Atrial fibrillation symptom reduction and improved quality of life following the hybrid convergent procedure: a CONVERGE trial subanalysis.

Background: CONVERGE was a prospective, multicenter, randomized controlled trial that evaluated the safety of Hybrid Atrial Fibrillation Convergent (HC) and compared its effectiveness to endocardial catheter ablation (CA) for the treatment of persistent atrial fibrillation (PersAF) and longstanding PersAF (LSPAF). In 2020, we reported that CONVERGE met its primary safety and effectiveness endpoints. The primary objective of the present study is to report CONVERGE trial results for quality of life (QOL) and Class I/III anti-arrhythmic drug (AAD) utilization following HC. Methods: Eligible patients had drug-refractory symptomatic PersAF or LSPAF and a left atrium diameter ≤6.0 cm. Enrolled patients were randomized 2:1 to receive HC or CA. Atrial Fibrillation Severity Scale (AFSS) and the 36-Item Short Form Health Survey (SF-36) were assessed at baseline and 12 months; statistical comparison was performed using paired t-tests. AAD utilization at baseline through 12 and 18 months post-procedure was evaluated; statistical comparison was performed using McNemar's tests. Results: A total of 153 patients were treated with either HC (n=102) or CA (n=51). Of the 102 HC patients, 38 had LSPAF. AFSS and SF-36 Mental and Physical Component scores were significantly improved at 12 months versus baseline with HC overall and for the subset of LSPAF patients treated with either HC or CA. The proportion of HC patients (n=102) who used Class I /III AADs at 12 and 18 months was significantly less (33.3% and 36.3%, respectively) than baseline (84.3%; P<0.001). In LSPAF patients who underwent HC (n=38), AADs use was 29.0% through 18 months follow-up versus 71.1% at baseline (P<0.001). Conclusions: HC reduced AF symptoms, significantly improved QOL, and reduced AAD use in patients with PersAF and LSPAF. ClinicalTrialsgov Identifier: NCT01984346.

Unveiling the Hidden Stroke Threat in Patients With Atrial Fibrillation and Primary Hyperparathyroidism.

Recent American College of Cardiology (ACC), American Heart Association (AHA), American College of Clinical Pharmacy (ACCP), and Heart Rhythm Society (HRS) guidelines suggest that patients with atrial fibrillation (AF) at intermediate to low annual risk of ischemic stroke can benefit from consideration of factors that might modify their risk of stroke. The role of nontraditional risk factors, such as primary hyperparathyroidism (PHPT), remains unexplored. In our study, we investigated the potential association between PHPT and the risk of ischemic stroke in patients with AF. Using data from the Nationwide Inpatient Sample Database, a retrospective cohort study focused on the adult population with AF, we stratified the participants based on PHPT presence. Demographic information, co-morbidities, and hospitalization details were extracted using International Classification of Diseases, Tenth revision codes. Propensity score matching was applied, encompassing over 20 confounding variables, including the risk factors outlined in the CHA2DS2-VASc (Congestive heart failure (C), Hypertension (H), Age ≥75 years (A2), Diabetes Mellitus (D), Stroke/Transient Ischemic Attack (TIA)/Thromboembolism (S2), Vascular disease (V), Age 65-74 years (A), Sex category [female] (Sc)) score. Multivariate logistic regression analysis was performed after matching to assess the independent impact of PHPT as an ischemic stroke risk factor. A total of 2,051 of the identified 395,249 patients with AF had PHPT. The PHPT group had an average age of 74 years and consisted of more women (66.1% vs 53.0%). After matching, it was observed that the PHPT group had longer hospital stays (5 vs 4 days) and higher hospitalization charges ($45,126 vs $36,644). This group exhibited higher rates of ischemic stroke (6.0% vs 4.4%) and mortality (6.3% vs 4.9%). The adjusted outcomes showed a 1.4-fold increased risk for ischemic stroke and a 1.32-fold increased risk for mortality in the PHPT cohort. The subgroup analysis showed a higher incidence of mortality in men with a high CHA2DS2-VASc score. In conclusion, this study highlights a marked association between PHPT and ischemic stroke in patients with AF, independent of the conventional CHA2DS2-VASc score. The potential mechanisms implicated include vascular changes, cardiac dysfunction, and coagulation cascade alterations. The presence of PHPT should be taken into consideration when deciding the assessment of thromboembolic risk.

