False Positive Research Articles

All the sites we cannot see: Sources and mitigation of false negatives in RNA modification studies.

RNA modifications are essential for human health - too much or too little of them leads to serious illnesses ranging from neurodevelopmental disorders to cancer. Technical advances in RNA modification sequencing are beginning to uncover the RNA targets of diverse RNA-modifying enzymes that are dysregulated in disease. However, the emerging transcriptome-wide maps of modified nucleosides installed by these enzymes should be considered as first drafts. In particular, a range of technical artefacts lead to false negatives- modified sites that are overlooked owing to technique-dependent, and often sequence-context-specific, 'blind spots'. In this Review, we discuss potential sources of false negatives in sequencing-based RNA modification maps, propose mitigation strategies and suggest guidelines for transparent reporting of sensitivity to detect modified sites in profiling studies. Important considerations for recognition and avoidance of false negatives include assessment and reporting of position-specific sequencing depth, identification of protocol-dependent RNA capture biases and applying controls for false negatives as well as for false positives. Despite their limitations, emerging maps of RNA modifications reveal exciting and largely uncharted potential for post-transcriptional control of all aspects of RNA function.

Utility of the Vestibular/Ocular Motor Screening in Military Medicine: A Systematic Review.

The Vestibular/Ocular Motor Screening (VOMS) was created as a brief clinical screening tool for identifying vestibular and ocular motor symptoms and impairments post-concussion. It was found to have predictive validity in correctly identifying concussed athletes from healthy controls. In 2018, the Military Acute Concussion Evaluation 2 (MACE2) replaced the original Military Acute Concussion Evaluation (MACE); the most prominent change between the MACE and MACE2 was the addition of the VOMS. Despite its adoption into military medicine, it is not known if the addition of the VOMS to the MACE2 is acutely helpful, and if it provides additional information for diagnosis, prognosis, and/or management. The purposes of this systematic review were: (1) to determine the utility of the VOMS in correctly identifying concussed individuals, particularly as it pertains to military medicine; (2) to explore the extent to which the VOMS can inform concussion prognosis; and (3) to establish the value of the VOMS as a measure for monitoring the evolution of symptoms throughout a service member's course of care. A comprehensive search of PubMed was performed from January 1, 2014 through August 16, 2023. Articles were included if they researched concussion or a related health condition or healthy controls and administered the VOMS. Articles were excluded if they discussed health conditions other than concussion; did not administer the VOMS; or were written in languages other than English. The tools used to assess methodological quality and risk of bias varied according to study design. Articles were classified into three primary domains: diagnosis, prognosis, and/or rehabilitation/recovery over time. A total of 231 articles were retrieved and 3 were duplicates, leaving 228 articles for review. Of the 228 articles screened, 100 relevant full-text articles were assessed for eligibility. Fifty-nine articles met our inclusion and exclusion criteria while the other 41 articles were rejected. Thirty-two articles helped to inform diagnosis, 15 prognosis, and 16 rehabilitation/recovery over time. The VOMS had excellent internal consistency and moderate to good test-retest reliability; however, a false-positive rate of 21.9% was found. Most studies indicated that a positive VOMS was associated with a delayed recovery. Several studies indicated that VOMS scores improved with targeted, active interventions and/or a symptom-guided progressive return to activity. The greatest limitation was the paucity of published evidence in the military population. More research is needed on the use of the VOMS in service members.

Adaptive Ransomware Detection Using Similarity-Preserving Hashing

Crypto-ransomware is a type of ransomware that encrypts the victim’s files and demands a ransom to return the files. This type of attack has been on the rise in recent years, as it offers a lucrative business model for threat actors. Research into developing solutions for detecting and halting the spread of ransomware is vast, and it uses different approaches. Some approaches rely on analyzing system calls made via processes to detect malicious behavior, while other methods focus on the affected files by creating a file integrity monitor to detect rapid and abnormal changes in file hashes. In this paper, we present a novel approach that utilizes hashing and can accommodate large files and dynamically take into account the amount of change within each file. Mainly, our approach relies on dividing each file into partitions and then performing selective hashing on those partitions to rapidly detect encrypted partitions due to ransomware. Our new approach addresses the main weakness of a previous implementation that relies on hashing files, not file partitions. This new implementation strikes a balance between the detection time and false positives based on the partition size and the threshold of partition changes before issuing an alert.

