High False Positive Rate Research Articles

Question–Answer Methodology for Vulnerable Source Code Review via Prototype-Based Model-Agnostic Meta-Learning

In cybersecurity, identifying and addressing vulnerabilities in source code is essential for maintaining secure IT environments. Traditional static and dynamic analysis techniques, although widely used, often exhibit high false-positive rates, elevated costs, and limited interpretability. Machine Learning (ML)-based approaches aim to overcome these limitations but encounter challenges related to scalability and adaptability due to their reliance on large labeled datasets and their limited alignment with the requirements of secure development teams. These factors hinder their ability to adapt to rapidly evolving software environments. This study proposes an approach that integrates Prototype-Based Model-Agnostic Meta-Learning(Proto-MAML) with a Question-Answer (QA) framework that leverages the Bidirectional Encoder Representations from Transformers (BERT) model. By employing Few-Shot Learning (FSL), Proto-MAML identifies and mitigates vulnerabilities with minimal data requirements, aligning with the principles of the Secure Development Lifecycle (SDLC) and Development, Security, and Operations (DevSecOps). The QA framework allows developers to query vulnerabilities and receive precise, actionable insights, enhancing its applicability in dynamic environments that require frequent updates and real-time analysis. The model outputs are interpretable, promoting greater transparency in code review processes and enabling efficient resolution of emerging vulnerabilities. Proto-MAML demonstrates strong performance across multiple programming languages, achieving an average precision of 98.49%, recall of 98.54%, F1-score of 98.78%, and exact match rate of 98.78% in PHP, Java, C, and C++.

UniEmbed: A Novel Approach to Detect XSS and SQL Injection Attacks Leveraging Multiple Feature Fusion with Machine Learning Techniques

Abstract Web applications are essential in the digital age, but their security vulnerabilities expose sensitive data and organizational integrity to sophisticated attacks. Among the most prevalent and damaging vulnerabilities in web applications are cross-site scripting (XSS) and SQL injection attacks. In this paper, we introduce UniEmbed, a unified approach for detecting XSS and SQL injection attacks using machine learning classifiers. This novel approach leverages natural language processing techniques, combining features from Word2Vec, the Universal Sentence Encoder (USE), and FastText to extract meaningful data from web applications. Extensive experiments were conducted using various machine learning classifiers on three benchmark datasets to evaluate the performance of the unified detection approach, demonstrating exceptional results. Experimental results demonstrate the superior performance of the MLP classifier. For the XSS attack dataset, the MLP classifier achieved an accuracy of 0.9982 and an F1-score of 0.9983, with minimal false positives and false negatives. Similarly, the hard voting classifier yielded the same outstanding results. For SQL injection attacks, the MLP classifier maintained exceptional performance, achieving an F1-score of 0.9980 and accuracy rates exceeding 0.9980 across two datasets. The classifier effectively minimized false positives and false negatives. The ROC curves further corroborate the effectiveness of the proposed method, indicating high true positive rates and low false positive rates. Furthermore, comparative analysis showed that the UniEmbed method consistently outperformed individual feature extraction methods across all classifiers. These findings indicate that the proposed UniEmbed method, particularly when combined with the MLP classifier, is highly effective in detecting both XSS and SQL injection attacks, making it a promising approach for enhancing web application security.

