True Positive Value Research Articles

Cephalosporin Allergy: Updates on Diagnostic Testing.

Cephalosporins are one of the most prescribed antibiotics worldwide and are implicated in a wide range of hypersensitivity reactions (HSR). This review summarizes recent updates in cephalosporin hypersensitivity with a focus on diagnostic testing. Reported testing strategies to evaluate different immediate and delayed cephalosporin HSR have included skin testing, in vitro testing, and diagnostic drug challenges. However, the diagnostic performance of in vivo and in vitro tests remains unclear across different hypersensitivity endotypes; adequately powered studies investigating the true positive and negative predictive value of these diagnostic modalities are needed using the reference standard of drug challenges to define cephalosporin hypersensitivity. Refinement of diagnostic testing should be guided by growth in our understanding of cephalosporin antigenic determinants. This growth will be crucial in driving further clarification of cross-reactivity between cephalosporins, and potentially delineating streamlined evaluation processes resulting in reduced unnecessary antibiotic avoidance.

Application value of indocyanine green fluorescence imaging in guiding sentinel lymph node biopsy diagnosis of gastric cancer: Meta-analysis.

Gastric cancer is a common malignant tumor of the digestive system worldwide, and its early diagnosis is crucial to improve the survival rate of patients. Indocyanine green fluorescence imaging (ICG-FI), as a new imaging technology, has shown potential application prospects in oncology surgery. The meta-analysis to study the application value of ICG-FI in the diagnosis of gastric cancer sentinel lymph node biopsy is helpful to comprehensively evaluate the clinical effect of this technology and provide more reliable guidance for clinical practice. To assess the diagnostic efficacy of optical imaging in conjunction with indocyanine green (ICG)-guided sentinel lymph node (SLN) biopsy for gastric cancer. Electronic databases such as PubMed, Embase, Medline, Web of Science, and the Cochrane Library were searched for prospective diagnostic tests of optical imaging combined with ICG-guided SLN biopsy. Stata 12.0 software was used for analysis by combining the "bivariable mixed effect model" with the "midas" command. The true positive value, false positive value, false negative value, true negative value, and other information from the included literature were extracted. A literature quality assessment map was drawn to describe the overall quality of the included literature. A forest plot was used for heterogeneity analysis, and P < 0.01 was considered to indicate statistical significance. A funnel plot was used to assess publication bias, and P < 0.1 was considered to indicate statistical significance. The summary receiver operating characteristic (SROC) curve was used to calculate the area under the curve (AUC) to determine the diagnostic accuracy. If there was interstudy heterogeneity (I 2 > 50%), meta-regression analysis and subgroup analysis were performed. Optical imaging involves two methods: Near-infrared (NIR) imaging and fluorescence imaging. A combination of optical imaging and ICG-guided SLN biopsy was useful for diagnosis. The positive likelihood ratio was 30.39 (95%CI: 0.92-1.00), the sensitivity was 0.95 (95%CI: 0.82-0.99), and the specificity was 1.00 (95%CI: 0.92-1.00). The negative likelihood ratio was 0.05 (95%CI: 0.01-0.20), the diagnostic odds ratio was 225.54 (95%CI: 88.81-572.77), and the SROC AUC was 1.00 (95%CI: The crucial values were sensitivity = 0.95 (95%CI: 0.82-0.99) and specificity = 1.00 (95%CI: 0.92-1.00). The Deeks method revealed that the "diagnostic odds ratio" funnel plot of SLN biopsy for gastric cancer was significantly asymmetrical (P = 0.01), suggesting significant publication bias. Further meta-subgroup analysis revealed that, compared with fluorescence imaging, NIR imaging had greater sensitivity (0.98 vs 0.73). Compared with optical imaging immediately after ICG injection, optical imaging after 20 minutes obtained greater sensitivity (0.98 vs 0.70). Compared with that of patients with an average SLN detection number < 4, the sensitivity of patients with a SLN detection number ≥ 4 was greater (0.96 vs 0.68). Compared with hematoxylin-eosin (HE) staining, immunohistochemical (+ HE) staining showed greater sensitivity (0.99 vs 0.84). Compared with subserous injection of ICG, submucosal injection achieved greater sensitivity (0.98 vs 0.40). Compared with 5 g/L ICG, 0.5 and 0.05 g/L ICG had greater sensitivity (0.98 vs 0.83), and cT1 stage had greater sensitivity (0.96 vs 0.72) than cT2 to cT3 clinical stage. Compared with that of patients ≤ 26, the sensitivity of patients > 26 was greater (0.96 vs 0.65). Compared with the literature published before 2010, the sensitivity of the literature published after 2010 was greater (0.97 vs 0.81), and the differences were statistically significant (all P < 0.05). For the diagnosis of stomach cancer, optical imaging in conjunction with ICG-guided SLN biopsy is a therapeutically viable approach, especially for early gastric cancer. The concentration of ICG used in the SLN biopsy of gastric cancer may be too high. Moreover, NIR imaging is better than fluorescence imaging and may obtain higher sensitivity.

