High False Positive Rate Research Articles

Breast MRI to Screen Women With Extremely Dense Breasts.

Women with extremely dense breasts are at a higher risk of breast cancer, and the sensitivity of mammography in this group is reduced due to the masking effect of overlapping tissue. This review examines supplemental screening methods to improve detection in this population, with a focus on MRI. Morphologic techniques offer limited benefits, digital breast tomosynthesis (DBT) shows inconsistent results, and ultrasound (US), while improving cancer detection rates (CDR), results in a higher rate of false positives. Functional imaging techniques show better performance, molecular breast imaging increases CDR but is limited in availability, and contrast-enhanced mammography is promising, with good results and as an accessible technique, but requires further validation. MRI, with sensitivity ranging from 81% to 100%, is the most supported modality. Despite strong evidence for MRI in this population, high costs, use of contrast, and longer scan times hinder widespread use. Abbreviated MRI protocols aim to overcome these barriers by reducing costs and scan duration. As personalized screening becomes a future focus, MRI remains the most effective option for women with extremely dense breasts. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 5.

Compositional data analysis enables statistical rigor in comparative glycomics

Comparative glycomics data are compositional data, where measured glycans are parts of a whole, indicated by relative abundances. Applying traditional statistical analyses to these data often results in misleading conclusions, such as spurious “decreases” of glycans when other structures increase in abundance, or high false-positive rates for differential abundance. Our work introduces a compositional data analysis framework, tailored to comparative glycomics, to account for these data dependencies. We employ center log-ratio and additive log-ratio transformations, augmented with a scale uncertainty/information model, to introduce a statistically robust and sensitive data analysis pipeline. Applied to comparative glycomics datasets, including known glycan concentrations in defined mixtures, this approach controls false-positive rates and results in reproducible biological findings. Additionally, we present specialized analysis modalities: alpha- and beta-diversity analyze glycan distributions within and between samples, while cross-class glycan correlations shed light on previously undetected interdependencies. These approaches reveal insights into glycome variations that are critical to understanding roles of glycans in health and disease.

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).

High-throughput protein binder discovery by rapid in vivo selection.

Proteins that selectively bind to a target of interest are foundational components of research pipelines 1,2 , diagnostics 3 , and therapeutics 4 . Current immunization-based 5,6 , display- based 7-14 , and computational approaches 15-17,18 for discovering binders are laborious and time- consuming - taking months or more, suffer from high false positives - necessitating extensive secondary screening, and have a high failure rate, especially for disordered proteins and other challenging target classes. Here we establish Phage-Assisted Non-Continuous Selection of Protein Binders (PANCS-binders), an in vivo selection platform that links the life cycle of M13 phage to target protein binding though customized proximity-dependent split RNA polymerase biosensors, allowing for complete and comprehensive high-throughput screening of billion-plus member protein variant libraries with high signal-to-noise. We showcase the utility of PANCS- Binders by screening multiple protein libraries each against a panel of 95 separate therapeutically relevant targets, thereby individually assessing over 10 11 protein-protein interaction pairs, completed in two days. These selections yielded large, high-quality datasets and hundreds of novel binders, which we showed can be affinity matured or directly used in mammalian cells to inhibit or degrade targets. PANCS-Binders dramatically accelerates and simplifies the binder discovery process, the democratization of which will help unlock new creative potential in proteome-targeting with engineered binder-based biotechnologies.

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.

Machine Learning Potential for Identifying and Forecasting Complex Environmental Drivers of Vibrio vulnificus Infections in the United States.

Environmental change in coastal areas can drive marine bacteria and resulting infections, such as those caused by Vibrio vulnificus, with both foodborne and nonfoodborne exposure routes and high mortality. Although ecological drivers of V. vulnificus in the environment have been well-characterized, fewer models have been able to apply this to human infection risk due to limited surveillance. The Cholera and Other Vibrio Illness Surveillance (COVIS) system database has reported V. vulnificus infections in the United States since 1988, offering a unique opportunity to both explore the forecasting capabilities machine learning could provide and to characterize complex environmental drivers of V. vulnificus infections. Machine learning models, in the form of random forest classification models, were trained and refined using the epidemiological data from 2008 to 2018, six environmental variables (sea surface temperature, salinity, chlorophyll a concentration, sea level, land surface temperature, and runoff rate) and categorical encoders to assess our predictive potential to forecast V. vulnificus infections based on environmental data. The highest-performing model, which used balanced classes, had an Area Under the Curve score of 0.984 and a sensitivity of 0.971, highlighting the potential of machine learning to anticipate areas and periods of V. vulnificus risk. A higher false positive rate was found when the model was applied to real-world imbalanced surveillance data, which is pertinent amid modeled underreporting and misdiagnosis ratios of V. vulnificus infections. Further models were also developed to explore multilevel spatial resolution, finding state-specific models can improve specificity and early warning system potential by exclusively using lagged environmental data. The machine learning approach was able to characterize nonlinear and interacting environmental associations driving V. vulnificus infections. This study accentuates the potential of machine learning and robust surveillance for forecasting environmentally associated marine infections, providing future directions for improvements, further application, and operationalization. https://doi.org/10.1289/EHP15593.

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.

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. 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. 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. 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.

Pattern Recognition in Older Adults’ Activities of Daily Living

Monitoring daily activities and behaviors is essential for improving quality of life in elderly care, where early detection of behavioral anomalies can lead to timely interventions and enhanced well-being. However, monitoring systems often struggle with scalability, high rates of false positives and negatives, and lack of interpretability in understanding anomalies within collected data. Addressing these limitations requires an adaptable, accurate solution to detect patterns and reliably identify outliers in elderly behavior data. This work aims to design a scalable monitoring system that identifies patterns and anomalies in elderly activity data while prioritizing interpretability to make well-informed decisions. The proposed system employs pattern recognition to detect and analyze outliers in behavior analysis, incorporating a service worker generated with Crontab Guru for automated data gathering and organization. Validation is conducted through statistical measures such as accumulated values, percentiles, and probability analyses to minimize false detections and ensure reliable performance. Experimental results indicate the system achieves high accuracy, with an occupancy probability across compartments and fewer outliers detected. The system demonstrates effective scalability and robust anomaly detection. By combining pattern recognition with a focus on interpretability, the proposed system provides actionable insights into elderly activity patterns and behaviors. This approach enhances the well-being of older adults, offering caregivers reliable information to support timely interventions and improve overall quality of life.

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.