Early diagnosis of lung cancer using a sensor gas analysis complex: case report

Background. Currently, low-dose computed tomography (LDCT) is the only screening test that reduces the risk of death from lung cancer. However, there are a number of disadvantages, such as lack of widespread use, high cost, high false-positive rate and the need to conduct studies only in high-risk groups, which significantly limit mass screening. exhaled breath analysis, which uses sensitive breath sensors, is a promising method to improve early diagnosis of lung cancer. Cancer Research Institute of Tomsk National Research Medical Center together with Tomsk State University and Tomsk Polytechnic Research Institute has developed a gas analysis complex capable of analyzing the gas composition of exhaled air with remote sampling from bags. during the study, data obtained by digitizing signals from gas analysis system sensors and patient metadata are recorded in a database for subsequent automated processing and analysis using a neural network. Case description. A 48-year-old female patient with a long history of smoking came to the clinic of the Cancer Research Institute for consultation with suspected pathological infiltration around the celiac trunk detected by abdominal CT. As a clinical trial of the developed gas analytical complex for cancer detection, a sample of exhaled air was taken, and the comparison of the composition of volatile organic compounds (VOCs) with that in the control group (healthy individuals) revealed abnormalities characteristic of lung cancer. the patient underwent a chest CT scan, which revealed stage IIB peripheral cancer of the lower lobe of the left lung. the original sensor gas analysis complex, which has no analogues in Russia, was used for the first time in the detection of lung cancer. the data obtained allowed us to suspect the presence of lung tumor in the patient and perform radical surgical treatment. the composition of VOCs in exhaled air was assessed on day 10 after surgery, and no significant changes in the composition of exhaled air were observed. Conclusion. Machine learning algorithms are actively used to diagnose socially significant diseases. the platforms being developed based on arrays of chemical sensors with data analysis using a neural network are promising candidates for implementation in screening activities.

In-Vehicle Network Anomaly Detection Based on a Graph Attention Network

<div>The increased connectivity of vehicles expands the attack surface of in-vehicle networks, enabling attackers to infiltrate through external interfaces and inject malicious traffic. These malicious flows often contain anomalous semantic information, potentially leading to misleading control instructions or erroneous decisions. While most semantic-based anomaly detection methods for in-vehicle networks focus on extracting semantic context, they often overlook interactions and associations between multiple semantics, resulting in a high false positive rate (FPR). To address these challenges, the Adaptive Structure Graph Attention Network Model (AS-GAT) is proposed for in-vehicle network anomaly detection. Our approach combines a semantic extractor with a continuously updated graph structure learning method based on attention weight similarity constraints. The semantic extractor identifies semantic features within messages, while the graph structure learning module adaptively updates the graph structure based on attention weights between semantics. This model effectively learns relationships between multiple semantics in in-vehicle network packets, thereby enhancing anomaly detection accuracy. A case study on a CAN-FD dataset from real vehicles demonstrates that using AS-GAT achieves an F1 score of 97.56% in anomaly detection, outperforming baseline methods by effectively identifying attack packets causing abnormal semantic time series changes, such as fuzzing, spoofing, and replay attacks. Additional experiments on two public datasets, SWaT and WADI, further validate AS-GAT’s superior anomaly detection performance compared to baseline models, highlighting the universal applicability of our approach.</div>

PAH-Finder: A Pattern Recognition Workflow for Identification of PAHs and Their Derivatives.

Polycyclic aromatic hydrocarbons (PAHs) are pervasive environmental pollutants with significant health risks due to their carcinogenic, mutagenic, and teratogenic properties. Traditional methods for PAH identification, primarily relying on gas chromatography-mass spectrometry (GC-MS), utilize spectral library searches together with other techniques, such as mass defect analysis. However, these methods are limited by incomplete spectral libraries and a high false positive rate. Here, we present PAH-Finder, a data-driven workflow that integrates machine learning with high-resolution mass spectrometry (HRMS). PAH-Finder introduces a novel approach to evaluate the fragment distribution of PAH backbones in MS spectra by normalizing fragment m/z values to a 0-100% range relative to the molecular ion peak. Seven machine learning features capture PAH fragmentation characteristics, and a random forest model trained on 98 PAH spectra and 1003 background spectra achieved an F1 score of ∼0.9 in 5-fold cross validation. Additionally, PAH-Finder leverages the presence of doubly charged fragments and molecular formula prediction to enhance the identification accuracy. In a case study, PAH-Finder identified 135 PAHs, including 7 types of previously unreported PAH formulas in particulate matter samples, demonstrating a 246% increase in annotation efficiency compared to the NIST20 library search. It also identified 32 heteroatom-doped PAHs not included in the training data set, showcasing its robustness of generalization. PAH-Finder's high accuracy in detecting a broad spectrum of PAHs facilitates efficient data processing and interpretation for nontargeted analysis, enhancing our understanding of air pollution and public health protection. PAH-Finder is freely available at Github (https://github.com/FangLabNTU/PAH-Finder).