BODYFAT: a new calculator to determine the risk of being overweight validated in Spanish children between 11 and 17 years of age

The assessment of body fat of children in primary care requires consideration of the dynamic changes in height, weight, lean mass, and fat mass during childhood growth. To achieve this, we aim to develop a predictive equation based on anthropometric values, with optimal diagnostic utility. This is a cross-sectional observational study, involving schoolgoers aged 11–17 years in the Vigo metropolitan area. Out of 10,747 individuals, 577 were randomly recruited. Variables: age, sex, ethnicity/country of origin, weight, height, 8 skinfolds, 3 diameters, 7 perimeters, and 85% percentile of body fat mass as the gold standard. Generalized additive regression was selected by cross-validation and compared using receiver operating characteristic curves (ROC curves). Sensitivity, specificity, positive and negative predictive values, true positive and true negative values, false positive and false negative values, accuracy, and positive and negative likelihood ratios were calculated. Two models were identified. The optimal model includes sex, weight, height, leg perimeter, and arm perimeter, with sensitivity of 0.93 (0.83–1.00), specificity of 0.91 (0.83–0.96), accuracy of 0.91 (0.84–0.96), and area under the curve (AUC) of 0.957 (0.928–0.986). The second model includes sex, age, and body mass index, with sensitivity of 0.93 (0.81–1.00), specificity of 0.90 (0.80–0.97), accuracy of 0.90 (0.82–0.96), and an AUC of 0.944 (0.903–0.984).Conclusion: Two predictive models, with the 85th percentile of fat mass as the gold standard, built with basic anthropometric measures, show very high diagnostic utility parameters. Their calculation is facilitated by a complementary online calculator.What is Known:• In routine clinical practice, mainly in primary care, BMI is used to determine overweight and obesity. This index has its weaknesses in the assessment of children.What is New:• We provide a calculator whose validated algorithm, through the determination of fat mass by impedanciometry, makes it possible to determine the risk of overweight and obesity in the community setting, through anthropometric measurements, providing a new practical, accessible and reliable model that improves the classification of overweight and obesity in children with respect to that obtained by determining BMI.

Autonomous Image-Based Corrosion Detection in Steel Structures Using Deep Learning.

Steel structures are susceptible to corrosion due to their exposure to the environment. Currently used non-destructive techniques require inspector involvement. Inaccessibility of the defective part may lead to unnoticed corrosion, allowing the corrosion to propagate and cause catastrophic structural failure over time. Autonomous corrosion detection is essential for mitigating these problems. This study investigated the effect of the type of encoder-decoder neural network and the training strategy that works the best to automate the segmentation of corroded pixels in visual images. Models using pre-trained DesnseNet121 and EfficientNetB7 backbones yielded 96.78% and 98.5% average pixel-level accuracy, respectively. Deeper EffiecientNetB7 performed the worst, with only 33% true-positive values, which was 58% less than ResNet34 and the original UNet. ResNet 34 successfully classified the corroded pixels, with 2.98% false positives, whereas the original UNet predicted 8.24% of the non-corroded pixels as corroded when tested on a specific set of images exclusive to the investigated training dataset. Deep networks were found to be better for transfer learning than full training, and a smaller dataset could be one of the reasons for performance degradation. Both fully trained conventional UNet and ResNet34 models were tested on some external images of different steel structures with different colors and types of corrosion, with the ResNet 34 backbone outperforming conventional UNet.

