Deep learning-based diagnosis of aortic dissection using an electrocardiogram: Development, validation, and clinical implications of the AADE score.

BACKGROUND: Aortic dissection (AD) is frequently associated with abnormalities in electrocardiographic findings. Advancements in medical technology present an opportunity to leverage these observations to improve patient diagnosis and care. OBJECTIVES: This study aimed to develop a deep learning artificial intelligence (AI) model for AD detection using electrocardiograms (ECGs) and introduce the AI-Aortic-Dissection-ECG (AADE) score to provide clinicians with a measure to determine AD severity. METHODS: From a cohort of 1878 patients, including 313 with AD, and 313 with chest pain (control group), we created training and validation subsets (7:3 ratio). A convolutional neural networks (CNN) model was trained for AD detection, with performance metrics like accuracy and F1 score (the harmonic mean of precision and recall) monitored. The AI-derived AADE score (0-1) was investigated against clinical parameters and ECG features over a median follow-up of 21.2 months. RESULTS: The CNN model demonstrated robust performance with an accuracy of 0.93 and an F1 score of 0.93 for the AD group, and an accuracy of 0.871 with an F1 score of 0.867 for the chest pain group. The AADE score showed correlations with specific ECG patterns and demonstrated that higher scores aligned with increased mortality risk. CONCLUSIONS: Our CNN-based AI model offers a promising approach for AD detection using ECG. The AADE score, based on AI, can serve as a pivotal tool in refining clinical assessments and management strategies.

Artificial intelligence-enabled 8-lead ECG detection of atrial septal defect among adults: a novel diagnostic tool.

Background: Patients with atrial septal defect (ASD) exhibit distinctive electrocardiogram (ECG) patterns. However, ASD cannot be diagnosed solely based on these differences. Artificial intelligence (AI) has been widely used for specifically diagnosing cardiovascular diseases other than arrhythmia. Our study aimed to develop an artificial intelligence-enabled 8-lead ECG to detect ASD among adults. Method: In this study, our AI model was trained and validated using 526 ECGs from patients with ASD and 2,124 ECGs from a control group with a normal cardiac structure in our hospital. External testing was conducted at Wuhan Central Hospital, involving 50 ECGs from the ASD group and 46 ECGs from the normal group. The model was based on a convolutional neural network (CNN) with a residual network to classify 8-lead ECG data into either the ASD or normal group. We employed a 10-fold cross-validation approach. Results: Statistically significant differences (p < 0.05) were observed in the cited ECG features between the ASD and normal groups. Our AI model performed well in identifying ECGs in both the ASD group [accuracy of 0.97, precision of 0.90, recall of 0.97, specificity of 0.97, F1 score of 0.93, and area under the curve (AUC) of 0.99] and the normal group within the training and validation datasets from our hospital. Furthermore, these corresponding indices performed impressively in the external test data set with the accuracy of 0.82, precision of 0.90, recall of 0.74, specificity of 0.91, F1 score of 0.81 and the AUC of 0.87. And the series of experiments of subgroups to discuss specific clinic situations associated to this issue was remarkable as well. Conclusion: An ECG-based detection of ASD using an artificial intelligence algorithm can be achieved with high diagnostic performance, and it shows great clinical promise. Our research on AI-enabled 8-lead ECG detection of ASD in adults is expected to provide robust references for early detection of ASD, healthy pregnancies, and related decision-making. A lower number of leads is also more favorable for the application of portable devices, which it is expected that this technology will bring significant economic and societal benefits.

Cordycepin suppresses vascular inflammation, apoptosis and oxidative stress of arterial smooth muscle cell in thoracic aortic aneurysm with VEGF inhibition.