Analysis of Autonomous Penetration Testing Through Reinforcement Learning and Recommender Systems.

Conducting penetration testing (pentesting) in cybersecurity is a crucial turning point for identifying vulnerabilities within the framework of Information Technology (IT), where real malicious offensive behavior is simulated to identify potential weaknesses and strengthen preventive controls. Given the complexity of the tests, time constraints, and the specialized level of expertise required for pentesting, analysis and exploitation tools are commonly used. Although useful, these tools often introduce uncertainty in findings, resulting in high rates of false positives. To enhance the effectiveness of these tests, Machine Learning (ML) has been integrated, showing significant potential for identifying anomalies across various security areas through detailed detection of underlying malicious patterns. However, pentesting environments are unpredictable and intricate, requiring analysts to make extensive efforts to understand, explore, and exploit them. This study considers these challenges, proposing a recommendation system based on a context-rich, vocabulary-aware transformer capable of processing questions related to the target environment and offering responses based on necessary pentest batteries evaluated by a Reinforcement Learning (RL) estimator. This RL component assesses optimal attack strategies based on previously learned data and dynamically explores additional attack vectors. The system achieved an F1 score and an Exact Match rate over 97.0%, demonstrating its accuracy and effectiveness in selecting relevant pentesting strategies.

Enhancing Smart Grid Security Using BLS Privacy Blockchain With Siamese Bi‐LSTM for Electricity Theft Detection

ABSTRACTEnergy management inside a blockchain framework developed for smart grids is primarily concerned with improving intrusion detection to protect data privacy. The emphasis is on real‐time detection of cyberattacks and preemptive forecasting of possible risks, especially in the realm of electricity theft within smart grid systems. Existing Electricity Theft Detection techniques for smart grids have obstacles such as class imbalance, which leads to poor generalization, increased complexity due to large EC data aspects, and a high false positive rate in supervised models, resulting in incorrect classification of regular customers as abnormal. To provide security in the smart grid, a novel BLS Privacy Blockchain with Siamese Bi‐LSTM is proposed. Initially, the privacy‐preserving Boneh‐Lynn‐Shacham blockchain technique is built on BLS Short signature and hash algorithms, which mitigate misclassification rates and false positives in the detection of smart grid attacks. Then, a hybrid framework employs an intrusion detection algorithm based on Siamese Bidirectional Long Short‐Term Memory to semantically distinguish between harmful and authentic behaviors, thereby improving data quality and predictive capabilities. Furthermore, a Recurrent Neural Network‐Generative Adversarial Network is presented for detecting electricity fraud, which addresses the issue of class imbalance. This uses both supervised and unsupervised loss functions to produce synthetic theft samples that closely resemble actual theft incidents. From the experiment, it is showing that the proposed models perform with high accuracy and low error rates. The proposed model from the outcomes when compared to other existing models achieves high accuracy, detection rate, recall, and low computation time.

First-generation high-affinity ST14 radiopharmaceutical: Design, synthesis, and preclinical PET imaging evaluation for pancreatic cancer detection.