Fracture risk prediction in postmenopausal women from GO Study: the comparison between FRAX, Garvan, and POL-RISK algorithms.

The aim of the longitudinal, retrospective study was to compare three tools designed to assess fracture risk: FRAX, Garvan, and POL-RISK in their prediction of fracture incidence. The study group consisted of 457 postmenopausal women with a mean age of 64.21 ± 5.94years from the Gliwice Osteoporosis (GO) Study. Comprehensive data on clinical factors related to fractures were collected for all participants. Bone densitometry was performed at the proximal femur using the Prodigy device (GE, USA). Fracture risk was established using the FRAX, Garvan, and POL-RISK algorithms. Data on the incidence of osteoporotic fractures were collected over the last 10years. During the period of observation 72, osteoporotic fractures occurred in 63 subjects. For a preliminary comparison of the predictive value of analyzed diagnostic tools, the fracture risk threshold of 10% was used. For FRAX, the fracture probability exceeding 10% was observed only in 11 subjects who experienced fractures; thus, the fracture was properly predicted only in 22.9% of women. For Garvan, the respective value was 90.5%, and for POL-RISK, it was 98.4%. That gave a very low true positive value for FRAX and a very high false positive value for Garvan and POL-RISK. Based on ROC curves, new thresholds for high risk of fractures were established for each calculator separately: 6.3% for FRAX major fracture, 20.0% for Garvan any fracture, and 18.0% for POL-RISK any fracture. Such thresholds improve the diagnostic accuracy of all compared fracture prediction tools. The current study showed that different fracture risk assessment tools, although having similar clinical purposes, require different cut-off thresholds for making therapeutic decisions. Better identification of patients requiring therapy based on such an approach may help reduce the number of new fractures.

Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study

BackgroundDeep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future.MethodsA total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 × 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined.ResultsAmong the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model’s performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425.ConclusionsThe model’s accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm.Clinical revelanceDeep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.

Multicentric evaluation of sensitivity of eight commercial anti-SARS-CoV-2 antibody assays and their correlation to virus neutralization titers in seropositive subjects

Diagnosis of SARS-CoV-2 virus is mainly based on direct detection. Determination of specific antibodies has been used mostly for epidemiological reasons. However, select immunoassays showed good correlation to plaque reduction virus neutralization test (PRNT) in smaller patient cohorts, which suggests their potential as predictors of virus neutralization titer. A total of 3,699 samples from Covid-19 patients were included in the multicentric study performed in the Czech Republic. Anti-SARS-CoV-2 antibody levels were evaluated by 8 commercial antibody assays. Simultaneously, PRNT evaluations were performed with the SARS-CoV-2 B.1.258 variant. All immunoassays showed an overall high true positive diagnostic value ranging from 79.17 to 98.04%. Several commercial EIA methods showed highly positive correlation between the assay results and PRNT levels, e.g., Liaison CoV-2 TrimericS IgG DiaSorin (Spearman r = 0.8833; Architect SASRS-CoV-2 IgG Abbott (r = 0.7298); NovaLisa SARS-CoV-2 IgG NovaTec (r = 0.7103) and Anti-SARS-CoV-2 ELISA IgG Euroimmun (r = 0.7094). While this correlation was less positive for other assays, those, conversely, presented higher true positive values. For most immunoassays, the positive percent agreement of the results was ≥ 95% in sera exhibiting PRNT levels of 1:80 and higher. The assays tested have shown variable correlation to PRNT. Those possessing high positive predictive values serve well as qualitative tests, while others can be utilised as quantitative tests highly predictive of neutralization antibody levels.

