Search

Abstract Introduction Sepsis-associated acute kidney injury (SA-AKI) is strongly associated with poor prognosis. We aimed to build a machine learning (ML)-based clinical model to predict 1-year mortality in patients with SA-AKI. Methods Six ML algorithms were included to perform model fitting. Feature selection was based on the feature importance evaluated by the SHapley Additive exPlanations (SHAP) values. Area under the receiver operating characteristic curve (AUROC) was used to evaluate the discriminatory ability of the prediction model. Calibration curve and Brier score were employed to assess the calibrated ability. Our ML-based prediction models were validated both internally and externally. Results A total of 12,750 patients with SA-AKI and 55 features were included to build the prediction models. We identified the top 10 predictors including age, ICU stay and GCS score based on the feature importance. Among the six ML algorithms, the CatBoost showed the best prediction performance with an AUROC of 0.813 and Brier score of 0.119. In the external validation set, the predictive value remained favorable (AUROC = 0.784). Conclusion In this study, we developed and validated a ML-based prediction model based on 10 commonly used clinical features which could accurately and early identify the individuals at high-risk of long-term mortality in patients with SA-AKI.

Concrete crack identification methods based on machine learning can greatly improve extraction efficiency and precision. However, in many cases, model training requires a large amount of sample data, and insufficient data makes it difficult to effectively obtain model parameters. This study introduces a deep learning framework that integrates filters, principal component analysis, and attention mechanisms suitable for small sample sizes. Firstly, the histogram equalization method is used for the raw images, which can effectively enhance image contrast. Then, to acquire effective images of the crack, different methods are employed for crack detection, which are subsequently handled by principal component analysis (PCA) for optimal feature choice. Att-Unet and Att-Mask R-cnn segmentation models are used to design the detection for concrete cracks. To raise the learning ability of the segmentation models, an attention mechanism is applied to each feature layer of the decoder, and the loss function is evaluated using a combination of the Focal function and Cross Entropy. To verify the effectiveness of the proposed method, Deep Crack datasets and 76 sets of concrete crack data were collected for testing. Experimental results have shown that the method proposed can significantly reduce the model’s demand for data volume and improve training speed, which provides a new direction for small-sample crack extraction.

Abstract Right ventricular (RV)‐pulmonary arterial uncoupling is the consequence of increased afterload and/or decreased RV contractility. However, the combination of arterial elastance (Ea) and end‐systolic elastance (Ees)/Ea ratio to assess RV function is unclear. We hypothesized that the combination of both could comprehensively assess RV function and refine risk stratification. The median Ees/Ea ratio (0.80) and Ea (0.59 mmHg/mL) were used to classify 124 patients with advanced heart failure into four groups. RV systolic pressure differential was defined as end‐systolic pressure (ESP) minus beginning‐systolic pressure (BSP). Patients among different subsets showed dissimilar New York Heart Association functional class (V = 0.303, p = 0.010), distinct tricuspid annular plane systolic excursion/ pulmonary artery systolic pressure (mm/mmHg; 0.65 vs. 0.44 vs. 0.32 vs. 0.26, p

ObjectivesInflammation is involved in the mechanisms of non-ischemic heart failure (NIHF). We aimed to investigate the prognostic value of 21 inflammatory biomarkers and construct a biomarker risk score to improve risk prediction for patients with NIHF.MethodsPatients diagnosed with NIHF without infection during hospitalization were included. The primary outcome was defined as all-cause mortality and heart transplantations. We used elastic net Cox regression with cross-validation to select inflammatory biomarkers and construct the best biomarker risk score model. Discrimination, calibration, and reclassification were evaluated to assess the predictive value of the biomarker risk score.ResultsOf 1,250 patients included (median age, 53 years, 31.9% women), 436 patients (34.9%) experienced the primary outcome during a median of 2.8 years of follow-up. The final biomarker risk score included high-sensitivity C-reactive protein-to-albumin ratio (CAR) and red blood cell distribution width-standard deviation (RDW-SD), both of which were 100% selected in 1,000 times cross-validation folds. Incorporating the biomarker risk score into the best basic model improved the discrimination (ΔC-index = 0.012, 95% CI 0.003–0.018) and reclassification (IDI, 2.3%, 95% CI 0.7%–4.9%; NRI, 17.3% 95% CI 6.4%–32.3%) in risk identification. In the cross-validation sets, the mean time-dependent AUC ranged from 0.670 to 0.724 for the biomarker risk score and 0.705 to 0.804 for the basic model with a biomarker risk score, from 1 to 8 years. In multivariable Cox regression, the biomarker risk score was independently associated with the outcome in patients with NIHF (HR 1.76, 95% CI 1.49–2.08, p < 0.001, per 1 score increase).ConclusionsAn inflammatory biomarker-derived risk score significantly improved prognosis prediction and risk stratification, providing potential individualized therapeutic targets for NIHF patients.