The non-specificity of 18F-FDG, coupled with high false-positive rates in pancreatitis, underscores an unmet clinical need for using specific positron emission tomography (PET) radiopharmaceuticals in noninvasive pancreatic cancer detection. ST14, a trypsin-like protease and a member of the type II transmembrane serine protease family, is overexpressed in various solid malignancies, including pancreatic cancer. This study aimed to develop a 68Ga-labeled PET radiopharmaceutical targeting ST14 for pancreatic cancer detection. A precursor ST14-06 was designed, and molecular docking was employed to preliminarily predict the binding mode. ST14-06 emerged as the preferred precursor with experimental inhibition assays confirming its high affinity for ST14 (IC50=1.06±0.08nM). 68Ga-ST14-06 was successfully synthesized with high radiochemical purity (RCP, >95%) and molar activity (25-30GBq/μmol) and was stable in saline and serum. In vitro studies demonstrated specific binding of the tracer to ST14-positive AsPC-1 cells compared to the blocking group (11.45±0.12% vs. 2.48±0.34%, P<0.01). PET/CT imaging in AsPC-1 tumor-bearing mice confirmed ST14-specific uptake, which was reduced by co-administration of an excess blocking agent. Biodistribution studies revealed higher distribution in AsPC-1 tumors (0.99±0.08%ID/g) than in PANC-1 tumors (0.32±0.02%ID/g) and the blocking group (0.32±0.04%ID/g) at 1h post-injection. Immunohistochemistry results showed that ST14 was highly positive in AsPC-1 tumors, but was negative in PANC-1 tumors. These preliminary findings suggest that 68Ga-ST14-06 has potential as a first-generation PET radiopharmaceutical for ST14-specific imaging, offering a promising tool for pancreatic cancer detection.

Toward a Computable Phenotype for Determining Eligibility of Lung Cancer Screening Using Electronic Health Records

PURPOSE Lung cancer screening (LCS) has the potential to reduce mortality and detect lung cancer at its early stages, but the high false-positive rate associated with low-dose computed tomography (LDCT) for LCS acts as a barrier to its widespread adoption. This study aims to develop computable phenotype (CP) algorithms on the basis of electronic health records (EHRs) to identify individual's eligibility for LCS, thereby enhancing LCS utilization in real-world settings. MATERIALS AND METHODS The study cohort included 5,778 individuals who underwent LDCT for LCS from 2012 to 2022, as recorded in the University of Florida Health Integrated Data Repository. CP rules derived from LCS guidelines were used to identify potential candidates, incorporating both structured EHR and clinical notes analyzed via natural language processing. We then conducted manual reviews of 453 randomly selected charts to refine and validate these rules, assessing CP performance using metrics, for example, F1 score, specificity, and sensitivity. RESULTS We developed an optimal CP rule that integrates both structured and unstructured data, adhering to the US Preventive Services Task Force 2013 and 2020 guidelines. This rule focuses on age (55-80 years for 2013 and 50-80 years for 2020), smoking status (current, former, and others), and pack-years (≥30 for 2013 and ≥20 for 2020), achieving F1 scores of 0.75 and 0.84 for the respective guidelines. Including unstructured data improved the F1 score performance by up to 9.2% for 2013 and 12.9% for 2020, compared with using structured data alone. CONCLUSION Our findings underscore the critical need for improved documentation of smoking information in EHRs, demonstrate the value of artificial intelligence techniques in enhancing CP performance, and confirm the effectiveness of EHR-based CP in identifying LCS-eligible individuals. This supports its potential to aid clinical decision making and optimize patient care.

Guidelines for Diagnosis of Noise-Induced Hearing Loss and Their Specificity.

A recent paper by Moore, Lowe and Cox has proposed guidelines for diagnosing noise-induced hearing loss (NIHL). It is referred to here as the MLC guidelines. Our aim was to assess the specificity of those guidelines (i.e., freedom from false-positive outcomes) and compare with pre-existing guidelines. We applied the MLC guidelines and pre-existing guidelines to three data sets composed of adults who do not have a history of material noise exposure and therefore cannot have NIHL. National Health Service (NHS) ENT clinic. Five hundred thirty-six patients with hearing difficulty and/or tinnitus who denied material noise exposure. Two large archival population studies of hearing were also assessed, which included 3250 participants without material noise exposure. False-positive outcome from guidelines. The MLC guidelines demonstrated moderate or high false-positive rates overall, the magnitude depending on the noise exposure scenario and whether clinical or population samples were considered. For the procedure applicable to steady broadband noise exposure, the false-positive rate averaged 56% in the population samples, compared to 31% for previous guidelines. For exposure to intense impulse sounds, the MLC guidelines take a different approach and the false-positive rate was about 70% in the population samples and even higher in the clinic sample. For exposure to intense tones, the MLC guidelines take yet another approach and the false-positive rate reached 80%. The MLC guidelines demonstrate poorer specificity than previous guidelines. Medical experts should be aware of their poor specificity and consequential likelihood of false-positive diagnoses of NIHL.

