Prediction of short-term adverse clinical outcomes of acute pulmonary embolism using conventional machine learning and deep Learning based on CTPA images.

To explore the predictive value of traditional machine learning (ML) and deep learning (DL) algorithms based on computed tomography pulmonary angiography (CTPA) images for short-term adverse outcomes in patients with acute pulmonary embolism (APE). This retrospective study enrolled 132 patients with APE confirmed by CTPA. Thrombus segmentation and texture feature extraction was performed using 3D-Slicer software. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimensionality reduction and selection, with optimal λ values determined using leave-one-fold cross-validation to identify texture features with non-zero coefficients. ML models (logistic regression, random forest, decision tree, support vector machine) and DL models (ResNet 50 and Vgg 19) were used to construct the prediction models. Model performance was evaluated using receiver operating characteristic (ROC) curves and the area under the curve (AUC). The cohort included 84 patients in the good prognosis group and 48 patients in the poor prognosis group. Univariate and multivariate logistic regression analyses showed that diabetes, RV/LV ≥ 1.0, and Qanadli index form independent risk factors predicting poor prognosis in patients with APE(P < 0.05). A total of 750 texture features were extracted, with 4 key features identified through screening. There was a weak positive correlation between texture features and clinical parameters. ROC curves analysis demonstrated AUC values of 0.85 (0.78-0.92), 0.76 (0.67-0.84), and 0.89 (0.83-0.95) for the clinical, texture feature, and combined models, respectively. In the ML models, the random forest model achieved the highest AUC (0.85), and the support vector machine model achieved the lowest AUC (0.62). And the AUCs for the DL models (ResNet 50 and Vgg 19) were 0.91 (95%CI: 0.90-0.92) and 0.94(95%CI: 0.93-0.95), respectively. Vgg 19 model demonstrated exceptional precision (0.93), recall (0.76), specificity (0.95) and F1 score (0.84). Both ML and DL models based on thrombus texture features from CTPA images demonstrated higher predictive efficacy for short-term adverse outcomes in patients with APE, especially the random forest and Vgg 19 models, potentially assisting clinical management in timely interventions to improve patient prognosis.

An additional proofreader contributes to DNA replication fidelity in mycobacteria.

The removal of mis-incorporated nucleotides by proofreading activity ensures DNA replication fidelity. Whereas the ε-exonuclease DnaQ is a well-established proofreader in the model organism Escherichia coli, it has been shown that proofreading in a majority of bacteria relies on the polymerase and histidinol phosphatase (PHP) domain of replicative polymerase, despite the presence of a DnaQ homolog that is structurally and functionally distinct from E. coli DnaQ. However, the biological functions of this type of noncanonical DnaQ remain unclear. Here, we provide independent evidence that noncanonical DnaQ functions as an additional proofreader for mycobacteria. Using the mutation accumulation assay in combination with whole-genome sequencing, we showed that depletion of DnaQ in Mycolicibacterium smegmatis leads to an increased mutation rate, resulting in AT-biased mutagenesis and increased insertions/deletions in the homopolymer tract. Our results showed that mycobacterial DnaQ binds to the ß clamp and functions synergistically with the PHP domain proofreader to correct replication errors. Furthermore, the loss of dnaQ results in replication fork dysfunction, leading to attenuated growth and increased mutagenesis on subinhibitory fluoroquinolones potentially due to increased vulnerability to fork collapse. By analyzing the sequence polymorphism of dnaQ in clinical isolates of Mycobacterium tuberculosis (Mtb), we demonstrated that a naturally evolved DnaQ variant prevalent in Mtb lineage 4.3 may enable hypermutability and is associated with drug resistance. These results establish a coproofreading model and suggest a division of labor between DnaQ and PHP domain proofreader. This study also provides real-world evidence that a mutator-driven evolutionary pathway may exist during the adaptation of Mtb.

CT-Based Radiomics for the Preoperative Prediction of Occult Peritoneal Metastasis in Epithelial Ovarian Cancers.