Quantifying the degree of scientific innovation breakthrough: Considering knowledge trajectory change and impact

Scientific breakthroughs have the potential to reshape the trajectory of knowledge flow and significantly impact later research. The aim of this study is to introduce the Degree of Innovation Breakthrough (DIB) metric to more accurately quantify the extent of scientific breakthroughs. The DIB metric takes into account changes in the trajectory of knowledge flow, as well as the deep and width of impact, and it modifies the traditional assumption of equal citation contributions by assigning weighted citation counts. The effectiveness of the DIB metric is assessed using ROC curves and AUC metrics, demonstrating its ability to differentiate between high and low scientific breakthroughs with high sensitivity and minimal false positives. Based on ROC curves, this study proposes a method to calculate the threshold for high scientific breakthrough, reducing subjectivity. The effectiveness of the proposed method is demonstrated through a dataset consisting of 1108 award-winning computer science papers and 9832 matched control papers, showing that the DIB metric surpasses single-dimensional metrics. The study also performs a granular analysis of the innovation breakthrough degree of non-award-winning papers, categorizing them into four types based on originality and impact through 2D histogram visualization, and suggests tailored management strategies. Through the adoption of this refined classification strategy, the management of innovation practices can be optimized, ultimately fostering the enhancement of innovative research outcomes. The quantitative tools introduced in this paper offer guidance for researchers in the fields of science intelligence mining and science trend prediction.

Improving the Accuracy and Precision of Disease Identification When Utilizing Ehr Data for Research: the Case for Hepatocellular Carcinoma.

Objective We assessed the performance of ICD codes to identify patients with hepatocellular carcinoma (HCC) in a large academic health system and determined whether employing an algorithm using a combination of ICD codes could deliver higher accuracy and precision than single ICD codes in identifying HCC cases using electronic health record (EHR) data. Results The use of a single ICD code entry for HCC (ICD-9-CM 155.0 or ICD-10-CM C22.0) in our cohort of 1,007 established ambulatory care patients with potential HCC yielded 58% false positives (not true HCC cases) based on chart reviews. We developed an ICD code-based algorithm that prioritized positive predictive value (PPV), F-score, and accuracy to minimize false positives and negatives. The highest performing algorithm required at least 10 ICD code entries for HCC and the sum of ICD code entries for HCC to exceed the sum of ICD code entries for non-HCC malignancies. The algorithm demonstrated high performance (PPV 97.4%, F-score 0.92, accuracy 94%), which was internally validated (PPV 92.3%, F-score 0.90, accuracy 91%) using a separate sample of potential HCC cases. Our findings support the need to assess the accuracy and precision of ICD codes before using EHR data to study HCC more broadly.

Sparse attention with residual pyramidal depthwise separable convolutional based malware detection with optimization mechanism

