Low False Positive Rate Research Articles

Zero-day exploits detection with adaptive WavePCA-Autoencoder (AWPA) adaptive hybrid exploit detection network (AHEDNet)

This paper introduces a new probabilistic composite model for the detection of zero-day exploits targeting the capabilities of existing anomaly detection systems in terms of accuracy, computational time, and adaptability. To address the issues mentioned above, the proposed framework consisted of three novel elements. The first key innovations are the introduction of “Adaptive WavePCA-Autoencoder (AWPA)” for pre-processing stage which address the denoising and dimensionality reduction, and contributes to the general dependability and accuracy of zero-day exploit detection. Additionally, a novel “Meta-Attention Transformer Autoencoder (MATA)” for enhancing feature extraction which address the subtlety issue, and improves the model’s ability and flexibility to detect new security threats, and a novel “Genetic Mongoose-Chameleon Optimization (GMCO)” was introduced for effective feature selection in the case of addressing the efficiency challenges. Furthermore, a novel “Adaptive Hybrid Exploit Detection Network (AHEDNet)” was introduced which address the dynamic ensemble adaptation issue where the accuracy of anomaly detection is very high with low false positives. The experimental results show the proposed model outperforms the other models of dataset 1 in accuracy of 0.988086 and 0.990469, precision of 0.987976 and 0.990628, recall of 0.988298 and 0.990435, with the lowest Hamming Loss of 0.011914 and 0.009531, also, the proposed model outperforms the other models of dataset 2 in accuracy of 0.9819 and 0.9919, precision of 0.9868 and 0.9968, recall of 0.9813 and 0.9923, with the lowest Hamming Loss of 0.0209 and 0.0109, thus the proposed model outperformed the other models in detecting zero-day exploits.

DSADA: Detecting Spoofing Attacks in Driver Assistance Systems Using Objects’ Spatial Shapes

Object detection algorithms suffer from a perceptual vulnerability where they cannot differentiate between counterfeit and real objects. In this paper, we investigate the perceptual vulnerability in advanced driver assistance systems (ADAS) when faced with physical and digital spoofing attacks. To address this vulnerability, we propose a method named DSADA (Detecting Spoofing Attacks in Driver Assistance) to mitigate creation and misclassification spoofing attacks against object detection algorithms utilizing the LiDAR point clouds and objects’ spatial shapes. DSADA receives the outcomes of the object detection algorithm along with the corresponding LiDAR point clouds for each scene. DSADA exploits the spatial shapes of objects obtained from the point clouds to cross-validate the outcomes of the object detection algorithm. Any discrepancy results in generating an alert to warn about the spoofing attack. We analyze defense-aware and unaware attacks against DSADA. The evaluation results show the effectiveness of the suggested method with a true positive rate of 100% and a low false positive rate of only 3.97%. The comparative evaluation validates that the suggested method identifies a broader range of spoofed objects, including projected, displayed and printed ones, while narrowing the scope of potential attacks to familiar objects in the driving context.

Comprehensive Analysis of a YOLO-based Deep Learning Model for Cotton Plant Leaf Disease Detection

Diagnosis of cotton plant diseases is essential to maintain agricultural sustainability and output. This study proposes a YOLO-based deep learning model for leaf disease detection to maximize cotton plant leaf disease detection accuracy. This method ensures a comprehensive evaluation of cotton plant health by combining various image processing techniques, improving the accuracy of disease identification. This study provides a viable path to improve crop health monitoring and management in cotton farming systems and emphasizes the importance of utilizing cutting-edge image processing techniques in agricultural activities. ROC curve performance and classification metrics were better for YOLOv5 than for VGG16 and ResNet50, as it had the highest F1 score (99.21%), recall, and precision. Consistent performance in classification tests was demonstrated by all models, which showed balanced precision, recall, and F1 scores. ResNet50 marginally outperformed VGG16 in terms of true positive rates, F1 score (98.88% vs. 98.65%), recall, and precision. More sophisticated models, such as YOLOv5 and ResNet50, showed higher efficiency and accuracy than VGG16, which makes them more appropriate for applications demanding low false positive rates and high precision. The proposed YOLO-based method improves the accuracy of disease identification, ensuring a thorough assessment of cotton plant health using image processing techniques. The results show that the proposed approach is quite successful in correctly detecting and classifying a variety of diseases that affect cotton plants.