RATIONALE AND OBJECTIVES: The objective of this study was to develop a comprehensive combined model for predicting occult peritoneal metastasis (OPM) in epithelial ovarian cancers (EOCs) using radiomics features derived from computed tomography (CT) and clinical-radiological predictors. MATERIALS AND METHODS: A total of 224 patients with EOCs were randomly divided into training dataset (N = 156) and test dataset (N = 86). Five clinical factors and seven radiological features were collected. The radiomics features were extracted from CT images of each patient. Multivariate logistic regression was employed to construct clinical and radiological models. The correlation analysis and least absolute shrinkage and selection operator algorithm were used to select radiomics features and build radiomics model. The important clinical, radiological factors, and radiomics features were integrated into a combined model by multivariate logistic regression. Receiver operating characteristics curve with area under the curve (AUC) were used to evaluate and compare predictive performance. RESULTS: Carbohydrate antigen 125 (CA-125) and human epididymal protein 4 (HE-4) were independent clinical predictors. Laterality, thickened septa and margin were independent radiological predictors. In the training dataset, the AUCs for the clinical, radiological and radiomics models in evaluating OPM were 0.759, 0.819, and 0.830, respectively. In the test dataset, the AUCs for these models were 0.846, 0.835, and 0.779, respectively. The combined model outperformed other models in both the training and the test datasets with AUCs of 0.901 and 0.912, respectively. Decision curve analysis indicated that the combined model yielded a higher net benefit compared to the other models. CONCLUSION: The combined model, integrating radiomics features with clinical and radiological predictors exhibited improved accuracy in predicting OPM in EOCs.

Mycobacterial DnaQ is an Alternative Proofreader Ensuring DNA Replication Fidelity.

Remove of mis-incorporated nucleotides ensures replicative fidelity. Although the ε-exonuclease DnaQ is a well-established proofreader in the model organism Escherichia coli, proofreading in mycobacteria relies on the polymerase and histidinol phosphatase (PHP) domain of replicative polymerase despite the presence of an alternative DnaQ homolog. Here, we show that depletion of DnaQ in Mycolicibacterium smegmatis results in increased mutation rate, leading to AT-biased mutagenesis and elevated insertions/deletions in homopolymer tract. We demonstrated that mycobacterial DnaQ binds to the b-clamp and functions synergistically with the PHP domain to correct replication errors. Further, we found that the mycobacterial DnaQ sustains replicative fidelity upon chromosome topological stress. Intriguingly, we showed that a naturally evolved DnaQ variant prevalent in clinical Mycobacterium tuberculosis isolates enables hypermutability and is associated with extensive drug resistance. These results collectively establish that the alternative DnaQ functions in proofreading, and thus reveal that mycobacteria deploy two proofreaders to maintain replicative fidelity.

Value of CT­derived fractional flow reserve in identifying patients with acute myocardial infarction based on coronary computed tomography angiography.

The aim of the present study was to determine whether coronary stenosis and computed tomography-derived fractional flow reserve (CT-FFR), detected by coronary computed tomography angiography (CCTA), can potentially contribute to distinguish acute myocardial infarction (AMI) from unstable angina (UA). The study retrospectively collected data from consecutive patients who were admitted with obstructive coronary artery disease (CAD) and who received CCTA and invasive coronary angiography (ICA) as part of their clinical workup. According to the inclusion criteria, the patients were divided into the AMI group and UA group, and the basic clinical data, CCTA stenosis degree and CT-FFR values were compared between the two groups. Univariate and multivariate logistic regression methods were used to analyze the association between ≥70% CCTA stenosis, ≤0.80 CT-FFR and AMI. A diagnostic model of AMI was established (model 1, ≤0.80 CT-FFR; model 2, ≥70% CCTA stenosis; and model 3, ≤0.80 CT-FFR combined with ≥70% CCTA stenosis), and the diagnostic efficacy of the three models for AMI was compared. The significance level was set at P<0.05. A total of 116 participants were finally enrolled in this study. There were 37 patients in the AMI group, with an average age of 62.06±7.74 years, and 79 patients in the UA group, with an average age of 58.11±10.0 years; there was no significant difference in age (P>0.05). The multivariate regression analysis revealed that ≤0.80 CT-FFR (HR=28.074; 95% CI: 5.712-137.973; P<0.001), and ≥70% CCTA stenosis (HR=10.796; 95% CI: 2.566-45.425; P=0.001) were independent risk factors for AMI. The diagnostic model of ≤0.80 CT-FFR combined with ≥70% CCTA stenosis (AUC=0.914; 95% CI: 0.847-0.958) exhibited increased diagnosis performance than the ≤0.80 CT-FFR model (AUC=0.865; 95% CI: 0.790-0.922; P=0.0060) and the ≥70% CCTA stenosis model (AUC=0.827; 95% CI: 0.745-0.891; P=0.0008). Collectively, it was demonstrated that ≤0.80 CT-FFR and ≥70% CCTA stenosis were independent risk factors for the diagnosis of AMI, and the combination of CT-FFR and CCTA stenosis further improved AMI diagnosis performance.

Associating Serum IgM, IgA Levels with Thoracic CT Indicators and Pulmonary Function Indexes in Acutely Exacerbated Chronic Obstructive Pulmonary Disease Patients.