The utility and impact of outpatient telemetry monitoring in post-transcatheter aortic valve replacement patients.

BACKGROUND: Conduction disturbances are a common complication of transcatheter aortic valve replacement (TAVR). Mobile Cardiac Telemetry (MCT) allows for continuous monitoring with near "real time" alerts and has allowed for timely detection of conduction abnormalities and pacemaker placement in small trials. A standardized, systematic approach utilizing MCT devices post TAVR has not been widely implemented, leading to variation in use across hospital systems. OBJECTIVES: Our aim was to evaluate the utility of a standardized, systematic approach utilizing routine MCT to facilitate safe and earlier discharge by identifying conduction disturbances requiring permanent pacemaker (PPM) placement. We also sought to assess the occurrence of actionable arrhythmias in post-TAVR patients. METHODS: Using guidance from the JACC Scientific Expert Panel, a protocol was implemented starting in December 2019 to guide PPM placement post-TAVR across our health system. All patients who underwent TAVR from December 2019 to June 2021 across four hospitals within Northwell Health, who did not receive or have a pre-existing PPM received an MCT device at discharge and were monitored for 30 days. Clinical and follow-up data were collected and compared to pre initiative patients. RESULTS: During the initiative 693 patients were monitored with MCT upon discharge, 21 of whom required PPM placement. Eight of these patients had no conduction abnormality on initial or discharge ECG. 59 (8.6 %) patients were found to have new atrial fibrillation or flutter via MCT monitoring. There were no adverse events in the initiative group. Prior to the initiative, 1281 patients underwent TAVR over a one-year period. The initiative group had significantly shorter length of stay than pre-initiative patients (2.5 ± 4.5 vs 3.0 ± 3.8 days, p < 0.001) and lower overall PPM placement rate within 30 days post-TAVR (16 % vs 20.5 %, P = 0.0125). CONCLUSIONS: In our study, implementation of a standardized, systematic approach utilizing MCT in post-TAVR patients was safe and allowed for timely detection of conduction abnormalities requiring pacemaker placement. This strategy also detected new atrial fibrillation and flutter. Reduction in post TAVR pacemaker rate and length of stay were also noted although this effect is multifactorial.

Site-specific effects of dobutamine on cardiac conduction and refractoriness.

