Change in minimum indexed left atrial volume predicts incident heart failure: the multi-ethnic study of atherosclerosis

Funding Acknowledgements

Type of funding sources: None.

Background and Purpose

Longitudinal change in the left atrium prior to the onset of heart failure has not been as well studied as left atrial (LA) dysfunction in pre-existing heart failure. This study used cardiac magnetic resonance (CMR) imaging to investigate the relationship between longitudinal change in LA volume and function and incident heart failure (HF), in a multi-ethnic population free of known cardiovascular disease at baseline.

Methods and Results

In the Multi-Ethnic Study of Atherosclerosis (MESA), 2470 participants (60±9 years, 47% males), free at baseline of clinically recognized cardiovascular disease, had LA volume, emptying fractions and peak longitudinal strain assessed with Multimodality Tissue Tracking (MTT; version 6.0 Toshiba, Japan) on CMR imaging at baseline (2000-02) and at follow-up 9.4±0.6 years later. Seventy three (3%) participants subsequently developed incident HF 7.1±2.1 years after the follow-up CMR exam. In cox regression models, an annualized change in all LA parameters were significantly associated with an increased risk of incident HF. An annual increase of 1ml/m2 in minimum indexed LA volumes (∆LAVimin) was most strongly associated with the risk of incident HF (Hazard Ratio(HR)=1.85, 95% confidence interval(CI) [1.49-2.29], P<0.001) and improved model reclassification and discrimination in predicting incident HF (c-statistic=0.80, 95%CI [0.75-0.86]; NRI=0.13, P=0.04; IDI=0.04, P=0.01; x2=6.52, P=0.69) adjusting for known risk factors (age, gender, systolic blood pressure, anti-hypertensive medication use, smoking status, diabetes mellitus, total cholesterol, previous atrial fibrillation) and baseline LA parameters.

Conclusion

In this multi-ethnic population free of clinical cardiovascular disease at baseline, ∆LAVimin was most strongly associated with, and incrementally predictive of incident HF, after adjusting for known risk factors and baseline LA measures.

A Machine Learning Model for Detection of Coronary Artery Disease Using Noninvasive Clinical Parameters

Background and Objective: Coronary artery disease (CAD) is one of the most prevalent causes of death worldwide. The early diagnosis and timely medical care of cardiovascular patients can greatly prevent death and reduce the cost of treatments associated with CAD. In this study, we attempt to prepare a new model for early CAD diagnosis. The proposed model can diagnose CAD based on clinical data and without the use of an invasive procedure. Methods: In this paper, machine-learning (ML) techniques were used for the early detection of CAD, which were applied to a CAD dataset known as Z-Alizadeh Sani. Since this dataset has 54 features, the Pearson correlation feature selection method was conducted to identify the most effective features. Then, six machine learning techniques including decision tree, deep learning, logistic regression, random forest, support vector machine (SVM), and Xgboost were employed based on a semi-random-partitioning framework. Result: Applying Pearson feature selection to the dataset demonstrated that only eight features were the most effective for CAD diagnosis. The results of running the six machine-learning models on the selected features showed that logistic regression and SVM had the same performance with 95.45% accuracy, 95.91% sensitivity, 91.66% specificity, and a 96.90% F1 score. In addition, the ROC curve indicates a similar result regarding the AUC (0.98). Conclusions: Prediction is an important component of medical decision support systems. The results of the present study showed that feature selection has a high impact on machine-learning performance and, regardless of the evaluation metrics of the machine-learning models, determining the effective features is very important. However, SVM and Logistic Regression were designated as the best models according to our selected features.

An Energy-Efficient and Blockchain-Integrated Software Defined Network for the Industrial Internet of Things

The number of unsecured and portable Internet of Things (IoT) devices in the smart industry is growing exponentially. A diversity of centralized and distributed platforms have been implemented to defend against security attacks; however, these platforms are insecure because of their low storage capacities, high power utilization, single node failure, underutilized resources, and high end-to-end delay. Blockchain and Software-Defined Networking (SDN) are growing technologies to create a secure system and to ensure safe network connectivity. Blockchain technology offers a strong and trustworthy foundation to deal with threats and problems, including safety, privacy, adaptability, scalability, and security. However, the integration of blockchain with SDN is still in the implementation phase, which provides an efficient resource allocation and reduced latency that can overcome the issues of industrial IoT networks. We propose an energy-efficient blockchain-integrated software-defined networking architecture for Industrial IoT (IIoT) to overcome these challenges. We present a framework for implementing decentralized blockchain integrated with SDN for IIoT applications to achieve efficient energy utilization and cluster-head selection. Additionally, the blockchain-enabled distributed ledger ensures data consistency throughout the SDN controller network and keeps a record of the nodes enforced in the controller. The simulation result shows that the proposed model provides the best energy consumption, end-to-end latency, and overall throughput compared to the existing works.

