Precision Rate Research Articles

Improving diagnostic precision in thyroid nodule segmentation from ultrasound images with a self-attention mechanism-based Swin U-Net model

BackgroundAccurate segmentation of thyroid nodules in ultrasound imaging remains a significant challenge in medical diagnostics, primarily due to edge blurring and substantial variability in nodule size. These challenges directly affect the precision of thyroid disorder diagnoses, which are crucial for metabolic and hormonal regulation.MethodsThis study proposes a novel segmentation approach utilizing a Swin U-Net architecture enhanced with a self-attention mechanism. The model integrates residual and multiscale convolutional structures in the encoder path, with long skip connections feeding into an attention module to improve edge preservation and feature extraction. The decoder path employs these refined features to achieve precise segmentation. Comparative evaluations were conducted against traditional models, including U-Net and DeepLabv3+.ResultsThe Swin U-Net model demonstrated superior performance, achieving an average Dice Similarity Coefficient (DSC) of 0.78, surpassing baseline models such as U-Net and DeepLabv3+. The incorporation of residual and multiscale convolutional structures, along with the use of long skip connections, effectively addressed issues of edge blurring and nodule size variability. These advancements resulted in significant improvements in segmentation accuracy, highlighting the model’s potential for addressing the inherent challenges of thyroid ultrasound imaging.ConclusionThe enhanced Swin U-Net architecture exhibits notable improvements in the robustness and accuracy of thyroid nodule segmentation, offering considerable potential for clinical applications in thyroid disorder diagnosis. While the study acknowledges dataset size limitations, the findings demonstrate the effectiveness of the proposed approach. This method represents a significant step toward more reliable and precise diagnostics in thyroid disease management, with potential implications for enhanced patient outcomes in clinical practice.

Validation of a New Clinical Test for Diagnosis of Trapeziometacarpal Arthritis

Abstract Purpose Symptomatic trapeziometacarpal arthrosis is primarily diagnosed on clinical grounds. The X-ray appearance correlates poorly with the presence and severity of pain; therefore, radiography is not a useful tool to define which patient is symptomatic, nor which one should be treated. There is not a specific gold standard test. The grind test is the most used clinical test; however, its level of diagnostic accuracy is not very high. The aim of this study is to describe and validate a new clinical test. Materials and Methods A prospective study was conducted to evaluate the diagnostic performance and reliability of the compression and flexion test. Results A total of 106 patients were included. Excellent interobserver agreement was found for both semiology tests (kappa = 0.82 and intraclass correlation coefficient = 0.97). The area under the curve for the compression and flexion test showed an estimate of 99.2 (95% confidence interval [CI]: 97.6–100) and for the grind test of 62 (95% CI: 51.2–71.9). The diagnostic performance of the compression and flexion test showed a sensitivity of 100% (95% CI: 92.1–99.9) and a specificity of 98.4% (95% CI: 91.2–100), in contrast to the grind test that reports a sensitivity of 22.2% (95% CI: 11.2–37.1) and a specificity of 93.4% [95% CI: 84.1–98.2]. Conclusions The diagnostic performance of the compression and flexion test is higher than that of the grind test. Furthermore, the results show an excellent interobserver correlation and diagnostic accuracy, making it a useful clinical tool for the diagnosis of trapeziometacarpal arthritis. Type of Study/Level of Evidence Diagnostic tests II.

Incremental learning based two-level multimodal data fusion model for Alzheimer disease prediction on different data modalities

ABSTRACT Alzheimer's disease (AD) is a complex neurodegenerative condition that affects millions of people worldwide, necessitating early and accurate diagnosis for optimal patient care. This study presents a novel Two-Level Multimodal Data Fusion Integrated Incremental Learner Ensemble Classifier (TMDFILE) for Alzheimer's detection. This method integrates temporal, spatial, spectral, audio, and text data modalities, utilising a gating mechanism to optimise the contribution of each modality. Incremental learning is employed to adjust evolving data patterns and, enhance long-term performance. The proposed TMDFILE was evaluated across five diverse datasets: achieving an accuracy of 94.5%, precision of 93.5%, recall of 95.1%, and F-measure of 94.1% on the ADNI dataset; an accuracy of 94.9%, with precision, recall, and F-measure values of 94.5%, 94.1%, and 94.3%, respectively, on the OASIS dataset; an accuracy of 93.5%, precision of 95.1%, and recall of 94.1% on the EEG Emotion Recognition dataset; an accuracy of 94.5%, precision of 93.5%, and recall of 95.1% on the Aberystwyth Dementia dataset, providing reliable classifications that contribute to early cognitive decline detection; and showed robust performance with an accuracy of 94.5%, precision of 93.5%, and recall of 95.1% on the BRATS dataset, relevant to brain imaging analysis for Alzheimer's detection. TMDFILE consistently outperformed traditional classifiers, including Support Vector Machines, Random Forest, and Convolutional Neural Networks, achieving an average precision of 93.5%, recall of 95.1%, F-measure of 94.1%, and accuracy of 94.5%. These findings underscore TMDFILE's effectiveness in diagnostic accuracy and reliability, establishing it as a promising tool for Alzheimer's disease detection across clinical and research applications.