Research of data mining methods for classification of imbalanced data sets

With the rapid development of information technology, which is widely used in all spheres of human life and activity, extremely large amounts of data have been accumulated today. By applying machine learning methods to this data, new practically useful knowledge can be obtained. The main goal of this paper is to study different machine learning methods for solving the classification problem and compare their efficiency and accuracy. A separate task is data pre-processing aimed at solving the problem of sample imbalance, as well as identifying the principal components that will be used to solve the classification problem. For this purpose, an information system for classifying the bankruptcy of a company with specified economic and financial characteristics was researched and developed. The study uses a dataset on the basis of which the efficiency and quality of application of several existing classification algorithms are evaluated. These classifiers are: conventional and linear Support Vector Machine, Extra Trees, Random Forest, Decision Tree, Logistic Regression, Multilayer perceptron Classifier, Gradient Boosting, Naive Bayes Classifier. For data pre-processing, we scaled the data, used the SMOTE method to get rid of the imbalance of the training sample, and performed principal component analysis and L1 regularisation. Principal component analysis allowed us to identify 15 principal components that have the greatest impact on classification accuracy and, accordingly, use them in the classification process. Analysing the results, we found that the best classifier was Random Forest with 95.9 % accuracy, and the worst was Naive Bayes with 85.1 %. To evaluate the quality of classification and select the best classifier, the Confusion matrix is used, which takes into account the number of true positive (TP) and true negative (TN) values, as well as the number of false negative (FN) and false positive (FP) classification results, and the values of such metrics as accuracy, precision, sensitivity, F1, and ROC. Accuracy is the percentage of correct answers given by the algorithm, while Recall is the number of TPs divided by the number of TPs plus the number of FNs. F1 indicates the balance between accuracy and sensitivity. Precision is the number of true positive predictions divided by the number of false positive and true negative predictions. ROC AUC is a tool for measuring performance for classification tasks at different thresholds. It shows how well a model can distinguish between classes. The conclusions present the main results of the study and indicate the main future direction of the work, namely, the study of classification results for other datasets and more efficient processing and analysis.

VGG19 Demonstrates the Highest Accuracy Rate in a Nine-Class Wound Classification Task Among Various Deep Learning Networks: A Pilot Study

Background. Current literature suggests relatively low accuracy of multi-class wound classification tasks using deep learning networks. Solutions are needed to address the increasing diagnostic burden of wounds on wound care professionals and to aid non-wound care professionals in wound management. Objective. To develop a reliable, accurate 9-class classification system to aid wound care professionals and perhaps eventually, patients and non-wound care professionals, in managing wounds. Methods. A total of 8173 training data images and 904 test data images were classified into 9 categories: operation wound, laceration, abrasion, skin defect, infected wound, necrosis, diabetic foot ulcer, chronic ulcer, and wound dehiscence. Six deep learning networks, based on VGG16, VGG19, EfficientNet-B0, EfficientNet-B5, RepVGG-A0, and RepVGG-B0, were established, trained, and tested on the same images. For each network the accuracy rate, defined as the sum of true positive and true negative values divided by the total number, was analyzed. Results. The overall accuracy varied from 74.0% to 82.4%. Of all the networks, VGG19 achieved the highest accuracy, at 82.4%. This result is comparable to those reported in previous studies. Conclusion. These findings indicate the potential for VGG19 to be the basis for a more comprehensive and detailed AI-based wound diagnostic system. Eventually, such systems also may aid patients and non-wound care professionals in diagnosing and treating wounds.