BACKGROUND: Isoproterenol, a non-specific beta agonist, is commonly used during electrophysiology studies (EPS). However, with the significant increase in the price of isoproterenol in 2015 and the increasing number of catheter ablations performed, the cost implications cannot be ignored. Dobutamine is a less expensive synthetic compound developed from isoproterenol with a similar mechanism to enhance cardiac conduction and shorten refractoriness, thus making it a feasible substitute with a lower cost. However, the use of dobutamine for EPS has not been well-reported in the literature. OBJECTIVE: To determine the site-specific effects of various doses of dobutamine on cardiac conduction and refractoriness and assess its safety during EPS. METHODS: From February 2020 to October 2020, 40 non-consecutive patients scheduled for elective EPS, supraventricular tachycardia, atrial fibrillation, and premature ventricular contraction ablations at a single center were consented and prospectively enrolled to assess the effect of dobutamine on the cardiac conduction system. At the end of each ablation procedure, measures of cardiac conduction and refractoriness were recorded at baseline and with incremental doses of dobutamine at 5, 10, 15, and 20 mcg/kg/min. For the primary analysis, the change per dose of dobutamine from baseline to each dosing level of dobutamine received by the patients, comparing atrioventricular node block cycle length (AVNBCL), ventricular atrial block cycle length (VABCL) and sinus cycle length (SCL), was tested using mixed-effect regression. For the secondary analysis, dobutamine dose level was tested for association with relative changes from baseline of each electrophysiologic parameter (SCL, AVNBCL, VABCL, atrioventricular node effective refractory period (AVNERP), AH, QRS, QT, QTc, atrial effective refractory period (AERP), ventricular effective refractory period (VERP), using mixed-effect regression. Changes in systolic and diastolic blood pressures were also assessed. The Holm-Bonferroni method was used to adjust for multiple testing. RESULTS: For the primary analysis there was no statistically significant change of AVNBCL and VABCL relative to SCL from baseline to each dose level of dobutamine. The SCL, AVNBCL, VABCL, AVNERP, AERP, VERP and the AH, and QT intervals all demonstrated a statistically significant decrease from baseline to at least one dose level with incremental dobutamine dosing. Two patients (5%) developed hypotension during the study and one patient (2.5%) received a vasopressor. Two patients (5%) had induced arrhythmias but otherwise no major adverse events were noted. CONCLUSION: In this study, there was no statistically significant change of AVNBCL and VABCL relative to SCL from baseline to any dose level of dobutamine. As expected, the AH and QT intervals, and the VABCL, VERP, AERP and AVNERP all significantly decreased from baseline to at least one dose level with an escalation in dobutamine dose. Dobutamine was well-tolerated and safe to use during EPS.

Ensemble classification of integrated CT scan datasets in detecting COVID-19 using feature fusion from contourlet transform and CNN.

The COVID-19 disease caused by coronavirus is constantly changing due to the emergence of different variants and thousands of people are dying every day worldwide. Early detection of this new form of pulmonary disease can reduce the mortality rate. In this paper, an automated method based on machine learning (ML) and deep learning (DL) has been developed to detect COVID-19 using computed tomography (CT) scan images extracted from three publicly available datasets (A total of 11,407 images; 7397 COVID-19 images and 4010 normal images). An unsupervised clustering approach that is a modified region-based clustering technique for segmenting COVID-19 CT scan image has been proposed. Furthermore, contourlet transform and convolution neural network (CNN) have been employed to extract features individually from the segmented CT scan images and to fuse them in one feature vector. Binary differential evolution (BDE) approach has been employed as a feature optimization technique to obtain comprehensible features from the fused feature vector. Finally, a ML/DL-based ensemble classifier considering bagging technique has been employed to detect COVID-19 from the CT images. A fivefold and generalization cross-validation techniques have been used for the validation purpose. Classification experiments have also been conducted with several pre-trained models (AlexNet, ResNet50, GoogleNet, VGG16, VGG19) and found that the ensemble classifier technique with fused feature has provided state-of-the-art performance with an accuracy of 99.98%.

Parallel CNN-ELM: A multiclass classification of chest X-ray images to identify seventeen lung diseases including COVID-19.

Numerous epidemic lung diseases such as COVID-19, tuberculosis (TB), and pneumonia have spread over the world, killing millions of people. Medical specialists have experienced challenges in correctly identifying these diseases due to their subtle differences in Chest X-ray images (CXR). To assist the medical experts, this study proposed a computer-aided lung illness identification method based on the CXR images. For the first time, 17 different forms of lung disorders were considered and the study was divided into six trials with each containing two, two, three, four, fourteen, and seventeen different forms of lung disorders. The proposed framework combined robust feature extraction capabilities of a lightweight parallel convolutional neural network (CNN) with the classification abilities of the extreme learning machine algorithm named CNN-ELM. An optimistic accuracy of 90.92% and an area under the curve (AUC) of 96.93% was achieved when 17 classes were classified side by side. It also accurately identified COVID-19 and TB with 99.37% and 99.98% accuracy, respectively, in 0.996 microseconds for a single image. Additionally, the current results also demonstrated that the framework could outperform the existing state-of-the-art (SOTA) models. On top of that, a secondary conclusion drawn from this study was that the prospective framework retained its effectiveness over a range of real-world environments, including balanced-unbalanced or large-small datasets, large multiclass or simple binary class, and high- or low-resolution images. A prototype Android App was also developed to establish the potential of the framework in real-life implementation.

Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture.

Around the world, several lung diseases such as pneumonia, cardiomegaly, and tuberculosis (TB) contribute to severe illness, hospitalization or even death, particularly for elderly and medically vulnerable patients. In the last few decades, several new types of lung-related diseases have taken the lives of millions of people, and COVID-19 has taken almost 6.27 million lives. To fight against lung diseases, timely and correct diagnosis with appropriate treatment is crucial in the current COVID-19 pandemic. In this study, an intelligent recognition system for seven lung diseases has been proposed based on machine learning (ML) techniques to aid the medical experts. Chest X-ray (CXR) images of lung diseases were collected from several publicly available databases. A lightweight convolutional neural network (CNN) has been used to extract characteristic features from the raw pixel values of the CXR images. The best feature subset has been identified using the Pearson Correlation Coefficient (PCC). Finally, the extreme learning machine (ELM) has been used to perform the classification task to assist faster learning and reduced computational complexity. The proposed CNN-PCC-ELM model achieved an accuracy of 96.22% with an Area Under Curve (AUC) of 99.48% for eight class classification. The outcomes from the proposed model demonstrated better performance than the existing state-of-the-art (SOTA) models in the case of COVID-19, pneumonia, and tuberculosis detection in both binary and multiclass classifications. For eight class classification, the proposed model achieved precision, recall and fi-score and ROC are 100%, 99%, 100% and 99.99% respectively for COVID-19 detection demonstrating its robustness. Therefore, the proposed model has overshadowed the existing pioneering models to accurately differentiate COVID-19 from the other lung diseases that can assist the medical physicians in treating the patient effectively.

Efficacy and Side Effect Profile of Intrathecal Morphine versus Distal Femoral Triangle Nerve Block for Analgesia following Total Knee Arthroplasty: A Randomized Trial.

(1) Background: The management of postoperative pain after knee replacement is an important clinical problem. The best results in the treatment of postoperative pain are obtained using multimodal therapy principles. Intrathecal morphine (ITM) and single-shot femoral nerve block (SSFNB) are practiced in the treatment of postoperative pain after knee replacement, with the most optimal methods still under debate. The aim of this study was to compare the analgesic efficacy with special consideration of selected side effects of both methods. (2) Materials and methods: Fifty-two consecutive patients undergoing knee arthroplasty surgery at the Department of Orthopedics and Traumatology of the Medical University of Warsaw were included in the study. Patients were randomly allocated to one of two groups. In the ITM group, 100 micrograms of intrathecal morphine were used, and in the SSFNB group, a femoral nerve block in the distal femoral triangle was used as postoperative analgesia. The other elements of anesthesia and surgery did not differ between the groups. (3) Results: The total dose of morphine administered in the postoperative period and the effectiveness of pain management did not differ significantly between the groups (cumulative median morphine dose in 24 h in the ITM group 31 mg vs. SSFNB group 29 mg). The incidence of nausea and pruritus in the postoperative period differed significantly in favor of patients treated with a femoral nerve block. (4) Conclusions: Although intrathecal administration of morphine is similarly effective in the treatment of pain after knee replacement surgery as a single femoral triangle nerve block, it is associated with a higher incidence of cumbersome side effects, primarily nausea and pruritus.