ENHANCING ONLINE PROCTORING EFFICIENCY

The transition to online examinations has necessitated robust proctoring mechanisms to ensure integrity and fairness. Traditional online proctoring systems often rely on human invigilators or basic monitoring software, both of which are prone to inefficiencies, high operational costs, and scalability challenges. This paper proposes an AI-based proctoring system that addresses two critical challenges: detecting disruptive sounds and identifying pre-existing infractions in online examination environments. The system integrates sound classification using a convolutional neural network (CNN) and visual recognition techniques for infraction detection. Extensive testing across diverse scenarios demonstrated high detection accuracy, low false positive rates, and real-time responsiveness. The results highlight the system's potential to transform online proctoring practices, ensuring reliable examination monitoring while maintaining candidate privacy and convenience.

P-1594. Predictive models to improve antibiotic decision-making in the Emergency Department for Extended-Spectrum β-Lactamase-producing Enterobacterales infections

Abstract Background Extended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E) infections are associated with high morbidity and mortality, often due to delayed initiation of carbapenem therapy. Carbapenems must be used judiciously to prevent emergence of resistant organisms. We developed a machine learning algorithm (MLA) to identify patients at increased risk for ESBL-E infections in the emergency department (ED).Figure 1:Receiver Operating Characteristic (ROC) curve for predicting Extended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E) Receiver Operating Characteristic (ROC) curve for predicting Extended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E) infections in Emergency Department Patients using a gradient boosting machine learning model. The area under the curve (AUC) is 0.8, indicating good discrimination between patients with and without ESBL-E. Higher True Positive Rate (TPR) at a low False Positive Rate (FPR) signifies better model performance. Methods Adults (≥18) who visited an ED in the Johns Hopkins Health System between 1/2019 and 4/2024 and received Gram-negative therapies appropriate for sepsis or had documented ESBL-E infections were included. Timestamped ED vital signs, healthcare utilization, healthcare worker (HCW)-mediated patient connections, medication history, comorbidities and laboratory results populated prior to first antibiotic order were used as predictors; our primary outcome was ESBL-E infection defined by positive culture. The probability of ESBL-E infection was estimated using a gradient boosting machine learning algorithm (MLA). Because of the time-dependent nature of increasing ESBL-E infections, the MLA was derived using data from encounters prior to 7/1/2023 and evaluated in the remaining encounters using area under the operating characteristics curve (AUC) analysis.Table 1:Patient Cohort Demographics Results In total there were 129,773 patient encounters included, of which 4289 (3.3%) had a positive ESBL-E sample collected during their ED encounter. Out-of-sample predictive accuracy was high (AUC 0.80; Figure). Prior HCW-mediated connections to ESBL-positive patients and prior exposure (≤6 months) to carbapenems, cephalosporins and proton pump inhibitors were the strongest predictors of ESBL-E infection. Abnormal vital signs, increased age, and prior exposure to any antibiotic (prior 6 months) were also important factors in prediction accuracy. Conclusion An MLA using data readily available from the EHR at the time of antibiotic ordering provided good discrimination between ED patients with and without ESBL-E infection. Further refinement and implementation of MLA-driven decision-support in the EDs could drive more targeted use of broad-spectrum antibiotics and improved patient outcomes. Disclosures Jeremiah S. Hinson, MD, PhD, Beckman Coulter: Advisor/Consultant|Beckman Coulter: Grant/Research Support|Beckman Coulter: Stocks/Bonds (Private Company)

P-1589. Characterization of Blood Culture Ordering Practices at a Single Veterans Affair Medical Center