Digital-Tier Strategy Improves Newborn Screening for Glutaric Aciduria Type 1.

Glutaric aciduria type 1 (GA1) is a rare inherited metabolic disease increasingly included in newborn screening (NBS) programs worldwide. Because of the broad biochemical spectrum of individuals with GA1 and the lack of reliable second-tier strategies, NBS for GA1 is still confronted with a high rate of false positives. In this study, we aim to increase the specificity of NBS for GA1 and, hence, to reduce the rate of false positives through machine learning methods. Therefore, we studied NBS profiles from 1,025,953 newborns screened between 2014 and 2023 at the Heidelberg NBS Laboratory, Germany. We identified a significant sex difference, resulting in twice as many false-positives male than female newborns. Moreover, the proposed digital-tier strategy based on logistic regression analysis, ridge regression, and support vector machine reduced the false-positive rate by over 90% compared to regular NBS while identifying all confirmed individuals with GA1 correctly. An in-depth analysis of the profiles revealed that in particular false-positive results with high associated follow-up costs could be reduced significantly. In conclusion, understanding the origin of false-positive NBS and implementing a digital-tier strategy to enhance the specificity of GA1 testing may significantly reduce the burden on newborns and their families from false-positive NBS results.

Credibility of results in emotion science: a Z-curve analysis of results in the journals Cognition & Emotion and Emotion

ABSTRACT Failed replication attempts have raised concerns over the prevalence of publication bias and false positive results in the psychological literature. Using a sample of 65,970 test statistics from Cognition & Emotion and Emotion, this article assesses the credibility of results in emotional research. All test statistics were converted to z-scores and analysed with Z-curve. A Z-curve analysis provides information about the amount of selection bias, the expected replication rate and the false positive risk. Lastly, Z-curve is used to determine an alpha level that lessens the false positive risk without unnecessary loss of power. The results show evidence of selection bias in emotional research, but trend analyses showed a decrease over time. Based on the z-curve estimates, we predict a 15% and 70% success rate in replication studies. Therefore, replication studies should increase sample sizes to avoid type-II errors. The risk of false positives with the traditional alpha level of 5% is between 5% and 33%. Lowering alpha to 1% is sufficient to reduce the false positive risk to less than 5%. In sum, our findings may alleviate concerns about high false positive rates among emotional researchers. However, selection bias and low power remain challenges to be addressed.

Diagnosing gastrointestinal infections based on cycle threshold cut-offs of PCR.

This study compared the performance of molecular vs stool culture assays for gastrointestinal infection (GII) detection, with focus on defining cycle threshold (Ct) cut-off values for positive culture results. A total of 6,000 records of patients with suspected GII between October 2022 and February 2023 and registered at Clalit HealthCare Services in Haifa, Israel, were reviewed. Stool samples were collected from all patients with suspected GII. PCR was performed with the Seegene Allplex GI-Bacteria (I) assay kit. PCR-positive samples were cultured on bacteria-specific agar media. Out of 356 PCR-positive samples, 196 (55.1%) were culture-positive. Significant differences were noted between the mean Ct of culture-positive vs culture-negative samples for Shigella spp. (P < 0.0001), E. coli O157 (P = 0.0001), and Campylobacter spp. (P = 0.004). Shigella had the lowest Ct cutoff (27.14). Negative culture results for PCR-positive samples may result from low bacterial load. At the same time, false-positive PCR results may exist. Thus, PCR result should be considered along with clinical presentation and with Ct value consideration.IMPORTANCEGII diagnostic procedures have shifted from traditional- to molecular-based assays, which may increase missdiagnosis due to the high PCR sensitivity and false positives. This study suggests to consider a Ct threshold for each pathogen in order to reduce inaccurate diagnosis. Alternatively, culture should be performed for PCR-positive samples.