Recent developments indicate that malware programs present a significant risk in the security and privacy of cloud systems. Existing research in malware detection encounters numerous significant challenges due to the constantly changing and advanced characteristics of malware. Malware detection systems frequently experience high rates of false positives and false negatives, where legitimate applications are incorrectly identified as malware or actual malware remains undetected, which results in operational inefficiencies. Traditional signature-based approaches struggle in recognizing new or modified malware. Additionally, sophisticated malware types, such as file less malware, ransom ware, and rootkits pose detection challenges as they integrate deeply into systems or alter their behaviour to evade detection. These challenges highlight the urgent need for ongoing advancements in this field. Existing methods of malware detection that rely on signatures have been found to be both inefficient and slow in the context of cloud environments. Also, Existing studies have focused on detecting malware by analysing input API calls. But, these models have encountered challenges such as limited accuracy and difficulties in effectively classifying malware types. In contrast, Deep Learning (DL) have shown success by analysing malware behaviour through API calls, which yields encouraging results. Additionally, the data produced by API calls necessitates more computational resources for training. To address these challenges, a new deep learning-based malware detection approach utilizes 2D grayscale images derived from API calls, along with an effective tuning strategy has been proposed. Initially, data are collected from cloud malware dataset. Then, API calls are converted into 2D gray scale images in order to construct gray scale image dataset. After getting the gray scale image, pre-processing is performed to reduce high level noise and to enhance the quality of image by weighted mean filter and anisotropic filter, which helps to improve the performance in classification. Next, these images are then passed into the feature extraction stage to extract sufficient features with an effective integrated densely connected squeeze MobileNet v2 (Ef-DeSMob2), which reduces the dimensionality issue and increase the computational complexity. Then, the collected features are passed into the classification phase to detect normal and malware classes from the samples using sparse attention with residual pyramidal depth wise separable convolutional neural networks (SA:ResPyDSC), which focus to enhance the security and reliability of the model. Finally, the hyper parameters in the classifier model like weights, bias are properly fine-tuned by utilizing hybrid white shark beluga optimization algorithm (Hy-WBeOp). The experimental findings illustrate that the proposed method attains accuracy of 98.06%, precision of 97.99%, recall of 97.05%, f1-score of 96.08% and error metrics like MSE AT 0.08, RMSE of 0.27 and MAE of 0.21, which shows that the proposed method helps to classify the malware classes accurately with less error rates. The proposed approach outperforms with the existing techniques because of its great efficiency. Overall, this approach establish a strong malware detection system classification and enhance the reliability and effectiveness of protection against malicious attacks.

Fast and Robust Noise Background Modeling and Quasiperiodic Oscillation Detection for Astronomical Time Series

Spectrum with confidence levels is a commonly used method for quasiperiodic oscillation (QPO) detection, but it is prone to yield false positives for two reasons: poor choice and/or biased modeling of the null hypothesis (or noise background). Motivated by this, we propose a new time-domain maximum-likelihood estimation method, which can quickly and accurately estimate the noise background free from background trends, spectra peaks, and even QPOs. Our method provides a wide range of candidate stochastic models (e.g., conventional first-order autoregressive, power law, generalized Gauss–Markov, Matérn, and damped random walk), some of which have not been considered previously. Some pitfalls (e.g., detrending) in previous QPO detections are also correctly processed to minimize the false detections. Along with the multitaper method and wavelet, we revisit QPO detection in the X-ray emission from the active galaxies RE J10341+396 and 1H 0707-495, and point out why the significance levels of the QPO at ∼2.6 × 10−4 Hz would be different in previous detections and reduced if the whole observation duration is considered. Our algorithm can be easily extended to other branches of astrophysics and beyond.

Distributed Denial of Service Attack Detection and Prevention Using Pipit Fox-Attentional Deep Learning in Software-Defined Networking

The Software-Defined Network (SDN) remains the innovative model that assists in satisfying the new application requirements of future networks. However, destructive attacks, particularly Distributed Denial of Service (DDoS) attacks, are aimed primarily at the SDN control panel, presenting a significant risk to network security. The traditional approaches for DDoS attack detection exhibit several limitations including interpretability challenges, overfitting problems, and false predictions. To mitigate these drawbacks, the research proposed a Pipit Flying Fox Optimized Deep Neural Network (PPF-DNN) and Intelligent Pipit Forage Optimized-Attentional Convolutional Neural Network (IPFO-ACNN) model. The channel attention is employed to enable the network to focus selectively on relevant information, improving the model’s sensitivity to subtle anomalies associated with DDoS attacks. By dynamically adjusting the attention weights across channels, the mechanism enhances the capability of the model to discriminate the normal network traffic and malicious patterns, which results in improved precision and reduced false positives. This approach harnesses the power of CNN to automatically extract hierarchical features from network data, enhancing the efficacy of the ACNN model in attack detection. IPFO and PPF algorithms integrate the unique strengths of bio-inspired algorithms, creating a synergistic approach for efficient model parameter tuning. In the case of Training Percentage (TP) 80, the accuracy, sensitivity, and specificity of the IPFO-ACNN model are evaluated as 98.87%, 99.24% and 97.91%, respectively. Similarly, the PPF-DNN model’s performance is assessed as 98.49%, 92.50% and 98.55%, which presents a promising avenue for bolstering network security infrastructure, ensuring more robust DDoS detection and mitigation capabilities in an increasingly complex cyber threat landscape.

