blocking PP2A activity, SET assisted CDK9 to maintain Pol II CTD phosphorylation and activated mRNA transcription. Our findings position SET as a key factor that modulates chromatin PP2A activity, promoting the oncogenic transcription in the pancreatic cancer.

A Robust and Integrated Visual Odometry Framework Exploiting the Optical Flow and Feature Point Method.

In this paper, we propose a robust and integrated visual odometry framework exploiting the optical flow and feature point method that achieves faster pose estimate and considerable accuracy and robustness during the odometry process. Our method utilizes optical flow tracking to accelerate the feature point matching process. In the odometry, two visual odometry methods are used: global feature point method and local feature point method. When there is good optical flow tracking and enough key points optical flow tracking matching is successful, the local feature point method utilizes prior information from the optical flow to estimate relative pose transformation information. In cases where there is poor optical flow tracking and only a small number of key points successfully match, the feature point method with a filtering mechanism is used for posing estimation. By coupling and correlating the two aforementioned methods, this visual odometry greatly accelerates the computation time for relative pose estimation. It reduces the computation time of relative pose estimation to 40% of that of the ORB_SLAM3 front-end odometry, while ensuring that it is not too different from the ORB_SLAM3 front-end odometry in terms of accuracy and robustness. The effectiveness of this method was validated and analyzed using the EUROC dataset within the ORB_SLAM3 open-source framework. The experimental results serve as supporting evidence for the efficacy of the proposed approach.

Functional significance of cholesterol metabolism in cancer: from threat to treatment.

Cholesterol is an essential structural component of membranes that contributes to membrane integrity and fluidity. Cholesterol homeostasis plays a critical role in the maintenance of cellular activities. Recently, increasing evidence has indicated that cholesterol is a major determinant by modulating cell signaling events governing the hallmarks of cancer. Numerous studies have shown the functional significance of cholesterol metabolism in tumorigenesis, cancer progression and metastasis through its regulatory effects on the immune response, ferroptosis, autophagy, cell stemness, and the DNA damage response. Here, we summarize recent literature describing cholesterol metabolism in cancer cells, including the cholesterol metabolism pathways and the mutual regulatory mechanisms involved in cancer progression and cholesterol metabolism. We also discuss various drugs targeting cholesterol metabolism to suggest new strategies for cancer treatment.

AI-Assisted Ultrasound for the Early Diagnosis of Antibody-Negative Autoimmune Thyroiditis.

The prevalence of antibody-negative chronic autoimmune thyroiditis (SN-CAT) is increasing. The early diagnosis of SN-CAT can effectively prevent its further development. Thyroid ultrasound can diagnose autoimmune thyroiditis and predict hypothyroidism. Primary hypothyroidism with a hypoechoic pattern suggested by thyroid ultrasound and negative thyroid serum antibodies is the main basis for the diagnosis of SN-CAT. However, for early SN-CAT, only hypoechoic thyroid changes and serological antibodies are currently available. This study explored how to achieve an accurate and early diagnosis of SN-CAT and prevent the development of SN-CAT combined with hypothyroidism. The diagnosis of a hypoechoic thyroid by artificial intelligence is expected to be a breakthrough in the accurate diagnosis of SN-CAT.

The Accurate Interpretation and Clinical Significance of Morphological Features of Fine Needle Aspiration Cells in Papillary Thyroid Carcinoma.