Leveraging machine learning models for anemia severity detection among pregnant women following ANC: Ethiopian context

BackgroundAnemia during pregnancy is a significant public health concern, particularly in resource-limited settings. Machine learning (ML) offers promising avenues for improved anemia detection and management. This study investigates the potential of ML models in predicting anemia severity among pregnant women attending Antenatal Care (ANC) visits in Ethiopia.MethodsData from the Ethiopian Demographic Health Survey, specialized hospitals, and public hospitals were utilized. The dataset included individuals diagnosed with severe (65.12%), moderate (15.63%), mild (16.65%) anemia, and non-anemic (2.61%) cases. Feature selection employed filter methods based on mutual information, and F-score was used to assess anemia severity prediction across four classes. Six ML models (MLP-NN, XGBoost, GNB, Decision Tree, Random Forest, and KNN) were evaluated using accuracy, precision, recall, and F1-score.ResultsThe Random Forest classifier achieved the best overall performance across all categories, with an accuracy of 97%, precision of 93%, recall of 93%, and F1-score of 93%. This indicates high true positive rates and low false positive rates. While other models like XGBoost, MLP-NN, and Decision Tree showed good performance, they weren’t quite as strong as Random Forest. Classifiers like KNN and GNB had lower overall accuracy and a tendency to misclassify some cases.ConclusionsThis study demonstrates the promising potential of Random Forest in predicting anemia severity among pregnant women in Ethiopia. The findings contribute to a more holistic understanding of anemia risk factors and pave the way for improved early detection and targeted interventions.

CRP/Lymphocyte Ratio and CRP/Albumin Ratio for Prognosis of Hyperglycemia in Patients Tuberculosis with Diabetes Mellitus

The issue is complicated by the rise in Diabetes Mellitus (DM) cases, a known risk factor for pulmonary TB, with 15% of pulmonary TB patients having a history of DM. DM and chronic hyperglycemia impair immune function, leading to long-term inflammation and worsening TB prognosis. Diagnostic methods include blood culture, AFB examination, chest X-ray, and genotyping, but more accessible tests are needed. Inflammatory markers, particularly lymphocytes, play a crucial role in TB prognosis with DM. Lymphopenia indicates chronic inflammation and a shift to memory lymphocytes. CRP, an inflammatory marker, indicates chronic inflammation, and hypoalbuminemia in DM due to kidney damage further complicates TB prognosis. The ratios of CRP to lymphocytes (CLR) and CRP to albumin (CAR) are gaining attention to better illustrate TB prognosis with DM. This cross-sectional study analyzed CLR and CAR as prognostic indicators in 30 pulmonary TB patients with DM in Jambi City from May to June 2024. CRP was tested at Prodia Jambi Laboratory, while Albumin, Lymphocytes, and blood glucose levels were tested at Labkesda of Jambi Province. The results show a Comparison with each parameter based on treatment status. Both parameters show slightly higher average values in intensive (&lt; 2 months), with an average of 5.55 for CLR and 1.82 for CAR, and there is a significant difference in CLR between intensive and follow-up treatment statuses, and ROC curve shows that CLR parameters have indicated high sensitivity and low false positive rate with AUC 0,692. A significant relationship is found between CLR and blood glucose levels with a p-value of 0.024 and an r-value of 0.411, indicating a moderately strong relationship where an increase in CRP-Lymphocyte ratio corresponds to an increase in blood glucose levels than each parameter.

Critical Fluctuations as an Early Warning Signal of Sports Injuries? A Proof of Concept Using Football Monitoring Data.