Change in left atrial function and volume predicts heart failure with preserved and reduced ejection fraction: the multi-ethnic study of atherosclerosis

Aims

This study used cardiac magnetic resonance (CMR) imaging to investigate the relationship between longitudinal change in left atrial (LA) function and incident heart failure (HF), in a multi-ethnic population free of known cardiovascular disease at baseline.

Methods and results

In the Multi-Ethnic Study of Atherosclerosis (MESA), 2470 participants (60±9 years, 47% males), free at baseline of clinically recognized cardiovascular disease, had LA volume and function assessed with CMR imaging at baseline (2000–02) and 9.4±0.6 years later. Seventy three (3%) participants developed incident HF over 7.1±2.1 years; of these, 39 participants had preserved ejection fraction (HFpEF) and 34 participants had reduced ejection fraction (HFrEF). An annual decrease of 1-SD unit in peak LA strain (ΔLASmax) was most strongly associated with the risk of HFpEF (subdistribution HR=2.56, 95% confidence interval (CI) [1.34–4.90], P=0.004) and improved model reclassification and discrimination in predicting HFpEF (c-statistic=0.84, 95% CI [0.79–0.90]; NRI=0.34, P=0.01; IDI=0.02, P=0.02; x2=4.25, P=0.89) adjusting for event-specific risk factors and baseline LA parameters. An annual decrease of 1ml/m2 of pre-atrial LA volume index (ΔLAVipreA) was most strongly associated with the risk of HFrEF (subdistribution HR=1.88, 95% CI [1.44–2.45], P<0.001) and improved model reclassification and discrimination in predicting HFrEF (c-statistic=0.81, 95% CI (0.72–0.90); NRI=0.31, P=0.03; IDI=0.01, P=0.50; x2=15.4, P=0.08), adjusting for event-specific risk factors and baseline LA measures (Table 1).

Conclusion

In this multi-ethnic population free of clinical cardiovascular disease at baseline, ΔLASmax and ΔLAVipreA were associated with, and incrementally predictive of HFpEF and HFrEF respectively, after adjusting for event-specific risk factors and baseline LA measures.

Disclaimer

The views expressed in this abstract are those of the authors and do not necessarily represent the views of the National Heart, Lung, and Blood Institute; the National Institutes of Health; or the U.S. Department of Health and Human Services.

Funding Acknowledgement

Type of funding sources: Public Institution(s). Main funding source(s): National Heart, Lung and Blood InstituteNational Center for Advancing Translational Sciences

Prognostic value of a left atrioventricular coupling index (LACI) in pre- and post-menopausal women. from the multi-ethnic study of atherosclerosis (MESA)

Background

Endogenous sex hormones associated with both the left atrial (LA) and left ventricular (LV) structures in peri-menopausal women, but the association of menopause status with left atrioventricular coupling is not well established.

Purpose

To assess the prognostic value of a left atrioventricular coupling index (LACI) in pre- and post-menopausal women without a history of cardiovascular disease (CVD) at baseline in the Multi-Ethnic Study of Atherosclerosis (MESA).

Methods

In women participating in the MESA study, the LACI was measured as the ratio of the left atrial (LA) end-diastolic volume to the left ventricular (LV) end-diastolic volume using cardiovascular magnetic resonance (CMR). Cox proportional hazard models were used to assess the association between the LACI and the outcomes of atrial fibrillation (AF), heart failure (HF), and hard CVD defined by myocardial infarction, resuscitated cardiac arrest, stroke, or coronary heart disease death.