Abstract Background Blood culture (BCx) is the gold standard for definitive diagnosis of bacteremia and fungemia, but there is limited guidance for ordering practices. Unnecessary BCx increases the risk of false positives which can lead to increased length of stay, antibiotic use (AU), and additional testing. Diagnostic stewardship aims to optimize the use of diagnostic tests to improve patient management and outcomes. This study aimed to describe the current practice of BCx ordering at a single facility and identify areas for intervention. Methods This was a retrospective review of BCx ordered from 11/01/23 to 12/31/23. BCx were excluded if there was no encounter 5 days before or 2 days after BCx collection or initial BCx were drawn at another facility. Labs, vitals, BCx order date/time, ordering provider, location and results, AU and antibiotic indication were extracted from the Corporate Data Warehouse. Indications for BCx and endovascular infection risk were determined via chart review. Appropriateness of BCx was determined by an algorithm denoting low, intermediate, or high risk of bacteremia associated with an infectious disease state (Figure 1). Intermediate and high risk were deemed appropriate. Endpoints were analyzed with descriptive statistics. Results 243 BCx were evaluated and 215 were analyzed. 156/215 (73%) were ordered in the Emergency Department (ED) (Table 1). 113/215 (53%) of BCx were appropriate with the most common indications including sepsis, intra-abdominal infection, and severe community acquired pneumonia (CAP) (Table 2). The rate of appropriateness was similar across clinical departments (Figure 2). For inappropriate BCx, 41 had no suspected infection documented, and CAP, cellulitis, and cystitis were the most documented indications (Table 2). 17/215 (8%) of BCx were positive, 6/102 in low risk, and 11/113 in intermediate/high risk group. 4/6 in the low risk were identified as contaminants. Conclusion This study found ∼50% of BCx were ordered unnecessarily, and there was both low positivity rate and false positives in this group reflecting current literature. Similar BCx ordering practices were identified across services. These findings highlight the need for intervention system wide to promote strong diagnostic stewardship and appropriate BCx ordering practices. Disclosures All Authors: No reported disclosures

Classification of CT scan and X-ray dataset based on deep learning and particle swarm optimization.

In 2019, the novel coronavirus swept the world, exposing the monitoring and early warning problems of the medical system. Computer-aided diagnosis models based on deep learning have good universality and can well alleviate these problems. However, traditional image processing methods may lead to high false positive rates, which is unacceptable in disease monitoring and early warning. This paper proposes a low false positive rate disease detection method based on COVID-19 lung images and establishes a two-stage optimization model. In the first stage, the model is trained using classical gradient descent, and relevant features are extracted; in the second stage, an objective function that minimizes the false positive rate is constructed to obtain a network model with high accuracy and low false positive rate. Therefore, the proposed method has the potential to effectively classify medical images. The proposed model was verified using a public COVID-19 radiology dataset and a public COVID-19 lung CT scan dataset. The results show that the model has made significant progress, with the false positive rate reduced to 11.3% and 7.5%, and the area under the ROC curve increased to 92.8% and 97.01%.

Termination of Resuscitation Rules for In-Hospital Cardiac Arrest

There are no validated decision rules for terminating resuscitation during in-hospital cardiac arrest. Decision rules may guide termination and prevent inappropriate early termination of resuscitation. To develop and validate termination of resuscitation rules for in-hospital cardiac arrest. In this prognostic study, potential decision rules were developed using a national in-hospital cardiac arrest registry from Denmark (data from 2017 to 2022) and validated using registries from Sweden (data from 2007 to 2021) and Norway (data from 2021 to 2022). Six variables (age, initial rhythm, witnessed status, monitored status, intensive care unit location, and resuscitation duration) were considered based on their bedside availability. Prognostic metrics were computed for all possible variable combinations. CIs were obtained using bootstrapping. Rules with a false-positive rate below 1% (predicting death in patients who might otherwise survive) and a positive rate of more than 10% (proportion of all cases for whom termination is proposed) were considered appropriate. The primary outcome was 30-day mortality. The cohorts included 9863 Danish, 12 781 Swedish, and 1308 Norwegian patients. The overall median (IQR) age was 74 (66-81) years, 63% were male, and the median (IQR) resuscitation duration was 13 (5-23) minutes. Of 53 864 possible termination rules, 5 were identified as relevant for clinical use. The best performing rule included 4 variables (unwitnessed, unmonitored, initial rhythm of asystole, and resuscitation duration more than or equal to 10 minutes). The rule proposed termination in 110 per 1000 cardiac arrests (positive rate, 11%; 95% CI, 10%-11%) and predicted 30-day mortality incorrectly in 6 per 1000 cases (false-positive rate, 0.6%; 95% CI, 0.3%-0.9%). All 5 rules performed similarly across all 3 cohorts. In this prognostic study, 5 termination of resuscitation rules were developed and validated for in-hospital cardiac arrest. The best performing rule had a low false-positive rate and a reasonable positive rate in all national cohorts. These termination of resuscitation rules may aid decision-making during resuscitation.