There has been an increasing interest in the development and prevention of sports injuries from a complex dynamic systems perspective. From this perspective, injuries may occur following critical fluctuations in the psychophysiological state of an athlete. Our objective was to quantify these so-called Early Warning Signals (EWS) as a proof of concept to determine their explanatory performance for injuries. The sample consisted of 23 professional youth football (soccer) players. Self-reports of psychological and physiological factors as well as data from heart rate and GPS sensors were gathered on every training and match day over two competitive seasons, which resulted in an average of 339 observations per player (range = 155-430). We calculated the Dynamic Complexity (DC) index of these data, representing a metric of critical fluctuations. Next, we used this EWS to predict injuries (traumatic and overuse). Results showed a significant peak of DC in 30% of the incurred injuries, in the six data points (roughly one and a half weeks) before the injury. The warning signal exhibited a specificity of 95%, that is, correctly classifying non-injury instances. We followed up on this promising result with additional calculations to account for the naturally imbalanced data (fewer injuries than non-injuries). The relatively low F1 we obtained (0.08) suggests that the model's overall ability to discriminate between injuries and non-injuries is rather poor, due to the high false positive rate. By detecting critical fluctuations preceding one-third of the injuries, this study provided support for the complex systems theory of injuries. Furthermore, it suggests that increasing critical fluctuations may be seen as an EWS on which practitioners can intervene. Yet, the relatively high false positive rate on the entire data set, including periods without injuries, suggests critical fluctuations may also precede transitions to other (e.g., stronger) states. Future research should therefore dig deeper into the meaning of critical fluctuations in the psychophysiological states of athletes. Complex Systems Theory suggests that sports injuries may be preceded by a warning signal characterized by a short window of increased critical fluctuations. Results of the current study showed such increased critical fluctuations before 30% of the injuries. Across the entire data set, we also found a considerable number of critical fluctuations that were not followed by an injury, suggesting that the warning signal may also precede transitions to other (e.g., healthier) states. Increased critical fluctuations may be interpreted as a window of opportunity for the practitioner to launch timely and targeted interventions, and researchers should dig deeper into the meaning of such fluctuations.

Extended 72-hour patency capsule protocol improves functional patency rates in high-risk patients undergoing capsule endoscopy.

Capsule endoscopy (CE) is a pivotal diagnostic tool for gastrointestinal (GI) disorders, yet capsule retention poses a significant risk, especially in patients with known risk factors. The patency capsule (PC) helps assess the functional patency of the GI tract to mitigate this risk. However, the standard 28-hour protocol for confirming patency often results in high false-positive rates, unnecessarily excluding many patients from undergoing diagnostic CE. To investigate the use of a 72-hour extended patency protocol to improve functional patency rates in patients at risk of capsule retention. We performed a prospective, open-label study evaluating an extended 72-hour protocol for confirming functional patency with the PC. Conducted over six months, 135 patients with risk factors for capsule retention were enrolled. The primary endpoint was the capsule retention rate in patients with confirmed functional patency. Secondary endpoints included the rates of confirmed patency via self-reporting or radiology, small bowel transit times, and adverse events. Functional patency was confirmed in 48.9% (n = 66) of patients within 28 hours, with an additional 17.4% (n = 12) confirmed within 72 hours, increasing the overall patency rate to 57.8%. There was no significant difference in small bowel transit time between patients confirmed for patency at 28 hours vs those confirmed at 72 hours. Importantly, no capsule retention was observed in patients who were confirmed for patency under the extended protocol. Notably, 50% (n = 39) of patients who proceeded to CE had clinically significant findings. Extending the patency assessment protocol to 72 hours significantly improves the rate of confirmed functional patency without increasing the risk of capsule retention. This protocol is safe, effective, and cost-neutral, allowing more patients to benefit from CE. Further studies are recommended to refine the protocol and enhance its clinical utility.

Evaluation of Neonatal Screening Programs for Tyrosinemia Type 1 Worldwide.

