The effect of educational application in nursing internship clinical training on cognitive and functional skills and students' satisfaction.

BACKGROUND: Clinical education plays an essential role in shaping the nursing identity and is one of the central elements in the education of nursing students. Today, with the advancement of novel technologies, utilizing mobile phone-based technologies in the education of medical sciences is inevitable. Therefore, this study was conducted with the aim of investigating the impact of the urology educational application on nursing students' cognitive-functional criteria and satisfaction during the internship period. METHODS: This experimental educational intervention study was conducted during nursing students' urology internship course at Shahid Beheshti School of Nursing and Midwifery in Rasht. The data collection tools included a demographic characteristics questionnaire, cognitive skills scale, functional skills scale, and satisfaction scale (Stokes, 2001). The data were analyzed using SPSS software version 16, and a significance level was set at 0.05. RESULTS: Out of 48 studied students, 28 (58.3%) were males. The mean age of the students was 20.34 (SD = 1.51) years. In the application group, the mean of students' cognitive skills after the intervention significantly increased by 2.33 units (95% CI: 1.73 to 2.9) (t(23) = 7.97, P < 0.001, d = 1.626). By controlling the scores before the intervention, the adjusted mean score of cognitive skills in the application group was 0.56 units (95% CI: -0.16 to 1.28) higher than the traditional group; however, this difference was not statistically significant (F(1, 45) = 2.42, P = 0.127, η2p = 0.051). There was no statistically significant difference between the mean score of students' functional skills in traditional and application groups (t(46) = 0.63, P = 0.532, d = 0.184). The total mean score of satisfaction with education in the application group was 83.0 (SD: 10.7). According to the values ​​of the quartiles, 75% of the students scored higher than 75.9, 50% scored higher than 83.9, and 25% scored higher than 91.1. CONCLUSION: According to the results of this study, students' scores of functional and cognitive assessment and satisfaction with the application in urology clinical training were reported as favorable. Therefore, it is recommended that mobile phone-based technologies be used in students' clinical education and internships in combination with the traditional method.

Fertility Rate and Sperm DNA Fragmentation Index following Varicocelectomy in Primary Infertile Men with Clinical Varicocele: A Prospective Longitudinal Study.

BACKGROUND: Varicocele is one of the most common treatable causes of male infertility, and its treatment may be beneficial for fertility. This study aimed to evaluate fertility rate and DNA fragmentation index (DFI) following varicocelectomy in primary infertile men with clinical varicocele. MATERIALS AND METHODS: This prospective longitudinal study was conducted on primary infertility men, in a tertiary center from December 2018 to December 2019 with one-year follow-up. Data of the semen parameters, DFI (%), and fertility rate were gathered before, as well as 4 and 12 months after undergoing varicocelectomy. For data analysis, SPSS software and analytical test were used. RESULTS: Out of 76 patients who were analyzed, 22 (29%) became fertile and 54 (71%) remained infertile. Semen parameters and DFI (%) were improved significantly following varicocelectomy (P<0.001). Smoking history, occupational heated exposure, body mass index (BMI), and infertility duration were determined as predictors associated with fertility status (P<0.05). CONCLUSION: Although varicocele repair improved the DFI, the fertility rate was achieved in less than one-third of patients; it seems that the other parameters, such as the history of smoking, occupational heated exposure, overweight, and duration of infertility should be considered as predictors of fertility status, in primary infertile men who are a candidate for varicocelectomy.

Evaluation of the frequency of metabolic syndrome and assessment of cardiometabolic index among men with erectile dysfunction: a prospective cross-sectional study.