Words to live by: Using medic impressions to identify the need for prehospital lifesaving interventions.

Prehospital emergencies require providers to rapidly identify patients' medical condition and determine treatment needs. We tested whether medics' initial, written impressions of patient condition contain information that can help identify patients who require prehospital lifesaving interventions (LSI) prior to or during transport. We analyzed free-text medic impressions of prehospital patients encountered at the scene of an accident or injury, using data from STAT MedEvac air medical transport service from 2012 to 2021. EMR records were used to identify LSIs performed for these patients in prehospital settings. Text was cleaned via natural language processing and transformed using term frequency-inverse document frequency. A gradient boosting machine learning (ML) model was used to predict individual patient need for prehospital LSI as well as seven LSI subcategories (e.g., airway interventions, blood transfusion, vasopressor medication). A total of 12,913 prehospital patients were included in our sample (mean age = 52.3 years, 63% men). We observed good ML performance in predicting overall LSI (area under the receiver operating curve = 0.793, 95% confidence interval = [0.776-0.810]; average precision = 0.670, 95% confidence interval = [0.643-0.695] vs. LSI rate of 0.282) and equivalent-or-better performance in predicting each LSI subcategory except for crystalloid fluid administration. We identified individual words within medic impressions that portended high (e.g., unresponsive, hemorrhage) or low (e.g., droop, rib) LSI rates. Calibration analysis showed that models could prioritize correct LSI identification (i.e., high sensitivity) or accurate triage (i.e., low false-positive rate). Sensitivity analyses showed that model performance was robust when removing from medic impressions words that directly labeled an LSI. ML based on free-text medic impressions can help identify patient need for prehospital LSI. We discuss future work, such as applying similar methods to 9-1-1 call requests, and potential applications, including voice-to-text translation of medic impressions.

Anomaly detection algorithms for vehicle-to-network interaction operator-level interactive control support systems based on machine learning

Abstract This study proposes a charging transaction model based on a consortium blockchain to establish a mutual trust network between operators and power supply companies. The model employs the Practical Byzantine Fault Tolerance algorithm for transaction validation and utilizes smart contracts to handle account transfers, evaluations, and queries. Through case analysis, it is confirmed that the proposed integration of the particle swarm optimization-K-means method can simultaneously achieve low false-positive rates and high detection rates. Experimental results demonstrate that the anomaly detection algorithm in this paper effectively screens out abnormal data from on-chain charging data.

Shiba: A versatile computational method for systematic identification of differential RNA splicing across platforms.

Alternative pre-mRNA splicing (AS) is a fundamental regulatory process that generates transcript diversity and cell type variation. We developed Shiba, a comprehensive method that integrates transcript assembly, splicing event identification, read counting, and differential splicing analysis across RNA-seq platforms. Shiba excels in capturing annotated and unannotated AS events with superior accuracy, sensitivity, and reproducibility. It addresses the often-overlooked issue of junction read imbalance, significantly reducing false positives to aid target prioritization and downstream analyses. Unlike other tools that require large numbers of biological replicates or resulting in low sensitivity and high false positives, Shiba's statistics framework is agnostic to sample size, as demonstrated by simulated data and its effective application to real n =1 RNA-seq datasets. To extend its utility to single-cell RNA-seq, we developed scShiba, which applies Shiba's pseudobulk approach to analyze splicing at the cluster level. scShiba successfully revealed AS regulation in developmental dopaminergic neurons and differences between excitatory and inhibitory neurons. Both Shiba and scShiba are available in Docker/Singularity containers and Snakemake pipelines, ensuring reproducibility. With their comprehensive capabilities, Shiba and scShiba enable systematic quantification of alternative splicing events across various platforms, laying a solid foundation for mechanistic exploration of the functional complexity in RNA splicing.