An efficient sparse code shrinkage technique for ECG denoising using empirical mode decomposition

Accurate denoising of Electrocardiogram (ECG) signals is essential for reliable cardiac diagnostics, but traditional methods often struggle with high-frequency noise and artifacts, leading to potential misinterpretations. It is often impeded by interference such as power line interference (PLI) and Gaussian noise. To address this challenge, we suggest a novel ECG denoising technique that combines empirical mode decomposition (EMD) with wavelet domain sparse code shrinking. Our approach first decomposes the noisy ECG signal into Intrinsic Mode Functions (IMFs) using EMD. These IMFs are then transformed into the wavelet domain, where a sparse code shrinking function is applied to effectively reduce both Gaussian noise and PLI while preserving the integrity of the original signal. The effectiveness of the technique is assessed on the MIT-BIH database, where it shows marked improvements in Signal-to-Noise Ratio (SNR), Mean Squared Error (MSE), and Percentage Root Mean Square Difference (PRD). The suggested approach demonstrates improved SNR and reduced MSE when compared to prior approaches, which suggests that the ECG signals are clearer and more precise. This method presents a rather effective approach to enhancing ECG analysis as it is important for diagnosis and interpretation. At 10 dB SNR, the suggested technique achieves an MSE of 0.005, which is much less than the 0.076 and 0.0025 MSEs obtained by EMD wavelet adaptive thresholding and soft thresholding correspondingly. This indicates that the proposed approach effectively eliminates noise while preserving significant signal characteristics, leading to an improved and less erroneous signal reconstruction. Furthermore, the proposed method outperformed conventional techniques and demonstrated improved noise reduction and signal clarity, achieving an SNR of 19.24 and a PRD of 20.38 at 10 dB SNR.

Rapid and Ultra‐Sensitive SARS‐CoV‐2 Subgenomic RNA Detection Using Single‐Molecule With a Large Transistor‐SiMoT Bioelectronic Platform

AbstractThe replication of Coronaviridae viruses depends on the synthesis of structural proteins expressed through the discontinuous transcription of subgenomic RNAs (sgRNAs). Thus, detecting sgRNAs, which reflect active viral replication, provides valuable insights into infection status. Current diagnostic methods, such as PCR‐based assays, often involve high costs, complex equipment, and reliance on highly trained personnel. Additionally, their specificity can be compromised by technical limitations in kit design. While viral culture remains highly accurate, it is impractical for routine diagnostics. In this study, the single‐molecule‐with‐a‐large‐transistor (SiMoT) technology is presented for detecting sgRNA encoding the nucleocapsid (N) protein in clinical samples. SiMoT incorporates a stable layer of complementary DNA strands on the sensing gate electrode, facilitating rapid, sensitive, and specific sgRNA detection. Among 90 tested samples, SiMoT achieved a diagnostic sensitivity of 98.0% and a specificity of 87.8%, delivering results within 30 min. This user‐friendly platform requires minimal sample preparation and offers a cost‐effective point‐of‐care (POC) diagnostic solution. With its demonstrated diagnostic accuracy and scalability, SiMoT represents a promising tool for detecting active viral replication in SARS‐CoV‐2 and other coronaviruses. It addresses the limitations of existing molecular and culture‐based methods while enhancing accessibility to reliable diagnostics.

Accuracy and precision of in vitro EOS imaging compared to digital radiographs in the measurement of intramedullary lengthening.