In The Netherlands, newborn screening (NBS) for tyrosinemia type 1 (TT1) uses dried blood spot (DBS) succinylacetone (SUAC) as a biomarker. However, high false-positive (FP) rates and a false-negative (FN) case show that the Dutch TT1 NBS protocol is suboptimal. In search of optimization options, we evaluated the protocols used by other NBS programs and their performance. We distributed an online survey to NBS program representatives worldwide (N = 41). Questions focused on the organization and performance of the programs and on changes since implementation. Thirty-three representatives completed the survey. TT1 incidence ranged from 1/13,636 to 1/750,000. Most NBS samples are taken between 36 and 72 h after birth. Most used biomarkers were DBS SUAC (78.9%), DBS Tyrosine (Tyr; 5.3%), or DBS Tyr with second tier SUAC (15.8%). The pooled median cut-off for SUAC was 1.50 µmol/L (range 0.3-7.0 µmol/L). The median cut-off from programs using laboratory-developed tests was significantly higher (2.63 µmol/L) than the medians from programs using commercial kits (range 1.0-1.7 µmol/L). The pooled median cut-off for Tyr was 216 µmol/L (range 120-600 µmol/L). Overall positive predictive values were 27.3% for SUAC, 1.2% for Tyr solely, and 90.1% for Tyr + SUAC. One FN result was reported for TT1 NBS using SUAC, while three FN results were reported for TT1 NBS using Tyr. The NBS programs for TT1 vary worldwide in terms of analytical methods, biochemical markers, and cut-off values. There is room for improvement through method standardization, cut-off adaptation, and integration of new biomarkers. Further enhancement is likely to be achieved by the application of post-analytical tools.

Distributed Denial of Services: Detection and Prevention

Distributed Denial of Service is one of the most prominent and dangerous types of attacks dis- rupting critical online services, suffering finan- cial losses, and affecting organizational oper- ations. The exploitation of vulnerabilities is enough to overwhelm the targeted websites with malicious traffic, making them inaccessible to legitimate users. Such sophistication in attack patterns coupled with explosive growth in con- nected devices has challenged the traditional approaches of detection, being bare minimum signature-based or basic anomaly detection and likely to pose difficulties in coping with emerging threats, thus prone to high false positives. This paper presents a systematic review of ten works from very recent literature on ML and DL applications in DDoS detection and mit- igation. The techniques thus are supervised, unsupervised, and hybrids applied to datasets such as NSL-KDD, CICIDS2017. ML and DL techniques do appear promising for increas- ing accuracy in detection and adaptability, but then challenges persist-in scalability, efficiency or speed of computation, and quality of datasets. It would challenge the future of research: more light on real- time models, more diversified and all-inclusive datasets, and edge and federated computing towards better accelerated detection. These would significantly contribute to the ad- vancement of scalable effective solutions that counter complex DDoS threats in today’s net- work environments. Keywords Distributed Denial of Service (DDoS) Attacks, Cybersecurity, Network Traffic Anomaly De- tection, Real-Time Threat Detection, Machine Learning (ML), Deep Learning (DL), Hy- brid Detection Models, Anomaly Detection, Signature- Based Detection, Adaptive Security Models.

Enhancing Insider Threat Detection through Integrated Behavioral, Signature and Anomaly based Detection Methods

Insider threats present substantial risks to organizational security, as malicious actors exploit their authorized access to systems, networks, or data to perpetrate harmful activities. These threats encompass various forms, including data theft, sabotage, fraud, or espionage, leading to significant financial losses, reputational damage, or regulatory penalties. Traditional approaches to insider threat detection, such as anomaly-based, signature-based, and behavioral analysis methods, have inherent limitations, including high false positives, reliance on known patterns, and lack of contextual understanding. These approaches often fail to classify insider threats accurately, potentially leading to innocent insiders being mislabeled as malicious. In this project, a unified insider threat detection system is proposed, integrating anomaly-based, signature- based, and behavioral analysis methods using Support Vector Machines (SVMs). By combining these methods and leveraging the strengths of SVMs, the aim is to address the limitations of individual approaches and enhance detection accuracy. Weighted voting is employed to fuse the output of each detection method, providing a comprehensive likelihood estimate of insider threats. This integrated approach enables organizations to better identify and mitigate insider threats, safeguarding sensitive assets and maintaining a robust security posture. Keywords— Insider threat, Insider threat detection, Signature- based detection, Anomaly-based detection, Behavior analysis, False positives, Detection accuracy, Weighted Voting Mechanism.