Enhanced susceptibility of SARS-CoV-2 spike RBD protein assay targeted by cellular receptors ACE2 and CD147: Multivariate data analysis of multisine impedimetric response.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) enters the cells through the binding of spike protein to the host cell surface-expressing angiotensin-converting enzyme 2 (ACE2) or by endocytosis mediated by extracellular matrix metalloproteinase inducer (CD147). We present extended statistical studies of the multisine dynamic electrochemical impedance spectroscopy (DEIS) revealing interactions between Spike RBD and cellular receptors ACE2 and CD147, and a reference anti-RBD antibody (IgG2B) based on a functionalised boron-doped diamond (BDD) electrode. The DEIS was supported by a multivariate data analysis of a SARS-CoV-2 Spike RBD assay and cross-correlated with the atomic-level information revealed by molecular dynamics simulations. This approach allowed us to study and detect subtle changes in the electrical properties responsible for the susceptibility of cellular receptors to SARS-CoV-2, revealing their interactions. Changes in electrical homogeneity in the function of the RBD concentration led to the conclusion that the ACE2 receptor delivers the most homogeneous surface, delivered by the high electrostatic potential of the relevant docking regions. For higher RBD concentrations, the differences in electrical homogeneity between electrodes with different receptors vanish. Collectively, this study reveals interdependent virus entry pathways involving separately ACE2, CD147, and spike protein, as assessed using a biosensing platform for the rapid screening of cellular interactions (i.e. testing various mutations of SARS-CoV-2 or screening of therapeutic drugs).

Thermal-Visible Face Recognition Based on CNN Features and Triple Triplet Configuration for On-the-Move Identity Verification.

Face recognition operating in visible domains exists in many aspects of our lives, while the remaining parts of the spectrum including near and thermal infrared are not sufficiently explored. Thermal-visible face recognition is a promising biometric modality that combines affordable technology and high imaging qualities in the visible domain with low-light capabilities of thermal infrared. In this work, we present the results of our study in the field of thermal-visible face verification using four different algorithm architectures tested using several publicly available databases. The study covers Siamese, Triplet, and Verification Through Identification methods in various configurations. As a result, we propose a triple triplet face verification method that combines three CNNs being used in each of the triplet branches. The triple triplet method outperforms other reference methods and achieves TAR @FAR 1% values up to 90.61%.

Applying supervised contrastive learning for the detection of diabetic retinopathy and its severity levels from fundus images.

Diabetic Retinopathy (DR) is a major complication in human eyes among the diabetic patients. Early detection of the DR can save many patients from permanent blindness. Various artificial intelligent based systems have been proposed and they outperform human analysis in accurate detection of the DR. In most of the traditional deep learning models, the cross-entropy is used as a common loss function in a single stage end-to-end training method. However, it has been recently identified that this loss function has some limitations such as poor margin leading to false results, sensitive to noisy data and hyperparameter variations. To overcome these issues, supervised contrastive learning (SCL) has been introduced. In this study, SCL method, a two-stage training method with supervised contrastive loss function was proposed for the first time to the best of authors' knowledge to identify the DR and its severity stages from fundus images (FIs) using "APTOS 2019 Blindness Detection" dataset. "Messidor-2" dataset was also used to conduct experiments for further validating the model's performance. Contrast Limited Adaptive Histogram Equalization (CLAHE) was applied for enhancing the image quality and the pre-trained Xception CNN model was deployed as the encoder with transfer learning. To interpret the SCL of the model, t-SNE method was used to visualize the embedding space (unit hyper sphere) composed of 128 D space into a 2 D space. The proposed model achieved a test accuracy of 98.36%, and AUC score of 98.50% to identify the DR (Binary classification) and a test accuracy of 84.364%, and AUC score of 93.819% for five stages grading with the APTOS 2019 dataset. Other evaluation metrics (precision, recall, F1-score) were also determined with APTOS 2019 as well as with Messidor-2 for analyzing the performance of the proposed model. It was also concluded that the proposed method achieved better performance in detecting the DR compared to the conventional CNN without SCL and other state-of-the-art methods.