BACKGROUND: Chronic Obstructive Pulmonary Disease (COPD) is a respiratory condition characterized by acute exacerbations and reduced lung function. This study investigates the link between serum markers (Immunoglobulin M (IgM) and Immunoglobulin A (IgA)), thoracic computed tomography (CT) scan findings, and pulmonary function indexes during these episodes, aiming to improve our understanding and identify new diagnostic indicators. METHODS: From the First Affiliated Hospital of Hebei North University, we selected 89 COPD patients experiencing acute exacerbation within the past two years for our Acute Exacerbation Group (AG). Meanwhile, 96 COPD patients, initially treated at the same hospital and currently deemed stable, were chosen for the Stable Group (SG). Both groups underwent serum IgM and IgA tests, thoracic CT examinations, and pulmonary function assessments. RESULTS: In the AG Group, the serum IgM levels were marginally lower than in the Stable Group (SG), though the difference wasn't statistically significant (p = 0.097). Conversely, serum IgA levels in the AG were significantly lower than in the SG (p < 0.001). The AG also showed markedly reduced lung volume, inspiratory lung density, and pulmonary function indexes compared to the SG while having considerably higher values for emphysema index (EI) and air trapping index (ATI) (all p < 0.001). Pearson correlation analysis revealed that lung volume, average inspiratory lung density, and IgA levels had strong positive correlations with one-second forced expiratory volume (FEV1), FEV1/forced vital capacity (FVC), and diffuse carbon monoxide (DLCO) (with respective r-values of 0.824, 0.841, and 0.829; all p < 0.001). In contrast, EI and ATI exhibited significantly negative correlations with FEV1, FEV1/FVC, and DLCO (with r-values ranging from -0.837 to -0.885; all p < 0.001). CONCLUSIONS: The assessment of serum IgA combined with thoracic CT parameters offers valuable insights for diagnosing and evaluating acute exacerbations of COPD, presenting a straightforward clinical utility.

Downregulation of apoptotic repressor AVEN exacerbates cardiac injury after myocardial infarction.

Myocardial infarction (MI) is a leading cause of heart failure (HF), associated with morbidity and mortality worldwide. As an essential part of gene expression regulation, the role of alternative polyadenylation (APA) in post-MI HF remains elusive. Here, we revealed a global, APA-mediated, 3' untranslated region (3' UTR)-lengthening pattern in both human and murine post-MI HF samples. Furthermore, the 3' UTR of apoptotic repressor gene, AVEN, is lengthened after MI, contributing to its downregulation. AVEN knockdown increased cardiomyocyte apoptosis, whereas restoration of AVEN expression substantially improved cardiac function. Mechanistically, AVEN 3' UTR lengthening provides additional binding sites for miR-30b-5p and miR-30c-5p, thus reducing AVEN expression. Additionally, PABPN1 (poly(A)-binding protein 1) was identified as a potential regulator of AVEN 3' UTR lengthening after MI. Altogether, our findings revealed APA as a unique mechanism regulating cardiac injury in response to MI and also indicated that the APA-regulated gene, AVEN, holds great potential as a critical therapeutic target for treating post-MI HF.

Predictive value of reduced pulmonary arterial elasticity in acute pulmonary embolism for right ventricular dysfunction.

BACKGROUND: Computed tomography pulmonary angiography (CTPA) yields indices, such as the right ventricular/left ventricular (RV/LV) ratio > 1.0, which are commonly used for risk stratification of patients with acute pulmonary embolism (APE). Although pulmonary artery elasticity (PAE) has been previously described, its relationship with right ventricular dysfunction (RVD) has not been explored. Here, we investigated whether PAE, measured using CTPA, is associated with RVD. METHODS: Patients who underwent retrospective electrocardiogram-gated CTPA and had a definitive diagnosis of APE were included in the study. The subjects were classified into RVD and non-RVD groups according to the RVD on echocardiography. PAE, involving aortic distensibility (AD), aortic compliance (AC), and aortic stiffness (ASI), and right heart function indices were compared between the two groups, and their correlations were examined. Receiver operating characteristic (ROC) curves were generated to evaluate the specificity and sensitivity of the RVD prediction. RESULTS: Thirty-five patients with APE were enrolled in the study (RVD: 18, non-RVD: 17). The groups showed no significant differences in age, sex, number of patients receiving thrombolysis, and number of high-risk conditions (P > 0.05). Regarding PAE parameters, AD was significantly reduced in the RVD group compared to that in the non-RVD group (P < 0.05), whereas AC and ASI were not statistically different (P > 0.05). The ratio of the maximum cross-sectional area of PA and AA (PA/AAmax),the ratio of the minimum cross-sectional area of PA and AA(PA/AAmin), diameter of the coronary sinus, RV/LV diameter, RV/Lvarea, the ratio of the end-diastolic volume of right ventricular and left ventricular (RV/LVDV), the ratio of the end-systolic volume of right ventricular and left ventricular (RV/LVSV) were significantly greater in the RVD group than in the non-RVD group (P < 0.05). Correlation analysis of AD and right heart function parameters showed that AD was negatively correlated with PA/AAmax, PA/AAmin, RV/LV diameter, RV/LVDV, and PAE measured by ultrasound, with correlation coefficients ranging from - 0.336 to - 0.580 (P < 0.05). The ROC curves of AD and RV/LVdiameter to predict RVD had areas under the curve of 0.748 and 0.712, sensitivities of 82.35% and 70.59%, specificities of 66.67% and 72.22%, and cutoff values of 4.9433 and 1.1105, respectively. CONCLUSION: AD obtained by retrospective ECG-gated CTPA may be helpful in assessing RVD in patients with APE while accurately diagnosing APE. It contributes to timely diagnosis and treatment and improves the prognosis of patients with APE.