Papillary thyroid carcinoma (PTC) is the most common malignant neoplasm of the thyroid gland; fine needle aspiration cytology is the most basic and reliable diagnostic method before PTC operation. However, it is not clear which cell morphological changes can be used as a reliable standard for the diagnosis of PTC. A retrospective analysis was performed on 337 patients with PTC confirmed by postoperative histology. An additional 197 randomly selected patients with benign thyroid lesions were included in the study and used as a control group. True papillary arrangements, swirl arrangements, and escape arrangements had high specificity, all of which were 100%, but only swirl arrangements had ideal sensitivity (77.61%). The nuclear volume characteristics had a high sensitivity of more than 90%, but the specificities of both nuclear crowding and nuclear overlap were too low, only 16.34% and 23.35%. The sensitivities of five nuclear structural characteristics were more than 90%, but only the specificity of intranuclear cytoplasmic pseudoinclusions (INCIs) reached 100%, nuclear contour irregularity and pale nuclei with powdery chromatin also had ideal interpretation value except for grooves and marginally placed micronucleoli. Although the sensitivity of psammoma bodies (PBs) was low, the specificity was 100%. In terms of preparation methods, the method of liquid-based preparation (LBP) is obviously better than that of conventional smears. The diagnostic efficiency by the combined detection method of parallel tests showed that without reducing the specificity, the sensitivity increased with the increase of the number of morphological characteristics and finally reached 98.81%. The INCIs and swirl arrangements are the most common and important indicators for the diagnosis of PTC, whereas papillary-like arrangements, the crowding and overlap of nuclear, grooves, marginally placed micronucleoli, and multinucleated giant cells are of little significance for the diagnosis of PTC.

Assessment of cancer-related signaling pathways in responses to polystyrene nanoplastics via a kidney-testis microfluidic platform (KTP).

As a new type of environmental pollutants, micro/nano plastics (MPs/NPs) derived from plastic products are commonly contact in daily life and lead to some serious health issues. The toxicity effects of MPs/NPs on the human body have aroused wide concerns. Although MPs/NPs have been reported to be transmitted into the kidney and reproductive organs, the molecular mechanisms of MPs/NPs toxicity remain unclear due to the lack of a physiologically relevant organ-organ linking platform in vitro. Here, we present a kidney-testis microfluidic platform (KTP) with NPs exposure that enables the communication of kidney and testis chambers and reproduces endothelium-linked chambers to simulate the state in vivo. The function of KTP was assessed by cell counting kit (CCK-8), tight junction protein claudin-2 and glucose consumption. Results revealed that MPs/NPs entered the kidney and testis via endocytosis. Immunofluorescence and ELISA analysis were performed on KTP at 200 µg/mL PS-NP to identify the dysregulated proteins on cancer-related signaling pathways, including the MAPK signaling pathway (RTK, RAS, ERK, JNK, P38, NRF2, TNF-α, and TNF-α-R) and the PI3K-AKT signaling pathway (PI3K, AKT, MDM2, P53, and ΒΑD). This multi-organ platform (KTP) contributes to clarifying cancer pathways triggered by MPs/NPs exposure and provides a promising method for assessing diseases induced by environmental pollutants.

Targeting cell death pathways for cancer therapy: recent developments in necroptosis, pyroptosis, ferroptosis, and cuproptosis research.

Many types of human cells self-destruct to maintain biological homeostasis and defend the body against pathogenic substances. This process, called regulated cell death (RCD), is important for various biological activities, including the clearance of aberrant cells. Thus, RCD pathways represented by apoptosis have increased in importance as a target for the development of cancer medications in recent years. However, because tumor cells show avoidance to apoptosis, which causes treatment resistance and recurrence, numerous studies have been devoted to alternative cancer cell mortality processes, namely necroptosis, pyroptosis, ferroptosis, and cuproptosis; these RCD modalities have been extensively studied and shown to be crucial to cancer therapy effectiveness. Furthermore, evidence suggests that tumor cells undergoing regulated death may alter the immunogenicity of the tumor microenvironment (TME) to some extent, rendering it more suitable for inhibiting cancer progression and metastasis. In addition, other types of cells and components in the TME undergo the abovementioned forms of death and induce immune attacks on tumor cells, resulting in enhanced antitumor responses. Hence, this review discusses the molecular processes and features of necroptosis, pyroptosis, ferroptosis, and cuproptosis and the effects of these novel RCD modalities on tumor cell proliferation and cancer metastasis. Importantly, it introduces the complex effects of novel forms of tumor cell death on the TME and the regulated death of other cells in the TME that affect tumor biology. It also summarizes the potential agents and nanoparticles that induce or inhibit novel RCD pathways and their therapeutic effects on cancer based on evidence from in vivo and in vitro studies and reports clinical trials in which RCD inducers have been evaluated as treatments for cancer patients. Lastly, we also summarized the impact of modulating the RCD processes on cancer drug resistance and the advantages of adding RCD modulators to cancer treatment over conventional treatments.