Performance of electrochemical immunoassays for clinical diagnostics of SARS-CoV-2 based on selective nucleocapsid N protein detection: Boron-doped diamond, gold and glassy carbon evaluation.

The 21st century has already brought us a plethora of new threats related to viruses that emerge in humans after zoonotic transmission or drastically change their geographic distribution or prevalence. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first spotted at the end of 2019 to rapidly spread in southwest Asia and later cause a global pandemic, which paralyzes the world since then. We have designed novel immunosensors targeting conserved protein sequences of the N protein of SARS-CoV-2 based on lab-produced and purified anti-SARS-CoV-2 nucleocapsid antibodies that are densely grafted onto various surfaces (diamond/gold/glassy carbon). Titration of antibodies shows very strong reactions up to 1:72 900 dilution. Next, we showed the mechanism of interactions of our immunoassay with nucleocapsid N protein revealing molecular recognition by impedimetric measurements supported by hybrid modeling results with both density functional theory and molecular dynamics methods. Biosensors allowed for a fast (in less than 10 min) detection of SARS-CoV-2 virus with a limit of detection from 0.227 ng/ml through 0.334 ng/ml to 0.362 ng/ml for glassy carbon, boron-doped diamond, and gold surfaces, respectively. For all tested surfaces, we obtained a wide linear range of concentrations from 4.4 ng/ml to 4.4 pg/ml. Furthermore, our sensor leads to a highly specific response to SARS-CoV-2 clinical samples versus other upper respiratory tract viruses such as influenza, respiratory syncytial virus, or Epstein-Barr virus. All clinical samples were tested simultaneously on biosensors and real-time polymerase chain reactions.

Impact of Deposition of the (TiBx/TiSiyCz) x3 Multilayer on M2 HSS on the Cutting Force Components and Temperature Generated in the Machined Area during the Milling of 316L Steel.

High-speed steel (HSS) tools account for 20 percent of the cutting tools materials' global market. This is due to both their significant toughness and resistance to cracking, compared to cemented carbides. Covering steel tools with hard coatings clearly improves their mechanical properties, wear resistance, and significantly increases their durability. Physical vapor deposition methods are preferred for coating metal substrates, as they allow low temperature deposition. The most widely deposited coating materials are carbides, nitrides, and borides. They are combined with softer ones in the multilayer structure to promote increased resistance to cracking and delamination in comparison to monolayered structures. In this paper, the M2 steel end mills were coated by (TiBx/TiSiyCz) x3 multilayer by the pulsed laser deposition method. Coated and uncoated tools were tested in the cylindrical down milling of AISI 316L steel. Components of the cutting force and temperature generated in the machined area during dry milling were measured under two variants of operating conditions: V1 and V2. Tool wear mechanism was examined using scanning electron microscopy (SEM), accompanied by EDS analysis of worn areas. It was found that milling with higher speed (variant V2) is accompanied by lower cutting force components and a lower temperature generated in cutting area. The presence of the coating allowed lower cutting forces and temperature in the case of variant V1. The temperature measured during milling did not exceed 200 °C. The SEM observation of the edges of cutting tools indicated that the main mechanism of wear for both types of tools was abrasion. The built-up edge formation was observed in the case of tools tested at the V1 cutting parameters variant. It was assumed that it was the reason for higher cutting forces measured during milling according to this variant. The chemical composition of built-up edges was different for coated and uncoated tools. Tribo-chemical reactions were responsible for the reduction of the cutting force and temperature components observed during milling with a coated tool at V1 variant. Boron and titanium were the elements of the coating that enabled the tribo-oxidation reactions thanks to which friction was reduced. Our results show that this beneficial effect occurs with (TiBx/TiSiyCz) x3 coated tools, but can easily be lost with inadequately selected cutting parameters.

Compound motor action potentials in transient and persistent phrenic nerve injury - metanalysis.