Determination of Sensitivity and Positive Predictive Value for Handheld Doppler in the Assessment of Thoracodorsal Artery Perforators and Literature Review

Abstract Background: Hand-held Doppler (HHD) is still a very useful tool in the reconstructive surgeon’s armamentarium. One hundred percent specificity in detecting perforators can be achieved with HHD when a perforator compression test is applied. The study aimed to determine the sensitivity and positive predictive value (PPV) for HHD in the assessment of thoracodorsal artery perforators, by applying the perforator compression test, using the color Doppler ultrasound (CDU) as the standard. Materials and Methods: This was a cross-sectional study. The Plastic Surgeon assessed for perforators using HHD on both lateral thoracic areas for each patient, with a re-evaluation of the same locations by a Consultant Radiologist using the CDU. The data generated were analysed using the Statistical Package for the Social Sciences (SPSS) software version 20, and results were presented in charts and tables. The sensitivity and PPV for HHD were then calculated. Results: A total of 70 patients were included, 58 males (82.9%) and 12 females (17.1%). The age range was 18–65 years, with a mean of 31.77 years ± 11.72 years. Overall, 247 perforators were identified by HHD. The true positive, false-positive, and false-negative values for HHD were 127 (51.4%), 120 (48.6%), and 20 (8.1%), respectively. The sensitivity and PPV for the HHD were calculated as 86.3% and 51.4%, respectively. Conclusion: The sensitivity of HHD was high while the PPV was much lower compared to other studies. This implies that for patients with positive HHD signals, the probability of having perforators intraoperative is low.

Adam bald eagle optimization-based Shepard CNN for classification and pixel change detection of brain tumour using post and pre-operative brain MRI images

ABSTRACT Brain tumour is a dangerous disease and it harms health. This research develops a productive model to categorize brain tumours exploiting an Adam Bald Eagle optimization-based Shepard Convolutional Neural Network (ABEO-ShCNN). Initially, the preprocessing is done in pre- and post-operative Magnetic resonance imaging (MRI). Then, U-Net++ is exploited to segment, which is tuned by the Bald Border Collie Firefly Optimization Algorithm (BBCFO). The BBCFO is the incorporation of Border Collie Optimization (BCO), the Firefly optimization Algorithm (FA) and Bald Eagle Search (BES). Thereafter, feature extraction is done and then categorization is conducted using ShCNN in which the training is conducted by ABEO. The ABEO is the integration of Adam and BES. The ABEO-ShCNN model has acquired better accuracy, Positive Predictive Value (PPV), True Negative Rate (TNR), True Positive Rate (TPR) and Negative Predictive Value (NPV) for pre-operative MRI, with values of 92.70%, 92.90%, 91.30%, 89.60% and 89.50%, respectively.

Artificial Intelligence based real-time automatic detection and classification of skin lesion in dermoscopic samples using DenseNet-169 architecture

The most common challenge faced by dermoscopy images is the automatic detection of lesion features. All the existing solutions focus on complex algorithms to provide accurate detections. In this research work, proposed Online Tigerclaw Fuzzy Region Segmentation with Deep Learning Classification model, an intellectual model is proposed that provides discrimination of features with classification even in fine-grained samples. This model works on four different stages, which include the Boosted Anisotropic Diffusion filter with Recursive Pixel Histogram Equalization (BADF-RPHE) in the preprocessing stage. The next step is the proposed Online Tigerclaw Fuzzy Region Segmentation (OTFRS) algorithm for lesion area segmentation of dermoscopic images, which can achieve 98.9% and 97.4% accuracy for benign and malignant lesions, respectively. In the proposed OTFRS, an accuracy improvement of 1.4% is achieved when compared with previous methods. Finally, the increased robustness of lesion classification is achieved using Deep Learning Classification –DenseNet 169 with 500 images. The proposed approach was evaluated with accuracy classifications of 100% and 98.86% for benign and malignant lesions, respectively, and a processing time of less than 18 sec. In the proposed DensetNet-169 classification technique, an accuracy improvement of 3% is achieved when compared with other state-of-art methods. A higher range of true positive values is obtained for the Region of Convergence (ROC) curve, which indicates that the proposed work ensures better performance in clinical diagnosis for accurate feature visualization analysis. The methodology has been validated to prove its effectiveness and throw light on the lives of affected patients so they can resume normalcy and live long. The research work was tested in real-time clinical samples, which delivered promising and encouraging results in skin cell detection procedures.