BACKGROUND: Thoracic aortic aneurysm (TAA) is a type of common and serious vascular disease, in which inflammation, apoptosis and oxidative stress are strongly involved in the progression. Cordycepin, a bioactive compound from Cordyceps militaris, exhibits anti-inflammatory and anti-oxidative activities. This study aimed to address the role and mechanism of cordycepin in TAA. METHODS: The thoracic aortas were perivascularly administrated with calcium chloride (CaCl2), and human aortic smooth muscle cells (HASMCs) were incubated with angiotensin II (Ang II) to simulate the TAA model in vivo and in vitro, respectively. The effect and mechanism of cordycepin in TAA were explored by hematoxylin and eosin (HE) staining, immunohistochemistry (IHC), immunofluorescence (IF), western blot, biochemical test, cell counting kit-8 (CCK-8), and terminal deoxynucleotidyl transferase deoxyuridine triphosphate (dUTP) nick end labeling (TUNEL) assays. RESULTS: Cordycepin improved the CaCl2-induced the aneurysmal alteration and disappearance of normal wavy elastic structures of the aorta tissues, TAA incidence and thoracic aortic diameter in rats, and Ang II-induced the cell viability of HASMCs. Cordycepin reversed the CaCl2-induced the relative protein expression of cleaved caspase 9, cleaved caspase 3, interleukin (IL)-6, tumor necrosis factor (TNF)-α and IL-1ß, and the relative levels of glutathione (GSH), malonaldehyde (MDA) and reactive oxygen species (ROS) in vivo, or Ang II-induced these changes in vitro. Mechanically, cordycepin reduced the relative protein expressions of vascular endothelial growth factor (VEGF), VEGF receptor 2 (VEGFR2), cluster of differentiation 31 (CD31) and endothelial nitric oxide synthase (eNOS) in the Ang II-induced HASMCs. Correspondingly, overexpression of VEGF increased the levels of the indicators involved in apoptosis, inflammation and oxidative stress, which were antagonized with the cordycepin incubation in the Ang II-induced HASMCs. CONCLUSION: Cordycepin inhibited apoptosis, inflammation and oxidative stress of TAA through the inhibition of VEGF.

Anti­silencing function 1B promotes the progression of pancreatic cancer by activating c­Myc.

The present study aimed to explore the role of histone chaperone anti­silencing function 1B (ASF1B) in pancreatic cancer and the underlying mechanism. The biological function of ASF1B was investigated in pancreatic cancer cell lines (PANC­1 and SW1990) and a mouse xenograft model. Chromatin immunoprecipitation was used to detect the effect of ASF1B on the transcriptional activity of c­Myc. ASF1B was highly expressed in pancreatic adenocarcinoma (PAAD) samples from The Cancer Genome Atlas. ASF1B expression was positively associated with poor survival rates in patients with PAAD. Silencing of ASF1B in PANC­1 and SW1990 cells inhibited cell proliferation, migration and invasion, and induced apoptosis. Mechanistically, ASF1B increased H3K56 acetylation (H3K56ac) in a CREB­binding protein (CBP)­dependent manner. ASF1B promoted H3K56ac at the c­Myc promoter and increased c­Myc expression. In PANC­1 and SW1990 cells, the CBP inhibitor curcumin and the c­Myc inhibitor 10058­F4 reversed the promoting effects of ASF1B on cell proliferation, migration and invasion. In the mouse xenograft model, ASF1B silencing inhibited tumor growth, and was associated with low H3K56ac and c­Myc expression. ASF1B promoted pancreatic cancer progression by activating c­Myc via CBP­mediated H3K56ac.

Nanoparticles loaded with circ_0086375 for suppressing the tumorigenesis of pancreatic cancer by targeting the miR-646/SLC4A4 axis.

Nanoparticles possess the ability to adsorb and load other compounds. This study aimed to synthesize a gene carrier with polyethyleneimine (PEI), hyaluronic acid (HA) and mesoporous silica nanoparticles (MSNs) for circ_0086375 delivery to investigate the role and mechanism of circ_0086375 in pancreatic cancer (PC) progression. The expression of genes and proteins was detected by quantitative real-time polymerase chain reaction and Western blot. In vitro experiments were performed by cell counting Kit-8 (CCK-8), 5-Ethynyl-2'-deoxyuridine (EdU) assay, flow cytometry, transwell assay, and wound healing assay, respectively. Dual-luciferase activity assay was used to investigate the target relationship between miR-646 and circ_0086375 or SLC4A4 (solute carrier family 4 member 4). Circ_0086375 loaded PEI/HA-based mesoporous silica nanoparticles (MSNs) were prepared, and in vivo assay was performed by using xenograft tumor model. Circ_0086375 expression was decreased in PC tissues and cells. Restoration of circ_0086375 suppressed PC cell proliferation, migration and invasion in vitro and in vivo. Mechanistically, circ_0086375 acted as a sponge for miR-646 to elevate SLC4A4 expression, which was confirmed to be a target of miR-646. The prepared circ_0086375/MSN/PEI/HA nanocomplexes showed excellent fluorescent properties and a higher cellular uptake of circ_0086375 in PC cells. Moreover, circ_0086375/MSN/PEI/HA showed relatively more anticancer effects in PC than that of circ_0086375 alone in vitro and in vivo. Delivery of circ_0086375 by nanoparticles suppresses the tumorigenicity of pancreatic cancer by miR-646/SLC4A4 axis, suggesting a new potential target for future pancreatic cancer treatment.