Non-contrast magnetic resonance imaging versus ultrasonography for hepatocellular carcinoma surveillance: A randomized, single-center trial.

This study aimed to compare ultrasonography (US) and non-contrast magnetic resonance imaging (MRI) in the surveillance of hepatic malignancy. We conducted a randomized, non-blinded, single-center trial at a single center in South Korea. Eligible individuals were aged 20-70 years with liver cirrhosis, Child-Pugh class A, and no history of liver cancer or other recent malignancy. Participants were randomized 1:1 to receive up to ten semiannual surveillance using US or non-contrast MRI with serum alpha-fetoprotein testing. The primary endpoints were the detection rates of Barcelona Clinic Liver Cancer [BCLC] stage 0 or A tumors, stage distribution at initial diagnosis, and false-positive referral rates. From June 2015 to November 2017, 416 patients were screened, and 414 were enrolled and assigned to the US (n=207) or MRI (n=207) group. In total, 23 participants in US group and 25 in MRI group were diagnosed with liver cancer by November 2022. The detection rates of BCLC stage 0 or A tumors were not different between the US and MRI groups (8% [95% confidence interval (CI), 5 - 13%] versus 12% [8 - 17%]). BCLC stage 0 tumors were more prevalent in the MRI group than in the US group (8% versus 3%). The MRI group had earlier BCLC stage (P=0.014) and lower false-positive referral rate (0.7% [95% CI, 0.4 - 1.2%] versus 3.1% [2.3 - 4.1%], P <0.001) compared to the US group. Non-contrast MRI is a better alternative to US for the surveillance of cirrhotic patients offering earlier stage at initial diagnosis and lower false-positive referral rate. ClincalTrials.gov, NCT02514434.

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.

Quantifying Metagenomic Strain Associations from Microbiomes with Anpan.

Genetic and genomic variation among microbial strains can dramatically influence their phenotypes and environmental impact, including on human health. However, inferential methods for quantifying these differences have been lacking. Strain-level metagenomic profiling data has several features that make traditional statistical methods challenging to use, including high dimensionality, extreme variation among samples, and complex phylogenetic relatedness. We present Anpan, a set of quantitative methods addressing three key challenges in microbiome strain epidemiology. First, adaptive filtering designed to interrogate microbial strain gene carriage is combined with linear models to identify strain-specific genetic elements associated with host health outcomes and other phenotypes. Second, phylogenetic generalized linear mixed models are used to characterize the association of sub-species lineages with such phenotypes. Finally, random effects models are used to identify pathways more likely to be retained or lost by outcome-associated strains. We validated our methods by simulation, showing that we achieve more accurate effect size estimation and a lower false positive rate compared to alternative methodologies. We then applied our methods to a dataset of 1,262 colorectal cancer patients, identifying functionally adaptive genes and strong phylogenetic effects associated with CRC status, sometimes complementing and sometimes extending known species-level microbiome CRC biomarkers. Anpan's methods have been implemented as a publicly available R library to support microbial community strain and genetic epidemiology in a variety of contexts, environments, and phenotypes.

A prospectively deployed deep learning-enabled automated quality assurance tool for oncological palliative spine radiation therapy.