BCIDS‐IoT: A Binary Classification Intrusion Detection Scheme for Internet of Things Communication

ABSTRACTThe integration of Internet of Things (IoT) devices into daily life has exponentially increased the amount of data. In an IoT computing environment, like Smart Homes, Internet of Medical Things, Industrial Internet of things, Internet of Vehicles, and Smart Agriculture, there is a significant volume of data being exchanged between devices, servers, and users. This gives attackers a chance to launch malicious attacks on devices and associated resources. In this article, we have addressed this issue and proposed a machine learning‐based malware detection technique for the secure communication of IoT (BCIDS‐IoT). The proposed BCIDS‐IoT employs numerous algorithms for efficient detection. The benchmark UNSW‐NB15 dataset is utilized for the analysis. BCIDS‐IoT lowers false positives, maintains high detection rates, and allows for large‐scale network traffic without compromising performance. The various models, such as logistic regression, decision trees, random forests, extra trees, K‐nearest neighbors, and artificial neural network (ANNs), are utilized in the proposed BCIDS‐IoT. Metrics like precision, recall, and F1‐score are also calculated alongside accuracy. ANN surpassed all other models with an accuracy of . Finally, the proposed BCIDS‐IoT is also compared with different closely related schemes, indicating its outperformance among all.

Postmortem interval estimation of human skeletonized remains through luminol chemiluminescence.

Postmortem interval (PMI) estimation represents a significant challenge in the forensic sciences, particularly when dealing with human skeletal remains. A screening protocol for distinguishing possible remains of forensic interest is a crucial tool for judicial purposes. In this context, luminol chemiluminescence emerges as a promising method, with low overall costs and required time. This method is primarily used as a presumptive test, based on the understanding that the intensity of the chemiluminescence reactions decreases with an increase in the postmortem interval, thus underlining its practical implications.This research aims to expand previous research on the potential of luminol chemiluminescence, evaluating its usefulness in estimating PMI. Our sample comprised 239 human clavicles, with known PMI. The luminol solution was sprayed on each powder bone sample in a dark room, observed by the naked eye and photographed. The intensity of the chemiluminescence reaction was measured using a binary and a 5-level scale.The present results reveal that this method is a suitable tool for PMI estimation as a presumptive test, reducing time and costs in criminal investigations. The findings underscore the high sensitivity of luminol chemiluminescence for detecting recent PMI but also highlight a notable incidence of false positives. Thus, our results confirm luminol chemiluminescence as a powerful tool for dating time of death, particularly for identifying forensic relevant remains. Still, the relatively low specificity indicates that it should be complemented with additional tests for further confirmation and scientific validation of the remains' forensic relevance.

A Method for Predicting the Impact of Labor Education at Institutions of Higher Education Based on a Two-Stage Clustering Algorithm

In order to develop more accurate teaching plans and methods based on students’ characteristics and needs, and improve the effectiveness of labor education, a two-stage clustering algorithm based method for predicting the effectiveness of labor education in universities is studied. A two-stage clustering algorithm-based method for predicting the effectiveness of labor education in universities has been proposed. Through in-depth analysis of labor education data in universities, principal component analysis (PCA) was used to select 16 most representative variables from the original features. Subsequently, self-organizing map (SOM) neural network was used for preliminary clustering, and the optimal number of clusters was determined to be 8. Furthermore, the K-means clustering algorithm performs fine clustering based on the initial centers provided by SOM, significantly improving the stability and accuracy of clustering. At the same time, processing the outliers in the clustering results has reduced their impact on the clustering effect. Finally, the processed data was input into an improved XGBoost prediction model, which achieved a true positive rate (TPR) of over 85% on the ROC curve when predicting the effectiveness of labor education in universities. While maintaining a low false positive rate (FPR), the model outperformed other comparison methods significantly. This achievement not only validates the effectiveness of the proposed method in feature selection, clustering optimization, and prediction model construction, but also confirms its ability to accurately predict the labor education effectiveness of students in different grades, providing strong support for higher education institutions to optimize teaching plans and improve educational outcomes.