Predictive value of coronary stenosis degree combined with CT-FFR and resting-state CTP for major adverse cardiac events in obstructive coronary artery disease.

CT-based flow reserve fraction (CT-FFR) and CT perfusion (CTP), as a complement to coronary computed tomographic angiography (CCTA) have been revealed to be associated with the prognosis of patients with obstructive coronary artery disease (CAD). However, the prognostic value of coronary stenosis combined with CT-FFR and resting-state CTP based on CCTA for major adverse cardiac events (MACE) is not known and requires further investigation. Fifty-two patients with obstructive CAD (50%-90% stenosis) examined by CCTA were retrospectively collected and followed-up for the occurrence of MACE. Logistic regression was performed to analyze the effects of the degree of coronary stenosis, resting-state CTP, and CT-FFR in predicting the risk of MACE. MACE prediction models were developed, and the area under the receiver operating characteristic curve (AUC) was used to evaluate the predictive validity of different models for MACE. Ethics approval was provided by the First Affiliated Hospital of Hebei North University (Zhangjiakou, China; No. K2020237). Logistic regression analysis showed that coronary artery stenosis ≥ 70%, CT-FFR ≤ 0.80, and perfusion index (PI) were independent predictors for MACE in patients with obstructive CAD (P < .05). The model based on coronary stenosis combined with PI and CT-FFR (AUC = 0.944) was better than those based on the degree of coronary stenosis combined with PI (AUC = 0.874), coronary stenosis degree combined with CT-FFR (AUC = 0.895), and any single index (P < .05). The combined model established by coronary stenosis, CT-FFR, and resting-state CTP based on a "1-stop" CCTA examination for predicting MACE among patients with obstructive CAD has good diagnostic efficacy and shows incremental discriminatory power.

Comparison of value of 640-slice CT kidney scan and kidney ultrasound in the diagnosis of chronic kidney disease.

To explore the value of 640-slice CT kidney scan and kidney ultrasound (KUS) in the diagnosis of chronic kidney disease (CKD). The data of 120 CKD patients at our institution between June 2019 and September 2020 were analyzed, and they were randomly divided into ultrasound (US) group (n = 40, KUS), CT group (n = 40) first receiving a plane CT scan to determine the scope of dynamic volume scan, which was performed for scans in cortical, parenchymal, and delayed phases with bolus injection of contrast medium, and combined group (n = 40, KUS and 640-slice CT kidney scan), with the images obtained read and analyzed. The subjective scores and effective radiation doses of 640-layer CT kidney scan were counted to calculate the detection rates. The subjective scores of 640-slice CT kidney scan in plane scan, cortical phase, parenchymal phase, and delayed phase were (1.23 ± 0.42), (1.80 ± 0.40), (2.08 ± 0.26), (2.18 ± 0.38) in the CT group and (1.18 ± 0.38), (1.85 ± 0.36), (2.08 ± 0.26), (2.20 ± 0.40) in the combined group. The effective radiation doses in the CT and combined groups were (1.92 ± 0.32) mSv and (1.95 ± 0.35) mSv. The reading results showed that 26 cases (65.0%), 30 cases (75.0%), and 38 cases (95.0%) were detected in the US, CT and combined groups, respectively, with remarkably higher detection rate in the combined group than the US and CT groups (P < 0.05). 640-slice CT kidney scan and KUS can be adopted for the diagnosis of CKD; with low radiation dose, good image quality, and higher detection rate in the former, their combination can improve the clinical detection rate of CKD and is worth promoting.