Results

Among the 2,087 women participants (61±10 years), 485 cardiovascular events were observed during the mean follow-up period of 13.2±3.3 years. A higher LACI was independently associated with AF (HR 1.70; 95% CI [1.51–1.90]), HF (HR 1.62; [1.33–1.97]), and hard CVD (HR 1.30; [1.13–1.51], all p<0.001). Adjusted models with the LACI showed significant improvement in model discrimination and reclassification when compared to currently used standard models used to predict the incidence of AF (C-statistic=0.82 vs. 0.79; NRI=0.325; IDI=0.036), HF (C-statistic=0.84 vs. 0.81; NRI=0.571; IDI=0.023), hard CVD (C-statistic=0.78 vs. 0.76; NRI=0.229; IDI=0.012).

Conclusion

In a multi-ethnic population of pre- and post-menopausal women, the LACI is an independent predictor of HF, AF, and hard CVD. In both pre- and post-menopausal women, the LACI has an incremental prognostic value for predicting cardiovascular events over traditional risk factors and sex hormone levels.

ClinicalTrials: gov Identifier: NCT00005487

Funding Acknowledgement

Type of funding sources: None.

Explainable AI for Bearing Fault Prognosis Using Deep Learning Techniques

Predicting bearing failures is a vital component of machine health monitoring since bearings are essential parts of rotary machines, particularly large motor machines. In addition, determining the degree of bearing degeneration will aid firms in scheduling maintenance. Maintenance engineers may be gradually supplanted by an automated detection technique in identifying motor issues as improvements in the extraction of useful information from vibration signals are made. State-of-the-art deep learning approaches, in particular, have made a considerable contribution to automatic defect identification. Under variable shaft speed, this research presents a novel approach for identifying bearing defects and their amount of degradation. In the proposed approach, vibration signals are represented by spectrograms, and deep learning methods are applied via pre-processing with the short-time Fourier transform (STFT). A convolutional neural network (CNN), VGG16, is then used to extract features and classify health status. After this, RUL prediction is carried out with the use of regression. Explainable AI using LIME was used to identify the part of the image used by the CNN algorithm to give the output. Our proposed method was able to achieve very high accuracy and robustness for bearing faults, according to numerous experiments.

Artificial Bee Colony Reinforced Extended Kalman Filter Localization Algorithm in Internet of Things with Big Data Blending Technique for Finding the Accurate Position of Reference Nodes

In recent years, the growth of internet of things (IoT) is immense, and the observations of their evolution need to be carried out effectively. The development of the IoT has been broadly adopted in the construction of intelligent environments. There are various challenging IoT issues such as routing messages, addressing, Localizing nodes, data blending, etc. Formerly learning eloquent information from big data systems to construct a data-gathering setup in an IoT environment is challenging. Among many viable data sources, the IoT is a rich big data source: Various IoT nodes produce a massive quantity of data. Localization is one of the crucial problems that make a significant impact inside the IoT system. It needs to be engaged with proper and effective procedures to collect all sorts of data without noise. Numerous localization procedures and schemes have been initiated by deploying the IoT sensor with wireless sensor networks for both interior and outside environments. To accomplish higher localization accuracy, with less cost for the large volume of data, it is considered a hectic task in the IoT sensor environment. By viewing the nature of the IoT, the merging of different technologies such as the internet, WiFi, etc., can aid diverse ways to acquire information about various objects' locations. Location-based service is an exceptional service of the IoT, whereas localization accuracy is a significant issue. The data generated from the sensor are available in both static and dynamic forms. In this article, a sophisticated accuracy localization scheme for big data is proposed with an optimization approach that can effectively produce proper and effective outcomes for IoT environments. The theme of the article is to develop an enriched Swarm Intelligence algorithm based on Artificial Bee Colony by using the EKF (Extended Kalman Filter) data blend technique for improving Localization in IoT for the unsuspecting environment. The performance of the proposed algorithm is evaluated by using communication consumption and Localization accuracy and its comparative advantage.

Prognostic value of left atrioventricular coupling index (LACI) in pre- and post-menopausal women : from the multi-ethnic study of atherosclerosis (MESA)

Funding Acknowledgements

Type of funding sources: None.

BACKGROUND

Although endogenous sex hormones influence both left atrial (LA) and left ventricular (LV) structure in peri-menopausal women, no study has ever evaluated the interaction between sex hormones levels and the left atrioventricular coupling.