Purpose: Recently, an association has been observed between metabolic syndrome and erectile dysfunction (ED). This study aimed to evaluate the cardiometabolic index (CMI) in patients with ED. Methods: This cross-sectional study was performed on 144 patients with ED who were referred to a urology clinic in Rasht, Iran, from 2019 to 2021. Metabolic syndrome was evaluated according to National Cholesterol Education Program Expert Panel (NCEP) and Adult Treatment Panel III (ATP III) criteria which are considered three positive criteria from five. Also, the ED severity was classified as weak, moderate, and severe based on the five-item International Index of Erectile Function (IIEF5) questionnaire. Results: The mean age of participants was 53.46 ± 10.58 years. 56.9% had abdominal obesity, 48.6% had hypertriglyceridemia, 34.7% had low HDL-C, 55.6% had hypertension and 56.9% had elevated fasting blood sugar (FBS). 43.8% had diabetes and 13.2% had cardiovascular disease. The mean CMI was 2.51 ± 1.57. The prevalence of metabolic syndrome was 50.7%. Body mass index (BMI) was significantly associated with metabolic syndrome and CMI (P = 0.001). The severity of ED had a significant relationship with high FBS in patients. CMI and components of abdominal obesity, hypertriglyceridemia, and low HDL-C had no statistically significant relationship with ED. However, the incidence of moderate and severe ED increased with increasing the number of metabolic syndrome components. Conclusion: ED is not significantly associated with metabolic syndrome and CMI, however, the severity of this disorder increases with increasing the number of components of metabolic syndrome.

ProGen2: Exploring the boundaries of protein language models.

Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial-intelligence-driven protein design. However, we lack a sufficient understanding of how very large-scale models and data play a role in effective protein model development. We introduce a suite of protein language models, named ProGen2, that are scaled up to 6.4B parameters and trained on different sequence datasets drawn from over a billion proteins from genomic, metagenomic, and immune repertoire databases. ProGen2 models show state-of-the-art performance in capturing the distribution of observed evolutionary sequences, generating novel viable sequences, and predicting protein fitness without additional fine-tuning. As large model sizes and raw numbers of protein sequences continue to become more widely accessible, our results suggest that a growing emphasis needs to be placed on the data distribution provided to a protein sequence model. Our models and code are open sourced for widespread adoption in protein engineering. A record of this paper's Transparent Peer Review process is included in the supplemental information.

Large language models generate functional protein sequences across diverse families.

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.

Facial Features Detection System To Identify Children With Autism Spectrum Disorder: Deep Learning Models.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder associated with brain development that subsequently affects the physical appearance of the face. Autistic children have different patterns of facial features, which set them distinctively apart from typically developed (TD) children. This study is aimed at helping families and psychiatrists diagnose autism using an easy technique, viz., a deep learning-based web application for detecting autism based on experimentally tested facial features using a convolutional neural network with transfer learning and a flask framework. MobileNet, Xception, and InceptionV3 were the pretrained models used for classification. The facial images were taken from a publicly available dataset on Kaggle, which consists of 3,014 facial images of a heterogeneous group of children, i.e., 1,507 autistic children and 1,507 nonautistic children. Given the accuracy of the classification results for the validation data, MobileNet reached 95% accuracy, Xception achieved 94%, and InceptionV3 attained 0.89%.

The Comparison of Resistance Index of Testicular Artery Using Color Doppler Ultrasound in Infertile Men Undergoing Varicocelectomy.

BACKGROUND: Varicocele is one of the leading causes of infertility in men. Resistance index (RI) in testis is a parameter indicating parenchymal perfusion and microvascular functions. Increased RI in the testis of patients with varicocele might be a sign of impairments in microvascularization and a significant decrease in testicular perfusion. In the present study, RI in capsular and intraparenchymal testicular arteries was evaluated in patients with varicocele who underwent varicocelectomy. METHODS: This prospective cohort study was performed in 2019-2020 in Guilan, Iran. Sixty-six patients were included. Semen analysis was also done before surgeries. Patients with at least one disorder in semen analysis entered the study. RI in testicular arteries was measured by an experienced radiologist before surgeries. Six months after varicocelectomy, all patients underwent the same semen analysis and ultrasound imaging. Data were analyzed using SPSS software. The tests for analysis included McNemar Test and Wilcoxon and p<0.005 was considered as the significance level. RESULTS: According to the results, 42 patients (63.6%) had positive changes in sperm analysis after surgeries. Sperm analysis showed a significant increase in number, concentration, morphology, and motility of sperm after surgeries (p<0.001). Further measurements of capsular and intratesticular RI in all patients also indicated a significant decrease (p<0.001). CONCLUSION: Increased RI might be associated with impaired microperfusion in testis followed by impairments in semen. Moreover, mean capsular and intratesticular RI in patients decreased after surgeries and this decrease was significantly more in patients who had improvement in their semen parameters.

