Search

Objective: Fibromyalgia, a chronic pain disorder, impacts approximately 2% of adults in the US. Gabapentin and pregabalin are common treatments to manage fibromyalgia-related pain. Our recent study showed the risk of adverse cardiovascular events increased in diabetic neuropathy patients who were prescribed gabapentin or pregabalin. Here, we investigated whether the prescription of gabapentin or pregabalin has similar cardiovascular risk in patients with fibromyalgia. Methods: This retrospective cohort study leveraged electronic health records from 64 US healthcare organizations with 112 million patients. The study population included 105,602 patients first diagnosed with fibromyalgia and followed by a prescription of gabapentin, pregabalin, or other FDA-approved drugs for treating fibromyalgia from 2010 to 2019. Outcomes were deep venous thrombosis (DVT), myocardial infarcts (MI), peripheral vascular disease (PVD), strokes, heart failure, and pulmonary embolism (PE). In propensity-score-matched cohorts, 1-year and 5-year hazard ratios (HRs) were computed with their respective 95% confidence intervals (CIs). Additionally, we conducted sensitivity analyses on the subpopulations without other possible indications. Results: For 5-year follow-up, gabapentin increased the risk of PVD (HR = 1.46, 95% CI = 1.17–1.80), MI (HR = 1.31, 95% CI = 1.03–1.66), heart failure (HR = 1.27, 95% CI = 1.10–1.48), DVT (HR = 1.80, 95% CI = 1.33–2.44), and PE (HR = 2.23, 95% CI = 1.62–3.07). Pregabalin increased the risk of DVT (HR = 1.49, 95% CI = 1.01–2.20), and PE (HR = 2.24, 95% CI = 1.43–3.50). For 1-year follow-up, gabapentin increased the risk of PVD (HR = 1.32, 95% CI = 1.11–1.57), DVT (HR = 1.35, 95% CI = 1.09–1.68), and PE (HR = 1.36, 95% CI = 1.17–1.57). Pregabalin increased the risk of PVD (HR = 1.32, 95% CI = 1.06–1.63) and PE (HR = 1.25, 95% CI = 1.03–1.52). Sensitivity analyses showed similar trends. Conclusion: In fibromyalgia patients, the prescription of gabapentin and pregabalin moderately increased the risk of several adverse cardiovascular events. This risk, together with benefits and other adverse reactions, should be considered when prescribing these medications for fibromyalgia patients. [ABSTRACT FROM AUTHOR]

Pressure balance control between steel sleeve fillings and stratum is the key to ensuring project safety in the receiving construction of subway shield tunnels. Here, to realize the active regulation of the filing pressure in the steel sleeve, this study first improves the fixed cover of a conventional steel sleeve to a piston cover that can slide freely along the longitudinal direction of the sleeve and puts forward the corresponding methods for hydraulic pressure regulation and mechanical pressure regulation. The pressure-holding sealing performance of a new steel sleeve structure was tested, and a hydraulic pressure regulation method and a mechanical pressure regulation method were proposed. Finally, an effective path to proactive filler pressure regulation in the steel sleeve was explored. By improving the structure scheme of the steel sleeve, A steel sleeve model was designed at a 1:5 proportion, following the shield receiving steel sleeve structures and their sizes in practical tunneling. The model test was performed for several processes of active control of filler pressure, including pressurization by injection, decompression by discharge, machinal pressurization in low pressure, machinal pressurization in high pressure, and machinal decompression. The laws of filler pressure variation with hydraulic pressure and machinal thrust, the reactive force of hydraulic jack, and stress of steel sleeve were researched. The results revealed that the maximum stress of the new steel sleeve structure was 14.5 MPa under an elastic stress state, and the circumferential stress was always eight times the longitudinal stress. The new steel sleeve structure shows controllable pressure-holding sealing performance. The hydraulic pressure decrease appears as a slow linear trend of about 0.1% of the initial pressure per min after 1 min of pressure holding. The variation in the filler pressure at the central position of the steel sleeve is 16~24% greater than that at the periphery. Both hydraulic pressure regulation and mechanical pressure regulation could achieve controllable proactive regulation effects on a steel sleeve's filler pressure. The proposed new shield-receiving steel sleeve structure and the study results about its sealing performance and filler pressure regulation will promote the shield-receiving technology to be more controllable and safer. [ABSTRACT FROM AUTHOR]

Identifying disease-gene associations is important for understanding molecule mechanisms of diseases, finding diagnostic markers and therapeutic targets. Many computational methods have been proposed to predict disease related genes by integrating different biological databases into heterogeneous networks. However, it remains a challenging task to leverage heterogeneous topological and semantic information from multi-source biological data to enhance disease-gene prediction. In this study, we propose a knowledge graph-based disease-gene prediction system (GenePredict-KG) by modeling semantic relations extracted from various genotypic and phenotypic databases. We first constructed a knowledge graph that comprised 2,292,609 associations between 73,358 entities for 14 types of phenotypic and genotypic relations and 7 entity types. We developed a knowledge graph embedding model to learn low-dimensional representations of entities and relations, and utilized these embeddings to infer new disease-gene interactions. We compared GenePredict-KG with several state-of-the-art models using multiple evaluation metrics. GenePredict-KG achieved high performances [AUROC (the area under receiver operating characteristic) = 0.978, AUPR (the area under precision-recall) = 0.343 and MRR (the mean reciprocal rank) = 0.244], outperforming other state-of-art methods., (©2022 AMIA - All rights reserved.)

Elevated serum chloride levels (hyperchloremia) and the administration of intravenous (IV) fluids with high chloride content have both been associated with increased morbidity and mortality in certain subgroups of critically ill patients, such as those with sepsis. Here, we demonstrate this association in a general intensive care unit (ICU) population using data from the Medical Information Mart for Intensive Care III (MIMIC-III) database and propose the use of supervised learning to predict hyperchloremia in critically ill patients. Clinical variables from records of the first 24h of adult ICU stays were represented as features for four predictive supervised learning classifiers. The best performing model was able to predict second-day hyperchloremia with an AUC of 0.80 and a ratio of 5 false alerts for every true alert, which is a clinically-actionable rate. Our results suggest that clinicians can be effectively alerted to patients at risk of developing hyperchloremia, providing an opportunity to mitigate this risk and potentially improve outcomes.

Thoracic diseases are very serious health problems that plague a large number of people. Chest X-ray is currently one of the most popular methods to diagnose thoracic diseases, playing an important role in the healthcare workflow. However, reading the chest X-ray images and giving an accurate diagnosis remain challenging tasks for expert radiologists. With the success of deep learning in computer vision, a growing number of deep neural network architectures were applied to chest X-ray image classification. However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue. In this paper, to make a deep architecture more robust to noise and to reduce overfitting, we propose using deep generative classifiers to automatically diagnose thorax diseases from the chest X-ray images. Unlike the traditional deterministic classifier, a deep generative classifier has a distribution middle layer in the deep neural network. A sampling layer then draws a random sample from the distribution layer and input it to the following layer for classification. The classifier is generative because the class label is generated from samples of a related distribution. Through training the model with a certain amount of randomness, the deep generative classifiers are expected to be robust to noise and can reduce overfitting and then achieve good performances. We implemented our deep generative classifiers based on a number of well-known deterministic neural network architectures, and tested our models on the chest X-ray14 dataset. The results demonstrated the superiority of deep generative classifiers compared with the corresponding deep deterministic classifiers.