PURPOSE

 This study aimed to assess the prognostic value of a left atrioventricular coupling index (LACI) in pre- and post-menopausal women without history of CVD at baseline.

METHODS

In all women participating in the Multi-Ethnic Study of Atherosclerosis (MESA) with baseline cardiovascular magnetic resonance (CMR) study, LACI was measured as the ratio of the LA end-diastolic volume divided by the LV end-diastolic volume. Cox proportional hazard models were used to assess the association between LACI and the outcomes of atrial fibrillation (AF), heart failure (HF), coronary heart disease (CHD) death, and hard CVD defined by myocardial infarction, resuscitated cardiac arrest, stroke, or CHD death. In multivariable analyses, the associations between LACI and the time-to-event were evaluated, adjusting for demographics, traditional cardiovascular risk factors, menopausal status and sex hormone levels.

RESULTS

Among the 2,087 women (61.2 ± 10.1 years), 485 cardiovascular events were observed during mean follow-up period of 13.2 ± 3.3 years. Greater LACI was independently associated with AF (HR 1.70; 95% CI [1.51-1.90]), HF (HR 1.62; 95% CI [1.33-1.97]), CHD death (HR 1.36; 95% CI [1.10-1.68]), and hard CVD (1.30; 95% CI [1.13-1.51], all p < 0.001). Adjusted models with LACI showed significant improvement in model discrimination and reclassification compared to currently used standard models to predict the incidences of AF (C-statistic: 0.82 vs. 0.79; NRI = 0.325; IDI = 0.036), HF (C-statistic: 0.84 vs. 0.81; NRI = 0.571; IDI = 0.023), CHD death (C-statistic: 0.87 vs. 0.85; NRI = 0.506; IDI = 0.012), and hard CVD (C-statistic: 0.78 vs. 0.76; NRI = 0.229; IDI = 0.012). The prognostic value of LACI was homogeneous in both pre- and post-menopausal women with a better discrimination and reclassification compared to individual LA or LV parameters.

CONCLUSIONS

In a multi-ethnic population of pre- and post-menopausal women, LACI is an independent predictor of HF, AF, CHD death and hard CVD. In both pre- and post-menopausal women, LACI has an incremental prognostic value to predict cardiovascular events over traditional risk factors and sex hormone levels.

ClinicalTrials.gov Identifier: NCT00005487 Abstract Figure. Kaplan-Meier curves by LACI terciles  Abstract Figure. Kaplan-Meier curves by LACI and Menop.

Hybrid Deep Neural Network for Handling Data Imbalance in Precursor MicroRNA

Over the last decade, the field of bioinformatics has been increasing rapidly. Robust bioinformatics tools are going to play a vital role in future progress. Scientists working in the field of bioinformatics conduct a large number of researches to extract knowledge from the biological data available. Several bioinformatics issues have evolved as a result of the creation of massive amounts of unbalanced data. The classification of precursor microRNA (pre miRNA) from the imbalanced RNA genome data is one such problem. The examinations proved that pre miRNAs (precursor microRNAs) could serve as oncogene or tumor suppressors in various cancer types. This paper introduces a Hybrid Deep Neural Network framework (H-DNN) for the classification of pre miRNA in imbalanced data. The proposed H-DNN framework is an integration of Deep Artificial Neural Networks (Deep ANN) and Deep Decision Tree Classifiers. The Deep ANN in the proposed H-DNN helps to extract the meaningful features and the Deep Decision Tree Classifier helps to classify the pre miRNA accurately. Experimentation of H-DNN was done with genomes of animals, plants, humans, and Arabidopsis with an imbalance ratio up to 1:5000 and virus with a ratio of 1:400. Experimental results showed an accuracy of more than 99% in all the cases and the time complexity of the proposed H-DNN is also very less when compared with the other existing approaches.