Deep learning-enabled medical computer vision.

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields-including medicine-to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques-powered by deep learning-for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit-including cardiology, pathology, dermatology, ophthalmology-and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains.

For newly diagnosed breast cancer, estrogen receptor status (ERS) is a key molecular marker used for prognosis and treatment decisions. During clinical management, ERS is determined by pathologists from immunohistochemistry (IHC) staining of biopsied tissue for the targeted receptor, which highlights the presence of cellular surface antigens. This is an expensive, time-consuming process which introduces discordance in results due to variability in IHC preparation and pathologist subjectivity. In contrast, hematoxylin and eosin (H&E) staining-which highlights cellular morphology-is quick, less expensive, and less variable in preparation. Here we show that machine learning can determine molecular marker status, as assessed by hormone receptors, directly from cellular morphology. We develop a multiple instance learning-based deep neural network that determines ERS from H&E-stained whole slide images (WSI). Our algorithm-trained strictly with WSI-level annotations-is accurate on a varied, multi-country dataset of 3,474 patients, achieving an area under the curve (AUC) of 0.92 for sensitivity and specificity. Our approach has the potential to augment clinicians' capabilities in cancer prognosis and theragnosis by harnessing biological signals imperceptible to the human eye.

Machine learning for endoleak detection after endovascular aortic repair.

Diagnosis of endoleak following endovascular aortic repair (EVAR) relies on manual review of multi-slice CT angiography (CTA) by physicians which is a tedious and time-consuming process that is susceptible to error. We evaluate the use of a deep neural network for the detection of endoleak on CTA for post-EVAR patients using a novel data efficient training approach. 50 CTAs and 20 CTAs with and without endoleak respectively were identified based on gold standard interpretation by a cardiovascular subspecialty radiologist. The Endoleak Augmentor, a custom designed augmentation method, provided robust training for the machine learning (ML) model. Predicted segmentation maps underwent post-processing to determine the presence of endoleak. The model was tested against 3 blinded general radiologists and 1 blinded subspecialist using a held-out subset (10 positive endoleak CTAs, 10 control CTAs). Model accuracy, precision and recall for endoleak diagnosis were 95%, 90% and 100% relative to reference subspecialist interpretation (AUC = 0.99). Accuracy, precision and recall was 70/70/70% for generalist1, 50/50/90% for generalist2, and 90/83/100% for generalist3. The blinded subspecialist had concordant interpretations for all test cases compared with the reference. In conclusion, our ML-based approach has similar performance for endoleak diagnosis relative to subspecialists and superior performance compared with generalists.

Bridging Finite Element and Machine Learning Modeling: Stress Prediction of Arterial Walls in Atherosclerosis.

Finite element and machine learning modeling are two predictive paradigms that have rarely been bridged. In this study, we develop a parametric model to generate arterial geometries and accumulate a database of 12,172 2D finite element simulations modeling the hyperelastic behavior and resulting stress distribution. The arterial wall composition mimics vessels in atherosclerosis-a complex cardiovascular disease and one of the leading causes of death globally. We formulate the training data to predict the maximum von Mises stress, which could indicate risk of plaque rupture. Trained deep learning models are able to accurately predict the max von Mises stress within 9.86% error on a held-out test set. The deep neural networks outperform alternative prediction models and performance scales with amount of training data. Lastly, we examine the importance of contributing features on stress value and location prediction to gain intuitions on the underlying process. Moreover, deep neural networks can capture the functional mapping described by the finite element method, which has far-reaching implications for real-time and multiscale prediction tasks in biomechanics.