Novel Therapeutic Mechanism of Adipose-Derived Mesenchymal Stem Cells in Osteoarthritis via Upregulation of BTG2.

Background: Osteoarthritis (OA) is a debilitating and degenerative joint disease, which is characterized by progressive destruction of articular cartilage. Mesenchymal stem cells (MSCs) have been implicated in the treatment of OA. However, the function of adipose-derived MSCs (AD-MSCs) in OA and its underlying mechanism remain obscure. Aim: We aimed to explore the function of AD-MSCs in OA and investigate its potential regulatory mechanism. Methods: A guinea pig model of OA was constructed. AD-MSCs injected into the articular cavity of OA guinea pigs were viewed by in vivo bioluminescence imaging. The effect of AD-MSCs on the gonarthritis of OA guinea pigs was evaluated through both macroscopic and microscopic detections. The detailed molecular mechanism was predicted by GEO databases and bioinformatics tools and then verified via mechanism experiments, including ChIP assay, DNA pulldown assay, and luciferase reporter assay. Results: AD-MSCs had a significant positive therapeutic effect on the gonarthritis of the OA model, and the overall effects of it was better than that of sodium hyaluronate (SH). B-cell translocation gene 2 (BTG2) was significantly downregulated in the articular cartilage of the OA guinea pigs. Furthermore, BTG2 was positively regulated by Krüppel-like factor 4 (KLF4) in AD-MSCs at the transcriptional level. AD-MSCs performed an effect on KLF4 expression at the transcriptional levels. Conclusion: AD-MSCs suppresses OA progression through KLF4-induced transcriptional activation of BTG2. Our findings revealed an AD-MSCs-dominated therapeutic method for OA.

Diffuse Primary Malignant Pericardial Mesothelioma With Myocardial involvement: A Comprehensive Assessment Using Multimodel Echocardiography.

Diffuse primary malignant pericardial mesothelioma (PMPM) is an extremely rare and highly invasive tumor of pericardium. The tumor can infiltrate myocardium in part of cases, and will contribute to grave prognosis. Herein, we reported a 58-year-old man of diffuse PMPM with myocardial involvement, and summarized 39 cases of diffuse PMPM. Multimodal echocardiography, which combined conventional, tissue Doppler and speckle tracking echocardiography, was applied to diagnose diffuse PMPM with myocardial involvement, and assess the myocardial function. The common features were pericardial effusion, pericardial masses and thickened pericardium. The other echocardiographic characteristics were extensive and heterogenous echo, adhesion with pericardium and myocardium, reduced motion of adhered myocardium, and constriction performance. Diffuse PMPM with myocardial involvement revealed decreased LV diastolic function, and decreased LV and RV systolic function. Especially in systolic function, the unique strain features were reduced longitudinal strains from segmental to global and from epicardial to endocardial, relative 'septal sparing' pattern, and decreased transmural gradient of longitudinal strain. Our findings suggested that multimodal echocardiography not only can identify this disease, but also can provide detailed information of myocardial dysfunction, which provides a reference for clinicians to develop an optimal individualized treatment.

Emerging roles of protein palmitoylation and its modifying enzymes in cancer cell signal transduction and cancer therapy.

Protein palmitoylation is an increasingly investigated form of post-translational lipid modification that affects protein localization, accumulation, secretion and function. Recently, emerging findings have revealed that protein palmitoylation is crucial for many tumor-related signaling pathways, such as EGFR, RAS, PD-1/PD-L1 signaling, affecting the occurrence, progression and therapeutic response of tumors. Protein palmitoylation and its modifying enzymes, including palmitoylases and depalmitoylases, are expected to be new targets for effective tumor treatment. Recognizing the significance of palmitoylation modification on protein stability, localization and downstream signal regulation, this review focuses on the regulatory roles of protein palmitoylation and its modifying enzymes in tumor cell signal transduction, aiming to bring new ideas for effective cancer prevention and treatment.

Dual-functional significance of ATM-mediated phosphorylation of spindle assembly checkpoint component Bub3 in mitosis and the DNA damage response.