The Role of Pentacam Random Forest Index in Detecting Subclinical Keratoconus in a Chinese Cohort.

Purpose: This study aimed to evaluate the diagnostic accuracy of a novel shape index, the Pentacam Random Forest Index (PRFI), in detecting keratoconus (KC), specifically subclinical keratoconus, in Chinese refractive surgery candidates. Methods: This prospective cohort study included 856 participants who were divided into four groups based on their tomographic outcomes: the KC group (n = 137), the very asymmetric ectasia (VAE) group (n = 73), the normal cornea group (n = 363) and the tomographically suspected KC (TSK) group (n = 283). The diagnostic performance of PRFI and other widely used indices, including the shape index BAD-D and the combined index TBI, was assessed using receiver operating characteristic (ROC) curve analysis and compared using DeLong's test. The area under the curve (AUC), best cutoff values, and Youden index for each parameter are reported. Additionally, the false-positive rates of BAD-D and PRFI were calculated and compared in "normal corneas". Results: All shape and biomechanical parameters collected in this study were found to be significantly different among the four groups (KC, VAE, TSK, and normal groups; p = 0.000). The AUC of PRFI was the highest in detecting any form of KC (including clinical KC eyes and VAE-NT eyes) in Chinese refractive surgery candidates, outperforming the widely used shape index BAD-D (0.919 vs. 0.890, p < 0.001). There was no significant difference in performance between the PRFI and the combined TBI index (0.919 vs. 0.916, p > 0.05). For detecting subclinical KC eyes (i.e., VAE-NT), the AUC of PRFI was 0.774, which was statistically comparable to TBI (0.774 vs. 0.776, p > 0.05), while outperforming BAD-D (0.774 vs. 0.684, p < 0.001). The best cutoff values of PRFI for detecting any KC and VAE-NT eyes were determined to be 0.37 and 0.27, respectively. Additionally, PRFI demonstrated a lower false-positive rate than BAD-D (13.8% vs. 43.8%, p < 0.001). Notably, the relatively high false-positive rate of BAD-D observed in this study might be attributed to the smaller horizontal corneal diameter in tomographically suspected eyes. Conclusions: The PRFI proved to be a superior shape index compared to BAD-D in detecting any form of keratoconus, including subclinical cases, in Chinese refractive surgery candidates. This finding may be attributed to the relatively small corneas commonly observed in Asians.

The associations between modifiable risk factors and constipation: a comprehensive mendelian randomization study

ObjectiveEarly identification of modifiable risk factors is crucial for the prevention of constipation. This study systematically investigated the relationship between genetically predicted modifiable risk factors and constipation.MethodsThe inverse variance weighting (IVW) method was employed as the primary analytical approach. For similar exposure indicators, the multivariate Mendelian randomization (MVMR) method was used to adjust for potential biases in univariate MR analysis. The robustness of the results was further evaluated using the MR-Egger intercept test, Cochran’s Q test, and leave-one-out analysis. Bonferroni correction was applied to reduce the false positive rate in the results.ResultsThe IVW analysis indicated a significant causal association between genetically predicted gastroesophageal reflux disease [OR (95% CI) = 1.192 (1.079–1.315), P = 0.0005], atorvastatin use [OR (95% CI) = 16.995 (3.327–86.816), P = 0.0007], and constipation. Additionally, there was a potential causal association between education level [OR (95% CI) = 0.859 (0.767–0.964), P = 0.009], major depressive disorder [OR (95% CI) = 1.206 (1.041–1.399), P = 0.013], hypothyroidism [OR (95% CI) = 2.299 (1.327–3.985), P = 0.003], and aspirin use [OR (95% CI) = 4.872 (1.174–20.221), P = 0.029] with constipation. No causal associations were found for the other included indicators. Sensitivity analysis demonstrated the absence of evidence for heterogeneity and pleiotropy in any positive results.ConclusionThis study identified several risk factors that could be targeted for the prevention of constipation, offering valuable insights for public health policies.