Background: Afterload-related cardiac performance (ACP), a diagnostic parameter for septic cardiomyopathy, integrates both cardiac performance and vascular effects and could predict prognosis in septic shock. Objectives: We hypothesized that ACP would also correlate with clinical outcomes in patients with chronic heart failure (HF). Design: A retrospective study. Methods: We retrospectively studied consecutive patients with chronic HF who underwent right heart catheterization and established an expected cardiac output-systemic vascular resistance (CO-SVR) curve model in chronic HF for the first time. ACP was calculated as CO measured /CO predicted × 100%. ACP > 80%, 60%

Background: The prognostic significance of QRS duration (QRSd) in patients with dilated cardiomyopathy (DCM) and a left ventricular ejection fraction (LVEF) between 30% and 50% is unclear, resulting in questions regarding eligibility for cardiac resynchronisation therapy. This study aimed to explore the prognostic role of QRSd in patients with DCM and a LVEF 30–50% or LVEF

Covalent organic framework-based membranes are highly tunable materials with potential use in a variety of applications. Here the authors report a dual-activation interfacial polymerization strategy to prepare ionic covalent organic framework membranes with high ion exchange capacity.

Abstract Determining the etiology of end-stage renal disease (ESRD) constitutes a great challenge in the context of renal transplantation. Evidence is lacking on the genetic findings for adult renal transplant recipients through exome sequencing (ES). Adult patients on kidney transplant waitlist were recruited from 2017 to 2019. Trio-ES was conducted for the families who had multiple affected individuals with nephropathy or clinical suspicion of a genetic kidney disease owing to early onset or extrarenal features. Pathogenic variants were confirmed in 62 from 115 families post sequencing for 421 individuals including 195 health family members as potential living donors. Seventeen distinct genetic disorders were identified confirming the priori diagnosis in 33 (28.7%) families, modified or reclassified the clinical diagnosis in 27 (23.5%) families, and established a diagnosis in two families with ESRD of unknown etiology. In 14.8% of the families, we detected promising variants of uncertain significance in candidate genes associated with renal development or renal disease. Furthermore, we reported the secondary findings of oncogenes in 4.4% of the patients and known single-nucleotide polymorphisms associated with pharmacokinetics in our cohort to predict the drug levels of tacrolimus and mycophenolate. The diagnostic utility of the genetic findings has provided new clinical insight in most families that help with preplanned renal transplantation.

This study aimed to investigate the predictive value of Big endothelin-1(ET-1) for left ventricular reverse remodeling (LVRR) and prognosis in patients with dilated cardiomyopathy (DCM). Patients with DCM and a left ventricular ejection fraction (LVEF) ≤ 50% from 2008 to 2017 were included. LVRR was defined as the LVEF increased by at least 10% or follow-up LVEF increased to at least 50% with a minimum improvement of 5%; meanwhile, the index of left ventricular end-diastolic diameter (LVEDDi) decreased by at least 10% or LVEDDi decreased to ≤33 mm/m2. The composite outcome for prognostic analysis consisted of death and heart transplantations. Of the 375 patients included (median age 47 years, 21.1% female), 135 patients (36%) had LVRR after a median of 14 months of treatment. An independent association was found between Big ET-1 at baseline and LVRR in the multivariate model (OR 0.70, 95% CI 0.55–0.89, p = 0.003, per log increase). Big ET-1, body mass index, systolic blood pressure, diagnosis of type 2 diabetes mellitus (T2DM) and treatment with ACEI/ARB were significant predictors for LVRR after stepwise selection. Adding Big ET-1 to the model improved the discrimination (∆AUC = 0.037, p = 0.042 and reclassification (IDI, 3.29%; p = 0.002; NRI, 35%; p = 0.002) for identifying patients with LVRR. During a median follow-up of 39 (27–68) months, Big ET-1 was also independently associated with the composite outcome of death and heart transplantations (HR 1.45, 95% CI 1.13–1.85, p = 0.003, per log increase). In conclusion, Big ET-1 was an independent predictor for LVRR and had prognostic implications, which might help to improve the risk stratification of patients with DCM.