Both the DNA damage response (DDR) and the mitotic checkpoint are critical for the maintenance of genomic stability. Among proteins involved in these processes, the ataxia-telangiectasia mutated (ATM) kinase is required for both activation of the DDR and the spindle assembly checkpoint (SAC). In mitosis without DNA damage, the enzymatic activity of ATM is enhanced; however, substrates of ATM in mitosis are unknown. Using stable isotope labeling of amino acids in cell culture mass spectrometry analysis, we identified a number of proteins that can potentially be phosphorylated by ATM during mitosis. This list is highly enriched in proteins involved in cell cycle regulation and the DDR. Among them, we further validated that ATM phosphorylated budding uninhibited by benzimidazoles 3 (Bub3), a major component of the SAC, on serine 135 (Ser135) both in vitro and in vivo. During mitosis, this phosphorylation promoted activation of another SAC component, benzimidazoles 1. Mutation of Bub3 Ser135 to alanine led to a defect in SAC activation. Furthermore, we found that ATM-mediated phosphorylation of Bub3 on Ser135 was also induced by ionizing radiation-induced DNA damage. However, this event resulted in independent signaling involving interaction with the Ku70-Ku80-DNA-PKcs sensor/kinase complex, leading to efficient nonhomologous end-joining repair. Taken together, we highlight the functional significance of the crosstalk between the kinetochore-oriented signal and double-strand break repair pathways via ATM phosphorylation of Bub3 on Ser135.

Renal-on-Chip Microfluidic Platform with a Force-Sensitive Resistor (ROC-FS) for Molecular Pathogenesis Analysis of Hydronephrosis.

Hydronephrosis is one of the most common diseases in urology. However, due to the difficulties in clinical trials and the lack of reliable in vitro platforms, the surgical indicators are not clear. Herein, the renal-on-chip with a force-sensitive resistor microfluidic platform was established to simulate the state of hydronephrosis. Cell counting kit-8 (CCK-8) and tight junction protein claudin-2 were detected on a renal-on-chip microfluidic platform with a force-sensitive resistor (ROC-FS). The results indicated that the ROC-FS had normal physiological functions and the cell viability on ROC-FS declined to around 40% after 48 h of hydronephrosis-simulated treatment. In addition, proteomics analysis of 15 clinical ureteropelvic junction obstruction (UPJO) samples showed that compared with normal children, a total of 50 common proteins were differentially expressed in UPJO children (P < 0.05, |log2fold change| ≥ 1). Metabolomic analysis of 39 clinical UPJO samples showed that a total of 241 metabolisms were dysregulated. Subsequent immunofluorescence and enzyme-linked immunosorbent assay (ELISA) analysis using ROC-FS were performed to identify the clinical multi-omics results for screening. All results pointed out that the TGF-ß-related signaling pathways and arginine-related metabolism signaling pathways were dysregulated and α-SMA, AGT, and AGA might be the potential biomarkers of hydronephrosis. In addition, correlation analysis of AGT and KLK1 with differential renal function (DRF) from clinical samples indicated good correlation coefficients (R2 0.923, 0.8742, 0.6412, and 0.8347). This demonstrates the state of hydronephrosis could be significantly correlated with the biomarkers. These findings could provide a reliable reference for determining surgical biomarkers clinically, and ROC could be further used in the analysis of other kidney diseases.

Uncovering the Subtype-Specific Molecular Characteristics of Breast Cancer by Multiomics Analysis of Prognosis-Associated Genes, Driver Genes, Signaling Pathways, and Immune Activity.