A novel sensitive DDoS attacks against statistical test in network traffic fusion

AbstractDistributed denial of service (DDoS) attacks are common attacks that limit casual users from cracking critical network resources. A method to find the DDoS attack comes to light as an essential and hot research issue. Therefore, the increment in network usage scale demands more challenges to see the DDoS attack. Non‐real‐time collection of network traffic will make sincere complications inaccuracy; DDoS attack detection, and efficiency. Lately, sketch data structures play an excellent role in high‐speed networks to suppress and combine network traffic issues. However, the sketch data structure has issues rebuilding the reverse keys that behave abnormally due to the reversible hash function. To rectify the above difficulties, we include the Chinese Remainder Theorem‐based Reverse Sketching (CRTRS). However, Reverse Sketching is not good at suppressing and combining heavy network traffic, but it can easily detect abnormal keys. According to the network traffic records setup by CRTRS, we add the Modified Cumulative Sum Quality Control Scheme (MCSQCS) that encourages DDoS attack detection. The enforcement of the proposed work with DDoS attack detection has two kind of different data sets. The result of the experiments shows that it gives more accuracy and efficiency in detecting DDoS attacks. Therefore, comparing other DDoS detecting methods with the sketch data structure has fewer computational complications. Improving the anomalous keys is the most critical challenge in this proposed work. To illustrate the accuracy rate, we experiment with a new technique called CIC‐Friday Heavy network traffic fragment. We also explain the experimental results of the MAWI heavy network fragment with the various parameter setups. To compare our proposed method with other similar existing methods, we use a sketch data structure to manage the network traffic data. It also uses the MSPCA method to detect the DDoS attack. The information‐based analysis helps to see the DDoS attack. The result analysis of True Positive Value (TPV) and False Positive Value (FPV) with MSPCA techniques has 79% and .1% accuracy. Similarly, information‐based detection has an accuracy of about 90% and 5%. Hence, the proposed method gives more accuracy for the detection of DDoS attacks.

Comparison of diagnostic performance of two ultrasound risk stratification systems for thyroid nodules: a systematic review and meta-analysis.

To assume the ideal cut-off values and diagnostic performance of two thyroid imaging reporting and data systems published by the Korean Thyroid Association/Korean Society of Thyroid Radiology (Korean TI-RADS) and the American Thyroid Association (ATA TI-RADS). Eighteen studies with 25,422 patients from PubMed, SCOPUS, Embase, Web of Science, and Cochrane Library databases up to August 2022. True and false positive and negative values with characteristics were extracted. The highest area under the receiver operating characteristic curve (AUC) was 0.893 and 0.887 for Korean and ATA TI-RADS. High suspicion was judged as the best cut-off value with the highest AUC based on optimal sensitivity and specificity. In determining the risk of malignant thyroid nodules, high suspicion in Korean and ATA TI-RADS showed sensitivity as 71.3% and 73.5%, specificity as 7.9% and 86.4%, diagnostic odds ratios as 20.0289 and 20.9076, AUC as 0.893 and 0.887. There was no significant difference when directly comparing the diagnostic accuracy of both TI-RADS. The two risk stratification systems had good diagnostic performance with high AUC and no significant differences. The ideal cut-off can depend on the medical condition or thyroid nodules, because the changes of cut-off point may reciprocally alter sensitivity and specificity.

Sensitivity of Modern Deep Learning Neural Networks to Unbalanced Datasets in Multiclass Classification Problems

One of the critical problems in multiclass classification tasks is the imbalance of the dataset. This is especially true when using contemporary pre-trained neural networks, where the last layers of the neural network are retrained. Therefore, large datasets with highly unbalanced classes are not good for models’ training since the use of such a dataset leads to overfitting and, accordingly, poor metrics on test and validation datasets. In this paper, the sensitivity to a dataset imbalance of Xception, ViT-384, ViT-224, VGG19, ResNet34, ResNet50, ResNet101, Inception_v3, DenseNet201, DenseNet161, DeIT was studied using a highly imbalanced dataset of 20,971 images sorted into 7 classes. It is shown that the best metrics were obtained when using a cropped dataset with augmentation of missing images in classes up to 15% of the initial number. So, the metrics can be increased by 2–6% compared to the metrics of the models on the initial unbalanced data set. Moreover, the metrics of the rare classes’ classification also improved significantly–the True Positive value can be increased by 0.3 or more. As a result, the best approach to train considered networks on an initially unbalanced dataset was formulated.