Towards real-time myocardial infarction diagnosis: a convergence of machine learning and ion-exchange membrane technologies leveraging miRNA signatures.

Rapid diagnosis of acute myocardial infarction (AMI) is crucial for optimal patient management. Accurate diagnosis and time of onset of an acute event can influence treatment plans, such as percutaneous coronary intervention (PCI). PCI is most beneficial within 3 hours of AMI onset. MicroRNAs (miRNAs) are promising biomarkers, with potential of early AMI diagnosis, since they are released before cell death and subsequent release of larger molecules [e.g., cardiac troponins (cTn)], and have greater sensitivity and stability in plasma versus cTn regardless of timing of AMI onset. However, miRNA-based AMI diagnosis can result in false positives due to miRNA content overlap between AMI and stable coronary artery disease (CAD). Accordingly, we explored the possibility of using a miRNA profile, rather than a single miRNA, to distinguish between CAD and AMI, as well as different stages following AMI onset. First we screened a library of 800 miRNA using plasma samples from 4 patient cohorts; no known CAD, CAD, ST-segment elevation myocardial infarction (STEMI) and STEMI followed by PCI, using Nanostring miRNA profiling technology. From this screening, based on machine learning SCAD and Lasso algorithms, we identified 9 biomarkers (miR-200b, miR-543, miR-331, miR-3605, miR-301a, miR-18a, miR-423, miR-142, and miR-132) that were differentially expressed in CAD, STEMI and STEMI-PCI and explored them to identify a miRNA profile for rapid and accurate AMI diagnosis. These 9 miRNAs were selected as the most frequently identified targets by SCAD and Lasso, as indicated in the "drum-plot" model in the machine learning approach. We used age-matched patient samples to validate selected 9 miRNA biomarkers using a multiplexed ion-exchange membrane-based miRNA sensor platform, which measures specific miRNAs, and cTn as a control, simultaneously as a point-of-care device. Findings from this study will inform timely and accurate diagnosis of AMI and its stages, which are essential for effective management and optimal patient outcomes.

The Utility of a Community-Based Knee Ultrasound in Detecting Meniscal Tears: A Retrospective Analysis in Comparison with MRI.

MRI is the gold standard for detecting meniscal tears; however, ultrasound may readily detect meniscal changes, obviating the need for MRI. We aim to (1) determine ultrasound sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy in detecting meniscal changes, and (2) describe characteristic meniscal changes in US and their prevalence. A retrospective analysis of knee ultrasound scans for the presence of medial and lateral meniscal tears was conducted. Meniscal changes were characterized into five US appearances (cleft, diminutive, cyst, displaced fragment, and extrusion) by the consensus of two musculoskeletal radiologists. Ultrasound findings were then compared to MRI results. In total, 249 patients were included. Ultrasound sensitivity, specificity, PPV, NPV, and accuracy for medial meniscal tears were 79%, 97.3%, 95.3%, 86.6%, and 90%, respectively, and for lateral meniscal tears the ultrasound sensitivity, specificity, PPV, NPV, and accuracy were 63%, 99.5%, 96%, 93%, and 93.6%, respectively. The false negative and false positive rates for medial meniscal tears were 13.4% and 4.7%, respectively, and for the lateral meniscus, the false negative and false positive rates were 6.7% and 3.8%, respectively. Meniscal clefts were the most prevalent appearance in the medial meniscus followed by extrusions. Meniscal extrusions were the most prevalent appearance in the lateral meniscus followed by clefts. Community-based US is highly accurate in the detection of meniscal tears when compared with MRI, making it a valuable diagnostic imaging tool for detecting meniscal tears in a community setting where accessibility to MRI is limited or if there are MRI contraindications.

Mitigating overuse of antinuclear antibody (ANA) testing through educational intervention: a study in internal medicine and neurology departments.