Right varicocele secondary to left-sided inferior vena cava with a retro-aortic left renal vein and azygos continuation.

Varicocele represents the main cause of male infertility. Right-sided varicocele is rare and can be due to renal malignancy or a venous abnormality. The most common anomaly of the inferior vena cava (IVC) is interruption of IVC with azygos continuation, which is recognized as an uncommon congenital anomaly. The prevalence of the interruption of IVC is less than 0.3% in the healthy population. We describe the case of a 26-year-old man who had right varicocele because of a right-sided IVC with a retro-aortic left renal vein and azygos continuation. The right and left IVCs received the right and left common iliac veins, respectively, and the left renal vein crossed posteriorly to the aorta and joined the right IVC. The right IVC continued cephalad as the azygos vein within the retrocrural space. Isolated right-sided varicoceles are uncommon, but practitioners should be aware of such a condition. In case of a venous anomaly, clinicians should aware of the association with other important clinical presentations.

The Efficacy and Safety of On-demand Tramadol and Paroxetine Use in Treatment of Life Long Premature Ejaculation: A Randomized Double-blind Placebo-controlled Clinical Trial.

BACKGROUND: Several medical therapies have been proposed for the treatment of premature ejaculation (PE). Paroxetine and tramadol were both reported to be effective in treatment of PE. In this study, the therapeutic effects of tramadol, paroxetine and placebo were compared in treatment of primary PE. METHODS: In this randomized, double-blind, placebo-controlled clinical trial, 150 patients were divided into 3 groups. One group was treated with tramadol 50 mg ondemand, the other group took paroxetine 20 mg on-demand and the third group was treated with placebo. Before starting treatment and after 12 weeks, patients were asked to measure their average intravaginal ejaculation latency time (IELT) and fill the PEP (Premature Ejaculation Profile) questionnaire. RESULTS: At the end of the 12th week, the mean IELT and average of PEP scores improved in all 3 groups. The increase in tramadol group was significantly higher than the paroxetine and placebo groups (p<0.0001). There were no significant differences in terms of side effects between the 3 groups. CONCLUSION: The results showed that despite an increase in mean IELT and PEP scores in all 3 groups, the rate of improvement in tramadol group was significantly more than the others. Thus, tramadol may be considered as an appropriate alternative therapeutic option for lifelong PE.

Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease.

Deep learning and computer vision algorithms can deliver highly accurate and automated interpretation of medical imaging to augment and assist clinicians. However, medical imaging presents uniquely pertinent obstacles such as a lack of accessible data or a high-cost of annotation. To address this, we developed data-efficient deep learning classifiers for prediction tasks in cardiology. Using pipeline supervised models to focus relevant structures, we achieve an accuracy of 94.4% for 15-view still-image echocardiographic view classification and 91.2% accuracy for binary left ventricular hypertrophy classification. We then develop semi-supervised generative adversarial network models that can learn from both labeled and unlabeled data in a generalizable fashion. We achieve greater than 80% accuracy in view classification with only 4% of labeled data used in solely supervised techniques and achieve 92.3% accuracy for left ventricular hypertrophy classification. In exploring trade-offs between model type, resolution, data resources, and performance, we present a comprehensive analysis and improvements of efficient deep learning solutions for medical imaging assessment especially in cardiology.

Fast and accurate view classification of echocardiograms using deep learning.