Breast cancer is a heterogeneous malignant disease with different prognoses and has been divided into four molecular subtypes. It is believed that molecular events occurring in breast stem/progenitor cells contribute to the carcinogenesis and development of different breast cancer subtypes. However, these subtype-specific molecular characteristics are largely unknown. In this study, we employed 1217 breast cancer samples from The Cancer Genome Atlas (TCGA) database for a multiomics analysis of the molecular characteristics of different breast cancer subtypes based on PAM50 algorithms. We detected the expression changes of subtype-specific genes and revealed that the expression of particular subtype-specific genes significantly affected prognosis. We also investigated the mutations and copy number variations (CNVs) of breast cancer driver genes and the representative genes of ten signaling pathways in different subtypes and revealed several subtype-specifically altered genes. Moreover, we detected the infiltration of various immune cells in different subtypes of breast cancer and showed that the infiltration levels of major immune cell types are different among these subtypes. Additionally, we investigated the factors affecting the immune infiltration level and the immune cytolytic activity in different breast cancer subtypes, namely, the mutation burden, genome instability and cancer-associated fibroblast (CAF) infiltration. This study may shed light on the molecular events contributing to carcinogenesis and development and provide potential markers and targets for the clinical diagnosis and treatment of different breast cancer subtypes.

Association of PM2.5 with Insulin Resistance Signaling Pathways on a Microfluidic Liver-Kidney Microphysiological System (LK-MPS) Device.

Insulin resistance (IR) is a typical sign of metabolic dysregulation caused by fine particulate matter (PM2.5), but the underlying signaling has not been clearly determined. Herein, a microfluidic liver-kidney microphysiological system (LK-MPS) is presented to assess the signaling pathways of IR generated by PM2.5 at 200 µg/mL for 24 h. The LK-MPS device consisted of a biomimetic liver-kidney architecture and reconstructed two circulation paths: the liver metabolism-kidney excretion (LM-KE) and kidney excretion-liver metabolism (KE-LM), by which PM2.5 is feasibly distributed in the two organs. Transmission electron microscopy (TEM) analysis revealed that PM2.5 can embed in the cytoplasm and nuclei, undergo transport by vesicles, and lead to the destruction of mitochondria. Further comprehensive immunofluorescence, enzyme-linked immunosorbent assays (ELISAs) and untargeted metabolomic analyses confirmed that PM2.5 disturbed the classic IRS-1/AKT signaling pathway (INSR, IRS-1, PI3K, AKT, GLUT2, GLUT4, and FOXO1 downregulated) and IR-related metabolic pathways: UDP-hexosamine (UDP-GlcNAc), gluconeogenesis (ß-d-glucose 6-phosphate), and lipid biosynthesis (ceramide (Cer) and triacylglycerol (TG)) pathways, leading to the disorder of glucose levels. Collectively, these disorders aggravate hepatic and renal IR. Pearson's correlation coefficient test showed that elemental carbon (EC), polycyclic aromatic hydrocarbons (PAHs), and metals (Ca, Co, and V) were negatively correlated to the dysregulated proteins (INSR, IRS-1, AKT, FOXO1, GLUT2, and GLUT4). These findings may partially explain IR-related signaling pathways triggered by PM2.5.

Role of BCLAF-1 in PD-L1 stabilization in response to ionizing irradiation.

Programmed cell death ligand 1 (PD-L1) is a major immunosuppressive checkpoint protein expressed by tumor cells to subvert anticancer immunity. Recent studies have shown that ionizing radiation (IR) upregulates the expression of PD-L1 in tumor cells. However, whether an IR-induced DNA damage response (DDR) directly regulates PD-L1 expression and the functional significance of its upregulation are not fully understood. Here, we show that IR-induced upregulation of PD-L1 expression proceeds through both transcriptional and post-translational mechanisms. Upregulated PD-L1 was predominantly present on the cell membrane, resulting in T-cell apoptosis in a co-culture system. Using mass spectrometry, we identified PD-L1 interacting proteins and found that BCLAF1 (Bcl2 associated transcription factor 1) is an important regulator of PD-L1 in response to IR. BCLAF1 depletion decreased PD-L1 expression by promoting the ubiquitination of PD-L1. In addition, we show that CMTM6 is upregulated in response to IR and participates in BCLAF1-dependent PD-L1 upregulation. Finally, we demonstrated that the ATM/BCLAF1/PD-L1 axis regulated PD-L1 stabilization in response to IR. Together, our findings reveal a novel regulatory mechanism of PD-L1 expression in the DDR.

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19).

OBJECTIVE: The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. METHODS: We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation. RESULTS: The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%. CONCLUSION: These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. KEY POINTS: • The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.