Overuse of antinuclear antibody (ANA) tests leads to increased costs, false positives, and unnecessary treatments. This study evaluated ANA overuse in internal medicine and neurology departments and assessed the impact of an educational intervention. This quality improvement educational intervention study examined ANA test overuse in five internal medicine departments and one neurology department at a university-affiliated medical center. The educational intervention included a session focusing on ANA testing appropriateness. Outcome measures comprised the ANA/new patient ratio (APR) and the percentage of positive ANA test results. Outcomes were compared between the pre- and post-intervention periods (both 6months). The intervention took place in December 2021. The APR decreased from 43% in the pre-educational intervention period to 27% in the post-intervention period in the neurology department (odds ratio [OR] 0.49, confidence interval [95% CI] 0.37-0.63, P < 0.0001) and from 2.6% to 2.2% in the internal medicine departments (OR 0.89, 95% CI 0.73-1.10, P = 0.28). The percentage of positive ANA tests increased from 43% pre-intervention to 53% in the post-intervention period (OR 1.49, 95% CI 0.90-2.46, P = 0.12) in the neurology department and from 48% to 59% (OR 1.56, 95% CI 0.99-2.44, P = 0.0543) in the internal medicine departments. A simple educational intervention reduced unnecessary ANA testing in the neurology department but not in internal medicine departments, improving patient selection and potential cost savings. The results underscore the importance of targeted education to promote evidence-based behavior among healthcare professionals. Further research with longer follow-up is needed to assess the sustainability of these improvements.

Limitations when using artificial intelligence services to analyze chest X-rays

Background: One of the first radiology areas in which artificial intelligence began to be used and is still actively used to this day is chest X-ray examination. However, when interpreting these studies using artificial intelligence, radiologists still face a number of limitations on a daily basis that must be taken into account when making a medical opinion and which developers need to pay attention to in order to further improve the algorithms to increase their efficiency. Aims: Identification of limitations in the use of currently available artificial intelligence services for chest X-ray examinations and identification of promising directions for their further development. Materials and methods: A retrospective analysis of 155 cases of disagreement between the results of conclusions of artificial intelligence services and medical opinions when analyzing chest X-ray examinations was carried out. All cases included in the study were obtained from the Unified Radiological Information Service of the Unified Medical Information and Analytical System of Moscow. Results: Among the 155 analyzed cases of disagreement, 48 (31.0%) were false positives and 78 (50.3%) were false negatives. The remaining 29 (18.7%) cases were excluded from further study because they turned out to be true positive (27) or true negative (2). Among the 48 false-positive cases, the majority (93.8%) was due to the fact that the artificial intelligence service mistook normal anatomical structures of the chest (97.8% of cases) or a catheter shadow (2.2% of cases) for pneumothorax. Among false-negative studies, the proportion of missed clinically significant pathologies was 22.0%. Almost half of these cases (44.4%) were associated with missed lung nodes. The most common clinically insignificant pathology was calcifications in the lungs (60.9%). Conclusions: On the part of AI services, there was a tendency towards overdiagnosis. All false-positive cases were associated with erroneous detection of clinically significant pathology: pneumothorax, lung nodules, and pulmonary consolidation. Among false-negative cases, the proportion of missing clinically significant pathology was small and amounted to less than one-fourth.

Effect of Fluorescence Lymph Node Mapping on Improving Diagnostic Values of CT D3 Lymph Node Staging for Right-Sided Colon Cancer