Sentiment Analysis on Movie Reviews Dataset Using Support Vector Machines and Ensemble Learning

The internet makes it easier for people to connect to each other and has become a platform to express ideas and share information with the world. The growth of the internet has indirectly led to the development of social networking sites. The reviews posted by people on these sites implies their opinion, and analysis over reviews is required to understand their intent. In this paper, natural language processing technique and machine learning algorithms are applied to classify the text data. The contributions of the proposed approach are three-fold: 1) chi square selector is applied to select the k-best features, 2) support vector machines is executed to classify the reviews (hyperparameters of the SVM classifier are tuned using GridSearch approach), and 3) bagging algorithm is applied with the base classifier over the newly built SVM classifier. The number of base classifiers of the bagging algorithm is varied accordingly. The results of the proposed approach are compared to the similar existing work, and hence, it is found to achieve better results as compared to the existing systems.

An assessment of introducers used for airway management

Different introducers are available to assist with tracheal intubation. Subtle differences in the design of introducers can have a marked effect on safety and performance. The Difficult Airway Society's Airway Device Evaluation Project Team proposal states that devices should only be purchased for which there is at least a case-control study on patients assessing airway devices. However, resources are not currently available to carry out a case-control study on all introducers available on the market. This study comprised a laboratory and manikin-based investigation to identify introducers that could be suitable for clinical investigation. We included six different introducers in laboratory-based assessments (design characteristics) and manikin-based assessments involving the participation of 30 anaesthetists. Each anaesthetist attempted placement in the manikin's trachea with each of the six introducers in a random order. Outcomes included first-time insertion success rate; insertion success rate; number of attempts; time to placement; and distance placed. Each anaesthetist also completed a questionnaire. First-time insertion success rate depended significantly on the introducer used (p = 0.0016) and varied from 47% (Armstrong and P3) to 77% (Intersurgical and Frova). Median time to placement (including oesophageal placement) varied from 10 s (Eschmann and Frova) to 20 s (P3) (p = 0.0025). Median time to successful placement in the trachea varied from 9 s (Frova) to 22 s (Armstrong) (p = 0.037). We found that the Armstrong and P3 devices were not as acceptable as other introducers and, without significant improvements to their design and characteristics, the use of these devices in studies on patients is questionable. The study protocol is suitable for differentiating between different introducers and could be used as a basis for assessing other types of devices.

Sternocleidomastoid pyomyositis

INTRODUCTION

Pyogenic myositis (pyomyositis) represents a bacterial infection of striated muscle. Predominantly associated with tropical regions and commonly caused by Staphylococcus aureus, the incidence of cervical pyomyositis is rare. To our knowledge, we report the first case of group A streptococcal cervical pyomyositis in an immunocompetent British Caucasian patient.

CASE PRESENTATION

A previously well 48-year-old Caucasian male presented with sore throat, left sided neck pain and swelling. He was a lifelong non-smoker with no recent travel or animal exposure. On admission, he was febrile with unilateral neck swelling. Random blood glucose was normal and an HIV test negative. CT imaging confirmed a large heterogeneous mass extending throughout the entirety of the left sternocleidomastoid muscle. The patient underwent exploration and drainage of a large intra-sternocleidomastoid neck abscess. Microbiology identified group A - streptococcus. Histology confirmed abscess formation in muscle with no acid-fast bacilli. The patient recovered well postoperatively and continues to do well.

DISCUSSION

Cervical pyomyositis is a rare condition that if not treated appropriately may cause internal jugular vein thrombosis, sepsis and death. Pyomyositis requires a high index of suspicion and should be considered a differential diagnosis in any painful swelling in the head and neck region.

Charge order superstructure with integer iron valence in Fe(2)OBO(3)

Solution-grown single crystals of Fe(2)OBO(3) were characterized by specific heat, Mössbauer spectroscopy, and x-ray diffraction. A peak in the specific heat at 340 K indicates the onset of charge order. Evidence for a doubling of the unit cell at low temperature is presented. Combining structural refinement of diffraction data and Mössbauer spectra, domains with diagonal charge order are established. Bond-valence-sum analysis indicates integer valence states of the Fe ions in the charge ordered phase, suggesting Fe(2)OBO(3) is the clearest example of ionic charge order so far.

Microvascular free tissue transfer in the management of squamous cell carcinoma of the tongue during pregnancy

We describe a 36-year-old patient with a stage III carcinoma (pT2N1M0) of the tongue that presented in the second trimester of pregnancy. It was treated by primary excision and reconstruction with a free flap. To our knowledge this is the first reported case of successful microvascular free tissue transfer for oral cancer during pregnancy.