LINC01915 Facilitates the Conversion of Normal Fibroblasts into Cancer-Associated Fibroblasts Induced by Colorectal Cancer-Derived Extracellular Vesicles through the miR-92a-3p/KLF4/CH25H Axis.

Increasing long non-coding RNAs are reported to regulate the cell growth, apoptosis, and metastasis of cancer-associated fibroblasts (CAFs).This study aimed to explore how LINC01915 influences the conversion of normal fibroblasts (NFs) into CAFs in colorectal cancer (CRC). LINC01915 expression was initially measured in clinical tissue samples and in NFs and CAFs. Identification of the interaction between LINC01915, miR-92a-3p, KLF4, and CH25H was done. The effects of LINC01915, miR-92a-3p, and KLF4 on the angiogenesis, extracellular vesicle (EV) uptake by NFs, and activation of stromal cells were assessed using gain- or loss-of-function approaches. Xenograft mouse models were established to validate these in vitro findings in vivo. EVs were shown to stimulate NF proliferation, migration, and angiogenesis, as well as facilitate NF conversion into CAFs. CRC tissues and CAFs showed downregulated expression of LINC01915, which was associated with poor prognosis of patients. Moreover, employed LINC01915 inhibited tumor angiogenesis, CAF activation, and the uptake of tumor-derived EVs by NFs. Mechanistically, LINC01915 could competitively bind to miR-92a-3p and caused upregulation of the miR-92a-3p target KLF4 which, in turn, promoted the transcription of CH25H, leading to the suppressed uptake of EVs by NFs. The in vivo and in vitro experimental results showed that LINC01915 inhibited the uptake of CRC-derived EVs by NFs through the miR-92a-3p/KLF4/CH25H axis, thus arresting the angiogenesis and the conversion of NFs into CAFs and in turn prevent tumor growth. These data together supported the inhibiting role of LINC01915 in the conversion of NFs into CAFs triggered by the CRC-derived EVs and the ensuing tumor growth, which may be related to its regulation on the miR-92a-3p/KLF4/CH25H axis.

LINC01006 promotes cell proliferation and metastasis in pancreatic cancer via miR-2682-5p/HOXB8 axis.

BACKGROUND: Pancreatic cancer (PC) is one of the deadliest cancers about the digestive system. Recent researches have validated that long non-coding RNAs (lncRNAs) play vital roles in various cancers, while the function of LINC01006 in PC is rarely clarified. AIM OF THE STUDY: Investigation of the specific role of LINC01006 in PC. METHODS: LINC01006 expression was examined by RT-qPCR. CCK-8, EdU, transwell, wound healing, and western blot assays were carried out to explore the function of LINC01006 in PC. The interaction among LINC01006, miR-2682-5p and HOXB8 was verified by luciferase reporter, RIP and ChIP assays. RESULTS: The expression of LINC01006 was markedly upregulated in PC tissues and cells. Furthermore, LINC01006 knockdown inhibited PC cell proliferation, invasion and migration, and upregulation of LINC01006 led to the opposite results. Besides, miR-2682-5p expression was downregulated and negatively regulated by LINC01006 in PC. Meanwhile, LINC01006 could bind with miR-2682-5p in PC. Moreover, miR-2682-5p negatively regulated HOXB8 expression and there was a binding site between miR-2682-5p and HOXB8 in PC. Additionally, miR-2682-5p overexpression or HOXB8 knockdown rescued the promotive effects of LINC01006 upregulation on PC cell progression. Similarly, miR-2682-5p inhibition or HOXB8 overexpression countervailed the repressive role of LINC01006 downregulation in PC cell progression. In addition, the transcription factor HOXB8 could activate LINC01006 transcription in PC. CONCLUSIONS: LINC01006 promotes cell proliferation and metastasis in pancreatic cancer via miR-2682-5p/HOXB8 axis, which may facilitate the treatment for PC.