No study has examined myocardial work in subjects with cancer therapy-related cardiac dysfunction (CTRCD). Myocardial work, as a new ultrasonic indicator, reflects the metabolism and oxygen consumption of the left ventricle. The aim of this study was to test the relative value of new indices of myocardial work and global longitudinal strain (GLS) in detecting changes in myocardial function during the treatment of breast cancer by two-dimensional and three-dimensional echocardiography. We enrolled 79 breast cancer patients undergoing different tumor treatment regimens. Follow-up observation was conducted before and after chemotherapy. The effects of breast cancer chemotherapy and targeted therapy on the development of CTRCD [defined as an absolute reduction in left ventricular ejection fraction (LVEF) of >5% to

Recently, the overall survival (OS) and progression-free survival (PFS) of patients with advanced cancer has been significantly improved due to the application of immune checkpoint inhibitors (ICIs). Low response rate and high occurrence of immune-related adverse events (irAEs) make urgently need for ideal predictive biomarkers to identity efficient population and guide treatment strategies. Cytokines are small soluble proteins with a wide range of biological activity that are secreted by activated immune cells or tumor cells and act as a bridge between innate immunity, infection, inflammation and cancer. Cytokines can be detected in peripheral blood and suitable for dynamic detection. During the era of ICIs, many studies investigated the role of cytokines in prediction of the efficiency and toxicity of ICIs. Herein, we review the relevant studies on TNF-α, IFN-γ, IL-6, IL-8, TGF-β and other cytokines as biomarkers for predicting ICI-related reactions and adverse events, and explore the immunomodulatory mechanisms. Finally, the most important purpose of this review is to help identify predictors of ICI to screen patients who are most likely to benefit from immunotherapy.

Abstract Background Treacher Collins syndrome‐1 (TCS1; OMIM# 154500) is a rare autosomal dominant disease that is defined by congenital craniofacial dysplasia. Here, we report four sporadic and one familial case of TCS1 in Chinese patients with clinical features presenting as hypoplasia of the zygomatic complex and mandible, downslanting palpebral fissures, coloboma of the lower eyelids, and conductive hearing loss. Materials and Methods Audiological, radiological, and physical examinations were performed. Targeted next‐generation sequencing (NGS) was performed to examine the genetics of this disease in five probands, and Sanger sequencing was used to confirm the identified variants. A literature review discusses the pathogenesis, treatment, and prevention of TCS1. Results We identified a novel insertion of c.939_940insA (p.Gly314Argfs*35; NM_001135243.1), a novel deletion of c.1766delC (p.Pro589Leufs*7), two previously reported insertions of c.1999_2000insC (p.Arg667Profs*31) and c.4218_4219insG (p.Ser1407Valfs*23), and one previously reported deletion of c.4369_4373delAAGAA (p.Lys1457Glufs*12) in the TCOF1 gene. All five cases exhibited a degree of interfamilial and intrafamilial phenotypic variability. A review of the literature revealed no clear evidence of a genotype–phenotype correlation in TCS1. Conclusion Our results expand the variant spectrum of TCOF1 and highlight that NGS is essential for the diagnosis of TCS and that genetic counseling is beneficial for guiding prevention.

Ohr, a bacterial protein encoded by the Organic Hydroperoxide Resistance (ohr) gene, plays a critical role in resistance to organic hydroperoxides. In the present study, we show that the Cys-based thiol-dependent Ohr of Corynebacterium glutamicum decomposes organic hydroperoxides more efficiently than hydrogen peroxide. Replacement of either of the two Cys residues of Ohr by a Ser residue resulted in drastic loss of activity. The electron donors supporting regeneration of the peroxidase activity of the oxidized Ohr of C. glutamicum were principally lipoylated proteins (LpdA and Lpd/SucB). A Δohr mutant exhibited significantly decreased resistance to organic hydroperoxides and marked accumulation of reactive oxygen species (ROS) in vivo; protein carbonylation was also enhanced notably. The resistance to hydrogen peroxide also decreased, but protein carbonylation did not rise to any great extent. Together, the results unequivocally show that Ohr is essential for mediation of organic hydroperoxide resistance by C. glutamicum.

Anthracycline drugs are considered to be pivotal drugs in numerous chemotherapy regimens for breast cancer. However, the cardiotoxicity associated with the treatment is an important issue to be addressed. With the emergence of increasingly diverse antitumor drugs, anthracycline-free therapies are able to reduce the cardiotoxicity caused by anthracycline drugs while ensuring that a therapeutic effect is achieved. In the present review, anthracycline-free oncological therapy regimens for the treatment of patients with human epidermal growth factor receptor 2 (HER2)-positive breast cancer and the associated cardiovascular toxicity are discussed, as well as some monitoring strategies. It is recommended that patients with HER2-positive breast cancer patients should receive adjuvant chemotherapy with single or dual-targeted therapy, with or without endocrine therapy according to the hormone receptor status determined by immunohistochemical examination. The main side effects of targeted therapy include cardiac dysfunction, hypertension and arrhythmia. According to individual risk stratification, it is recommended that patients should be periodically monitored using echocardiography, electrocardiography and serum markers, to enable the timely detection of the cardiovascular adverse reactions associated with tumor treatment, thereby preventing the morbidity and mortality caused by the cardiotoxicity of these drugs. [ABSTRACT FROM AUTHOR]