BACKGROUND: The right phrenic nerve is vulnerable to injury (PNI) during cryoballoon ablation (CBA) isolation of the right pulmonary veins. The complication can be transient or persistent. The reported incidence of PNI fluctuates from 4.73% to 24.7% depending on changes over time, CBA generation, and selected protective methods. M e t h o d s: Through September 2019, a database search was performed on MEDLINE, EMBASE, and Cochrane Database. In the selected articles, the references were also extensively searched. The study provides a comprehensive meta-analysis of the overall prevalence of PNI, assesses the transient to persistent PNI ratio, the outcome of using compound motor action potentials (CMAP), and estimated average time to nerve recovery. R e s u l t s: From 2008 to 2019, 10,341 records from 48 trials were included. Out of 783 PNI retrieved from the studies, 589 (5.7%) and 194 (1.9%) were persistent. CMAP caused a significant reduction in the risk of persistent PNI from 2.3% to 1.1% (p = 0.05; odds ratio [OR] 2.13) in all CBA groups. The mean time to PNI recovery extended beyond the hospital discharge was significantly shorter in CMAP group at three months on average versus non CMAP at six months (p = 0.012). CMAP (in contrast to non-CMAP procedures) detects PNI earlier from 4 to 16 sec (p <0.05; I2 = 74.53%) and 3 to 9o (p <0.05; I2 = 97.24%) earlier. C o n c l u s i o n s: Right PNI extending beyond hospitalization is a relatively rare complication. CMAP use causes a significant decrease in the risk of prolonged injury and shortens the time to recovery.

Economics and laboratory efficiency of atrial fibrillation ablation.

PURPOSE OF REVIEW: Atrial fibrillation is a growing public health problem and is associated with an increased risk of comorbidities with enormous socioeconomic implications. This review article focuses on fiscal burden of atrial fibrillation on the healthcare system and economic value of atrial fibrillation ablations brought to the patient and the payers by improvement in outcomes and reduction in treatment costs. RECENT FINDINGS: This article summarizes the recently published studies evaluating the economic impact of atrial fibrillation treatment. Catheter ablation have shown to be the most successful strategy for treatment of defibrillation. However, repeat ablation is associated with higher costs, over and above any subsequent procedural costs, compared with a single ablation procedure for atrial fibrillation. Cryoballoon ablation has been shown to have fewer repeat ablations than radiofrequency ablations, which resulted in overall cost reduction. Improvement in laboratory efficiency, better utilization of laboratory resources and same-day discharge strategy can lead to further healthcare savings and increase in value to all stakeholders. SUMMARY: The value of healthcare delivery for patient with atrial fibrillation can be improved by advancement in technology that demonstrates cost reduction to the health system and outcomes improvements. Implementation of tactics that decrease cost and improve outcomes can alleviate some of the financial strain on healthcare systems, which is of extreme importance in the current climate.

Detection of Inflatable Boats and People in Thermal Infrared with Deep Learning Methods.

Smuggling of drugs and cigarettes in small inflatable boats across border rivers is a serious threat to the EU's financial interests. Early detection of such threats is challenging due to difficult and changing environmental conditions. This study reports on the automatic detection of small inflatable boats and people in a rough wild terrain in the infrared thermal domain. Three acquisition campaigns were carried out during spring, summer, and fall under various weather conditions. Three deep learning algorithms, namely, YOLOv2, YOLOv3, and Faster R-CNN working with six different feature extraction neural networks were trained and evaluated in terms of performance and processing time. The best performance was achieved with Faster R-CNN with ResNet101, however, processing requires a long time and a powerful graphics processing unit.

Impact of Cryoballoon Ablation on Electrophysiology Lab Efficiency During the Treatment of Patients With Persistent Atrial Fibrillation: A Subanalysis of the STOP Persistent AF Study.