Palliative spine radiation therapy is prone to treatment at the wrong anatomic level. We developed a fully automated deep learning-based spine-targeting quality assurance system (DL-SpiQA) for detecting treatment at the wrong anatomic level. DL-SpiQA was evaluated based on retrospective testing of spine radiation therapy treatments and prospective clinical deployment. The DL-SpiQA workflow involves auto-segmentation and labelling of all vertebral volumes on CT imaging using TotalSegmentator, an open-source deep learning algorithm based on nnU-Net, calculation of the radiation dose to each vertebra, and flagging and categorisation of potential treatments at the wrong anatomic level with automated email reports sent to involved radiation therapy personnel. We developed the DL-SpiQA tool based on retrospective clinical data from patients treated with palliative spine radiation therapy from sites included in the multicentre hospital network between Feb 12, 2014, and Nov 15, 2022. We used historic cases of patients who had a near-miss (ie, wrong-anatomic-level errors caught before the patient was treated) or had received wrong-anatomic-level treatment to test whether the tool could identify known errors successfully. We then used the tool prospectively over 15 months (April 24, 2023, to July 22, 2024) to evaluate any new spine radiation therapy treatment plan created for a patient, looking for any targeting errors, and dose and volume discrepancies. An email report was circulated with all the radiation therapy personnel; if any errors were found, these were highlighted and each error was defined. The tool was internally validated. All cases flagged by DL-SpiQA for both the retrospective and prospective studies were manually reviewed for dosimetric targeting, variant spine anatomy or spinal anomalies, and artificial intelligence (AI) segmentation errors. DL-SpiQA was further validated based on false positive and negative rates estimated from the retrospective results. DL-SpiQA was first tested retrospectively on 513 patients with segmentation of 10 106 vertebrae. The system raised flags for ten dose discrepancies, 49 normal anatomic variants, 49 cases with implants or other anomalies, and 20 segmentation errors (4% false positive rate). DL-SpiQA caught one historic treatment at the wrong anatomic level and three near-misses. DL-SpiQA was then prospectively deployed, reviewing 520 cases and identifying six documentation errors, which triggered detailed review by clinicians, and 43 additional cases, which confirmed clinical knowledge of variant anatomy. In all detected cases (ie, 49 of 520 cases in total), the appropriate personnel were alerted. A false negative rate of 0·03% is estimated based on the 4% AI segmentation error rate and the frequency of reported spine radiation therapy errors. The low false positive rate, the low false negative rate, and the high accuracy in flagging errors show that DL-SpiQA is an effective, AI-driven, automated quality assurance tool that could be used to identify anatomic spine variants and errors in targeting at the anatomic level. The tool could therefore help improve the safety of spine radiotherapy. Further external validation and tailoring is needed. None.

Enhancing VANET Security: An Unsupervised Learning Approach for Mitigating False Information Attacks in VANETs

Vehicular ad hoc networks (VANETs) enable communication among vehicles and between vehicles and infrastructure to provide safety and comfort to the users. Malicious nodes in VANETs may broadcast false information to create the impression of a fake event or road congestion. In addition, several malicious nodes may collude to collectively launch a false information attack to increase the credibility of the attack. Detection of these attacks is critical to mitigate the potential risks they bring to the safety of users. Existing techniques for detecting false information attacks in VANETs use different approaches such as machine learning, blockchain, trust scores, statistical methods, etc. These techniques rely on historical information about vehicles, artificial data used to train the technique, or coordination among vehicles. To address these limitations, we propose a false information attack detection technique for VANETs using an unsupervised anomaly detection approach. The objective of the proposed technique is to detect false information attacks based on only real-time characteristics of the network, achieving high accuracy and low processing delay. The performance evaluation results show that our proposed technique offers 30% lower data processing delay and a 17% lower false positive rate compared to existing approaches in scenarios with high proportions of malicious nodes.

Diagnostic accuracy of phosphorylated tau217 in detecting Alzheimer's disease pathology among cognitively impaired and unimpaired: A systematic review and meta-analysis.

Our review summarizes the diagnostic accuracy of plasma and cerebrospinal fluid (CSF) phosphorylated tau 217 (p-tau217) in detecting amyloid and tau pathology on positron emission tomography (PET). We systematically reviewed studies that reported the diagnostic accuracy of plasma and CSF p-tau217, searching MEDLINE/PubMed, Scopus, and Web of Science through August 2024. The accuracy of p-tau217 in predicting amyloid and tau pathology on PET was evaluated in 30 studies. Both plasma and CSF p-tau217 effectively detect amyloid and tau PET deposition. Plasma p-tau217 showed 82% sensitivity for detecting amyloid and 83% for tau, with 86% and 83% specificity, respectively. CSF p-tau217 had 79% sensitivity for amyloid and 91% for tau, with 91% and 84% specificity. p-tau217 effectively identifies Alzheimer's disease (AD) pathology. Plasma p-tau217 was comparable to CSF p-tau217 in detecting amyloid deposition on PET. Despite being less sensitive for detecting tau deposition on PET, plasma p-tau217 can be an efficient screening tool for underlying AD pathology. HIGHLIGHTS: Plasma phosphorylated tau 217 (p-tau217) serves as a viable biomarker alternative to cerebrospinal fluid p-tau217 due to the strong concordance between their results. Plasma p-tau217 accurately identifies amyloid and tau positron emission tomography (PET) positivity, exhibiting a low rate of false negatives and positives, thereby establishing it as a reliable diagnostic tool for Alzheimer's disease (AD). Plasma p-tau217 demonstrates slightly higher accuracy in predicting amyloid PET positivity compared to tau PET positivity. Plasma p-tau217 demonstrates higher predictive accuracy in detecting AD pathology among cognitively impaired individuals, compared to cognitively unimpaired individuals, suggesting its enhanced utility as a diagnostic biomarker in clinical settings.