Pengembangan Engine Web Crawler Sebagai Pencari Jejak Serangan Cyber Stored Cross-Site Scripting

Cross-site Scripting (XSS) vulnerability has long been a concern in web application security and is included in the OWASP Top 10 list. In 2017, XSS ranked 6th, but in 2021, it rose to the 4th position in the Injection category. This vulnerability exploits poorly validated input forms. This study aims to identify web pages that are vulnerable to Stored Cross-site Scripting attacks. The research is conducted by performing a search at three levels of depth. Web scraping is used to extract data from web pages, and the source code of the web pages is compared to Stored Cross-site Scripting attack patterns using the Knuth-Morris-Pratt algorithm. The results of the study indicate that some web pages exhibit detected attack patterns and traces of attacks, while others only show attack patterns without visible traces of attacks. Based on manual analysis of 56 randomly selected data from the research, it was found that 5 web pages had true positive values, indicating the presence of attack patterns and traces of attacks. Meanwhile, 49 other web pages had true negative values, where attack patterns were detected but no traces of attacks were found. This research provides insights into web pages vulnerable to Stored Cross-site Scripting attacks. The findings can be used to enhance web application security and reduce the potential for Cross-site Scripting attacks in the future.

Comparative Diagnostic of Cervical Tuberculous Lymphadenitis: PCR is a Fast, Efficient, and Improved Diagnostic Approach.

The study included 100 clinically suspected cases of TBLN. Fine needle aspirate (FNA) samples were processed for cytology staining and cultured on LJ & BACTEC 12B media. The biochemical tests were performed to identify the isolates at the species level. Additionally, for PCR, DNA was extracted and used for the diagnosis and identification of mycobacterial species. Patients ranged from 2 to 45 years with a mean age of 24.96 ± 9.10 years. Out of 100 patients, 73% had clinical symptoms of weight loss, followed by fever (72%), anorexia (66%), and night sweats (58%). 24% of patients were found to be smear-positive after Ziehl-Neelsen (ZN) staining and statistically highly significant with PCR. On LJ medium 34% and on BACTEC radiometric 45% of samples were smearing positive. Overall, 48% of cases were PCR-positive for TBLN. When compared with culture, the sensitivity and specificity of PCR were 93.75% and 100%, respectively, which are higher than cytology. The true positive predictive value (PPV) and negative predictive value (NPV) were 83.3% and 61.5%, respectively. This study suggests that PCR is a rapid, sensitive, and specific tool for correct diagnosis of TBLN cases as compared to staining and culture which lead to the early and proper management of mycobacterial diseases.

Neural network for classification of MnS microinclusions in steels

The influence of MnS inclusions on steel properties is highly noticeable. For instance, higher severity levels of inclusions are associated with lower mechanical properties and a higher risk of failure in service. Manual inclusions classification methods are the most used in laboratories and metallurgical sector industries because of their low cost, while automatic methods have high operating costs, which makes their use more restrict. Neural network models, on the other hand, are extremely advantageous for several applications. The present study is motivated by the use of a neural network model for classifying inclusions in steels. The aim is to achieve the highest possible accuracy in classifying the MnS inclusions severities (0, 0.5, 1.0, 1.5, 2.0, 2.5, 3.0, 3.5, 4.0, and 4.5) using optical images captured from steel specimens. The results have showed that the classification of MnS severities was very sensitive to the database number of images. A 98% training accuracy was obtained by increasing the number of images from 3,156 to 4,136, mostly adding images for some severity levels. However, validation and test results were not satisfactory. As such, a severity re-categorization of the database was able to enhance the true positive values, with an error of 8%. In general, the neural network represented speed in decision making, proving to be a potential tool for classifying steel inclusions.