Background/Objectives: This study evaluated the impact of fluorescence lymph node mapping (FLNM) using indocyanine green (ICG) on the diagnostic accuracy of preoperative computed tomography (CT) in right-sided colon cancer. Methods: A total of 218 patients who underwent laparoscopic right hemicolectomy with D3 lymph node dissection (LND) were analyzed: 86 patients in the FLNM group and 132 in the conventional surgery group. The FLNM technique allowed for enhanced intraoperative visualization of lymph node (LN) and more precise dissection, improving the identification of metastatic LNs. The diagnostic value of preoperative CT staging was assessed in both the FLNM and control groups by calculating the apparent prevalence, true prevalence, sensitivity, specificity, positive predictive value (PPV), negative predictive value, positive likelihood ratio (PLR), negative likelihood ratio, false positive and false negative proportions, and accuracy. Results: FLNM increased the accuracy of CT staging for detecting D3 LN metastasis in advanced cancer cases, with a higher PPV, PLR, and accuracy. In the FLNM group, the false-positive rate was significantly reduced, and the specificity was higher compared to the control group. Multivariate analysis identified FLNM as an independent factor associated with improved D3 LN metastasis detection. These findings suggest that incorporating FLNM into surgical procedures enhances the diagnostic value of preoperative CT by improving the precision of LND, particularly in patients with advanced colon cancer. Conclusions: The use of FLNM for D3 LND enhances the diagnostic accuracy of cN staging in right-sided colon cancer by improving surgical precision.

Incidence of Inborn Errors of Metabolism and Endocrine Disorders Among 40965 Newborn Infants at Riyadh Second Health Cluster of the Ministry of Health Saudi Arabia.

Inborn errors of metabolism (IEM) and endocrine disorders are common genetic conditions in the Saudi population with the incidence rate often underestimated. Newborn screening (NBS) using various disease panels provides the first line in the early detection and intervention among infants with a high risk of IEM. Here we aim to assess the incidence of screening disorders and provide an overview of the NBS program at the Ministry of Health Tertiary Care King Fahad Medical City. Dried blood spots (DBS) from 40,965 newborn infants collected on the second day after birth were analyzed for 20 disorders. The total number of positive screen ("repeat") samples over 10 years was about 1% (n = 382/40,965). The true positive result rate was 15.3% (n = 46/301) with the recall rates of individual disorders ranging from 0.26% (95% CI, 0.17-0.69) to 2.6% (95% CI, 2.19-3.05). The false positive result rate was 84.7% (n = 255/301) with biotinidase activity found to be the most common cause of the second sample repeat. The overall incidence of the screened diseases was 1:891 (95% CI, 11.61-12.47). CH and CAH are the most prevalent among endocrine disorders with an incidence of 1:4097 (95% CI, 2.19-3.05), and PA and ASA among the IEM with an incidence of 1:10,241 (95% CI, 0.09-0.95). In summary, we provide updated data and our experience on the incidence of various IEM and endocrine disorders among the Saudi population, highlight the role of false positive results of biotinidase activity that can increase the recall rate and lead to overestimation of the incidence data, and recommend multicenter studies to achieve a successful national NBS program.

Investigating 10 Yr of Volcanoacoustic Activity at Tungurahua Volcano, Ecuador, Aided by Machine Learning

Abstract Here, we present the results of applying diverse data processing and machine learning tools to investigate a very large dataset obtained from single station infrasonic recordings from the last 10 yr of the most recent period of explosive activity at Tungurahua volcano, Ecuador. To increase the quality and quantity of information extracted from the large data set and enhance pattern recognition, we combined traditional techniques with more recent ones. We divided the investigation into sequential steps: detection, discrimination, cleaning, and clustering. For the detection step, we tested the classical short-term average/long-term average algorithm and an algorithm specific for explosions detection called “Volcanic INfrasound Explosions Detector Algorithm (VINEDA)” and detected 118,516 events. To clean the detected signals from potential false positives, we used supervised classification that reduced the events to 75,483, and a catalog cleaning procedure using shallow learners including support vector machines, random forests, and a single layer neural network, trained using data from a manual catalog, to a final number of 36,359 events. This led to a sixfold increase in detected explosions compared to the manual catalog. Then, we applied hierarchical clustering to a well-studied time window of activity using two independent difference metrics: dynamic time warping and waveform cross correlation and showed the insights and drawbacks from this approach. We showed that the different techniques were able to reveal repeating and striving events between selected different eruptive phases and associated them to possible changes in eruptive dynamics. Finally, to analyze the whole dataset at once we used a convolutional autoencoder network and obtained similar results to the classical clustering in a fraction of the time. We identified different families of explosions that appeared, sometimes intermittently, and revealed various potentially competing eruptive processes during the whole time period.