Performance of cell free DNA as a screening tool based on the results of first trimester screening

The advent of non-invasive prenatal testing (NIPT) in the screening of fetal abnormalities has optimized prenatal care and decreased the rate of invasive diagnostic tests. In this retrospective descriptive study, we began with 1874 singleton pregnancies. After exclusion of some cases, the study cohort ended up with 1674 cases. We analyzed the performance of NIPT based on the results of first trimester screening (FTS) using serum screening combined with NT. The cases were also compared to diagnostic testing/pregnancy outcomes. Notably, in the subgroup with FTS risk < 1000, NIPT was reported to be normal in all cases with no false negative results. In the risk group of 1/300-1/1000, NIPT could detect all trisomy 21 cases with one false positive result. Moreover, in the risk group of 1/11 − 1/300, NIPT could detect all cases of trisomy 21, 13 and 18 with low false positive rate. However, the false positive rate for sex chromosomal abnormalities was high. Taken together, the current study confirms the applicability of NIPT as a tool for detection of fetal trisomies with high sensitivity and specificity. Yet, the high rate of false positive results for sex chromosome abnormalities should be considered in the interpretation of the results.

Utilizing machine learning-based QSAR model to overcome standalone consensus docking limitation in beta-lactamase inhibitors screening: a proof-of-concept study

In virtual drug screening, consensus docking is a standard in-silico approach consisting of a combined result from optimized docking experiments, a minimum of two results combination. Therefore, consensus docking is subjected to a lower success rate than the best docking method due to its mathematical nature, an unavoidable limitation. This study aims to overcome this drawback via random forest, an ensemble machine learning model. First, in vitro beta-lactamase inhibitory screening was performed using an in-house chemical library. The in vitro results were later used as a validation. Consequently, we optimized docking protocols for AutoDock Vina and DOCK6 programs. With an appropriate scoring function, we found that DOCK6 could identify up to 70% of all active molecules, double the inappropriate. Further consensus analysis reduced the success rate to 50%. Simultaneously, a false positive rate was down to 16%, which was experimentally favorable for a drug search. Finally, we trained two quantitative structure-activity relationship (QSAR) models using logistic regression as a reference model and a random forest as a test model. After combining consensus docking results, random forest-based QSAR outperformed a logistic regression by restoring the success rate to 70% and maintaining a low false positive rate of around 21%. In conclusion, this study demonstrated the benefit of using a random forest (machine learning)-based QSAR model to overcome a standard consensus docking limitation in beta-lactamase inhibitor search as a proof-of-concept.

A prospective comparison of two computer aided detection systems with different false positive rates in colonoscopy

This study evaluated the impact of differing false positive (FP) rates in two computer-aided detection (CADe) systems on the clinical effectiveness of artificial intelligence (AI)-assisted colonoscopy. The primary outcomes were adenoma detection rate (ADR) and adenomas per colonoscopy (APC). The ADR in the control, system A (3.2% FP rate), and system B (0.6% FP rate) groups were 44.3%, 43.4%, and 50.4%, respectively, with system B showing a significantly higher ADR than the control group. The APC for the control, A, and B groups were 0.75, 0.83, and 0.90, respectively, with system B also showing a higher APC than the control. The non-true lesion resection rates were 23.8%, 29.2%, and 21.3%, with system B having the lowest. The system with lower FP rates demonstrated improved ADR and APC without increasing the resection of non-neoplastic lesions. These findings suggest that higher FP rates negatively affect the clinical performance of AI-assisted colonoscopy.