BACKGROUND: The volume of atrial fibrillation (AF) catheter ablation procedures has increased to address the growing patient population with AF; however, the impact of cryoballoon ablation on electrophysiology (EP) lab throughput is under-studied when treating patients with persistent AF (PsAF). OBJECTIVE: To assess EP lab utilization associated with cryoballoon ablation for the treatment of patients with PsAF and to evaluate mechanisms that optimize hospital resources. METHODS: Procedural data derived from the STOP Persistent AF trial were input into a discrete event simulation to assess EP lab utilization during AF ablation procedures. Patient and physician delays and lab occupancy times were modeled in a nominal and efficient EP lab setting over 1000 days. Accounting for variation in procedural times, we evaluated the number of days in which preplanned pulmonary vein isolation (PVI) cases resulted in overtime or excess time for non-ablation EP cases within a given lab day. A sensitivity analysis determined the parameters that most strongly influenced EP lab throughput. RESULTS: Lab occupancy times for the Nominal Use (NU) case included 165 procedures, and the High-Efficiency Use (HEU) case was derived from 69 procedures conducted at sites with faster procedure times than average. The HEU case had shorter lab occupancy times than the NU case (158 ± 32 minutes vs 188 ± 51 minutes, respectively). In the NU case, a total of 2000 procedures were conducted, with 28 lab days (2.8%) extending into overtime and 900 lab days (90%) exhibiting excess time for a non-ablation EP case. In the HEU case, a total of 3000 procedures were conducted, with 87 lab days (8.7%) extending into overtime and 635 lab days (63.5%) exhibiting excess time for a non-ablation EP case. The model was most sensitive to lab occupancy duration and the time of day that overtime started. CONCLUSIONS: Cryoballoon ablation for the treatment of patients with PsAF confers EP lab efficiencies that can support 3 PVI cases in a lab day.

Thermal Face Verification through Identification.

This paper reports on a new approach to face verification in long-wavelength infrared radiation. Two face images were combined into one double image, which was then used as an input for a classification based on neural networks. For testing, we exploited two external and one homemade thermal face databases acquired in various variants. The method is reported to achieve a true acceptance rate of about 83%. We proved that the proposed method outperforms other studied baseline methods by about 20 percentage points. We also analyzed the issue of extending the performance of algorithms. We believe that the proposed double image method can also be applied to other spectral ranges and modalities different than the face.

COVID-19 Detection from Chest X-ray Images Using Feature Fusion and Deep Learning.

Currently, COVID-19 is considered to be the most dangerous and deadly disease for the human body caused by the novel coronavirus. In December 2019, the coronavirus spread rapidly around the world, thought to be originated from Wuhan in China and is responsible for a large number of deaths. Earlier detection of the COVID-19 through accurate diagnosis, particularly for the cases with no obvious symptoms, may decrease the patient's death rate. Chest X-ray images are primarily used for the diagnosis of this disease. This research has proposed a machine vision approach to detect COVID-19 from the chest X-ray images. The features extracted by the histogram-oriented gradient (HOG) and convolutional neural network (CNN) from X-ray images were fused to develop the classification model through training by CNN (VGGNet). Modified anisotropic diffusion filtering (MADF) technique was employed for better edge preservation and reduced noise from the images. A watershed segmentation algorithm was used in order to mark the significant fracture region in the input X-ray images. The testing stage considered generalized data for performance evaluation of the model. Cross-validation analysis revealed that a 5-fold strategy could successfully impair the overfitting problem. This proposed feature fusion using the deep learning technique assured a satisfactory performance in terms of identifying COVID-19 compared to the immediate, relevant works with a testing accuracy of 99.49%, specificity of 95.7% and sensitivity of 93.65%. When compared to other classification techniques, such as ANN, KNN, and SVM, the CNN technique used in this study showed better classification performance. K-fold cross-validation demonstrated that the proposed feature fusion technique (98.36%) provided higher accuracy than the individual feature extraction methods, such as HOG (87.34%) or CNN (93.64%).