Echocardiography is essential to cardiology. However, the need for human interpretation has limited echocardiography's full potential for precision medicine. Deep learning is an emerging tool for analyzing images but has not yet been widely applied to echocardiograms, partly due to their complex multi-view format. The essential first step toward comprehensive computer-assisted echocardiographic interpretation is determining whether computers can learn to recognize these views. We trained a convolutional neural network to simultaneously classify 15 standard views (12 video, 3 still), based on labeled still images and videos from 267 transthoracic echocardiograms that captured a range of real-world clinical variation. Our model classified among 12 video views with 97.8% overall test accuracy without overfitting. Even on single low-resolution images, accuracy among 15 views was 91.7% vs. 70.2-84.0% for board-certified echocardiographers. Data visualization experiments showed that the model recognizes similarities among related views and classifies using clinically relevant image features. Our results provide a foundation for artificial intelligence-assisted echocardiographic interpretation.

Molecular mechanics of Staphylococcus aureus adhesin, CNA, and the inhibition of bacterial adhesion by stretching collagen.

Bacterial adhesion to collagen, the most abundant protein in humans, is a critical step in the initiation and persistence of numerous bacterial infections. In this study, we explore the collagen binding mechanism of the multi-modular cell wall anchored collagen adhesin (CNA) in Staphylococcus aureus and examine how applied mechanical forces can modulate adhesion ability. The common structural-functional elements and domain organization of CNA are present across over 50 genera of bacteria. Through the use of molecular dynamics models and normal mode analysis, we shed light on the CNA's structural and conformational dynamics and its interactions with collagen that lead to collagen binding. Our results suggest that the linker region, CNA165-173, acts as a hinge exhibiting bending, extensional, and torsional modes of structural flexibility and its residues are key in the interaction of the CNA-collagen complex. Steered molecular dynamics simulations were conducted with umbrella sampling. During the course of these simulations, the 'locking' latch from the CNA N2 domain was dissociated from its groove in the CNA N1 domain, implying the importance of the latch for effective ligand binding. Finally, we observed that the binding efficiency of the CNA N1-N2 domains to collagen decreases greatly with increasing tensile force application to the collagen peptides. Thus, CNA and similar adhesins might preferentially bind to sites in which collagen fibers are cleaved, such as in wounded, injured, or inflamed tissues, or in which the collagenous tissue is less mature. As alternative techniques for control of bacterial infection are in-demand due to the rise of bacterial antibiotic resistance, results from our computational studies with respect to the mechanoregulation of the collagen binding site may inspire new therapeutics and engineering solutions by mechanically preventing colonization and/or further pathogenesis.

Performance of Seasonally and Continuously Loaded Constructed Wetlands Treating Dairy Farm Wastewater.

A 2-yr study compared the performance of seasonally and continuously loaded constructed wetlands treating dairy farm wastewater. One wetland was loaded during the growing season (GS) periods only, while the other was continuously loaded. Weekly samples were analyzed for 5-d biochemical oxygen demand (BOD), total suspended solids (TSS), total Kjeldahl N (TKN), total ammoniacal N (TAN), total P (TP), and . Annual average daily mass removal rates (kg ha) were similar for both wetlands in both years; however, seasonal differences were observed. With the exception of BOD in Year 2, average daily GS areal mass removal rates were higher for the seasonal wetland. However, GS mass exports from the seasonal wetland were higher by 28 to 94%, with the exception of BOD in Year 1. Annual mass reductions (MRs; %) for nutrients were higher for the continuous wetland in both years. Annual MRs were similar for in both years and for TSS in Year 2. Annual mass exports from the seasonal wetland were higher for nutrients and by 14 to 77% in both years. Pollutant MRs generally decreased during the nongrowing season (NGS) for the continuous wetland; however, in Year 2 when lower loading rates were used, the wetland still removed 84 to 99% of the pollutant masses. The continuous wetland also performed better during periods of high flow that occurred during the GS. Although there were minimal differences in annual treatment performance, continuously loaded systems require less additional infrastructure and should require less maintenance and may, therefore, be more attractive for agricultural applications.