Internet of Things Wearable Healthcare System for Monitoring the Challenges of COVID-19 Pandemic

During the COVID-19 situation, various application-based work has to be studied and deployed to enable an IoT-based health framework. This work-based study may guide professionals in envisaging solutions to related problems and fighting against the COVID-19 type pandemic. Therefore, it identifies various technologies of IoT-based systems for monitoring pandemic situations. The mechanisms included in IoT like actuators, sensors, and the cloud-based network serves to help people from home rather than visiting the hospital occasionally. It uses optimizers to train the “noise” and “cough” target classes. Mel Frequency Cepstral Coefficients (MFCCs) were initially employed in several speech processing approaches, but as the discipline of Music Information Retrieval (MIR) advanced alongside machine learning, it was discovered that MFCCs could accurately capture timbre. Overall, the study finds different IoT applications for the medical area during the pandemic situation with detailed descriptions. In this present condition, advanced methodologies have given way to innovation in day-to-day life. The IoT-based model provides an enhancement of 98.8% with a minimum training loss of 0.15. The framework depicts the excellent working of the proposed framework, and a true positive value of around 96.6% is shown in the confusion matrix and a true negative rate of around 97% was illustrated using this model. By making it possible for the cost-effective fabrication of wearable sensors through printing on a variety of flexible polymeric substrates, the rapid advancements in solution-based nanomaterials presented a hopeful viewpoint to the field of wearable sensors. This review focuses on the most recent significant advancements in the field of wearable sensors, including novel nanomaterials, manufacturing techniques, substrates, sensor types, sensing mechanisms, and readout circuits. It concludes with difficulties in the subject's future application.

Differences between the dispatch priority assessments of emergency medical dispatchers and emergency medical services: a prospective register-based study in Finland

BackgroundResponsive and efficient emergency medical services (EMS) require accurate telephone triage. In Finland, such services are provided by Emergency Response Centre Agency (ERC Agency). In 2018, a new Finnish computer-assisted emergency dispatch system was introduced: the Emergency Response Integrated Common Authorities (ERICA). After the introduction of ERICA, the appropriateness of EMS dispatch has not been investigated yet. The study´s objective is to determine the consistency between the priority triage of the emergency medical dispatcher (EMD) and the on-scene priority assessment of the EMS, and whether the priority assessment consistency varied among the dispatch categories.MethodsThis was a prospective register-based study. All EMS dispatches registered in the Tampere University Hospital area from 1 August 2021 to 31 August 2021 were analysed. The EMD’s mission priority triaged during the emergency call was compared with the on-scene EMS’s assessment of the priority, derived from the pre-set criteria. The test performance levels were measured from the crosstabulation of true or false positive and negative values of the priority assessment. Statistical significance was analysed using the chi-square test and the Kruskal–Wallis H test, and p-values < 0.05 were considered significant.ResultsOf the 6416 EMS dispatches analysed in this study, 36% (2341) were urgent according to the EMD’s dispatch priority, and of these, only 29% (688) were urgent according to the EMS criteria. On the other hand, 64% (4075) of the dispatches were non-urgent according to the EMD’s dispatch priority, of which 97% (3949) were non-urgent according to the EMS criteria. Moreover, there were differences between the EMD and EMS priority assessments among the dispatch categories (p < 0.001). The overall efficiency was 72%, sensitivity 85%, specificity 71%, positive predictive value 29%, and negative predictive value 97%.ConclusionWhile the EMD recognised the non-urgent dispatches with high consistency with the EMS criteria, most of the EMD’s urgent dispatches were not urgent according to the same criteria. This may diminish the availability of the EMS for more urgent missions. Thus, measures are needed to ensure more accurate and therefore, more efficient use of EMS resources in the future.