Accurate limb length measurement is essential during limb lengthening procedures to prevent neurologic and musculoskeletal complications. Magnetic intramedullary lengthening nails (MILN) rely on radiographs for measurement, but the optimal radiographic technique is not established. This study evaluated the precision and accuracy of EOS imaging versus digital radiography, including calibration techniques and measurement techniques for assessing intramedullary lengthening. An MILN was inserted into a Sawbones femur, and lengthening measurements from digital X-ray and EOS imaging were compared to external remote control (ERC) results. Measurements were taken with and without calibration using a magnification ball, nail width, or female nail length. Four observers measured the distraction gap, spindle length, full nail length, and male nail length at various hip flexion angles. Precision and accuracy were calculated for each technique. From 576 measurements, EOS imaging demonstrated significantly higher accuracy than digital radiography (83.6% vs. 73.5% absolute accuracy; p < 0.001) when non-calibrated values were included. EOS maintained superior accuracy at 30mm, 50mm, and 70mm of lengthening (p < 0.05), with no difference at 10mm. Calibration did not affect EOS accuracy, whereas digital radiography was less accurate without calibration (p < 0.001). Distraction gap measurement was the most accurate for both modalities, and 0° hip flexion provided the highest precision. Overall, EOS was more precise (79.4% vs. 71.7% precision rates; p < 0.001). EOS imaging is recommended for limb lengthening measurements due to its superior precision and accuracy. For digital radiographs, careful calibration is essential to achieve accurate measurements.

Cloud computing environment based hierarchical anomaly intrusion detection system using artificial neural network

Nowadays, computer technology is essential to everyday life, including banking, education, entertainment, and communication. Network security is essential in the digital era, and detecting intrusion threats is the most difficult problem. As a result, the network is monitored for unusual activity using this hierarchical anomaly intrusion detection system, and when these actions are detected, an alert is generated. This hierarchical anomaly intrusion detection system, which uses artificial neural network (ANN) and is implemented on a cloud computing environment, analyzes data even in the high levels of traffic and protects computer networks and data from malicious activity. As a result, this system shows better detection, accuracy, and precision rates.

Association between Healthy Eating Index-2020, alternative Mediterranean Diet scores, and gastrointestinal cancer risk in NHANES 2005–2018

Diet quality is closely related to the occurrence of gastrointestinal (GI) cancers; however, few studies have investigated the association between the Healthy Eating Index (HEI-2020) and the alternative Mediterranean diet (aMED) scores and GI (GI) cancers. This study aims to assess the association between HEI-2020, aMED scores and GI cancers. Information from a total of 26,320 participants was included in the National Health and Nutrition Examination Survey (NHANES). In our sub-analysis, we focused on participants with complete dietary and health data, specifically assessing the relationship between diet quality and GI cancers outcomes. The 24-hour recall questionnaire was used to collect and assess the participants’ average dietary intake. Diagnoses of GI cancers were based on self-reported medical history confirmed through physician interviews or linked cancer registry data, ensuring diagnostic reliability. Logistic regression models, restricted cubic splines (RCS), subgroup analysis, and interaction methods were employed to fully evaluate the associations between HEI-2020, aMED scores, and GI cancers. Mediation analysis was also conducted to identify potential mediators of this relationship. Even after fully adjusting for potential confounders, participants with high adherence to the HEI-2020-2020 and aMED scores were significantly associated with a reduced risk of GI cancers. Compared to the lowest tertile of HEI-2020, participants in the highest tertile had a 30% reduced risk of GI cancers (OR 0.70, 95% CI 0.50 to 0.98, p = 0.037). Compared to the lowest tertile of aMED scores, participants in the highest tertile had a 37% reduced risk of GI cancers (OR 0.63, 95% CI 0.44 to 0.92, p = 0.014). RCS analysis indicated that both HEI-2020 and aMED scores were significantly associated with GI cancers; however, no significant non-linear relationship was observed. The primary findings confirm that higher adherence to HEI-2020 and aMED scores is associated with a lower risk of GI cancers. These results suggest that maintaining a high-quality diet may play a crucial role in the prevention and management of these cancers. Further research is needed to elucidate the mechanisms and effects of healthy diet management and high-quality diets in the prevention of GI cancers.

"Advances in biomarker discovery and diagnostics for alzheimer's disease".

Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by intracellular neurofibrillary tangles with tau protein and extracellular β-amyloid plaques. Early and accurate diagnosis is crucial for effective treatment and management. The purpose of this review is to investigate new technologies that improve diagnostic accuracy while looking at the current diagnostic criteria for AD, such as clinical evaluations, cognitive testing, and biomarker-based techniques. A thorough review of the literature was done in order to assess both conventional and contemporary diagnostic methods. Multimodal strategies integrating clinical, imaging, and biochemical evaluations were emphasised. The promise of current developments in biomarker discovery was also examined, including mass spectrometry and artificial intelligence. Current diagnostic approaches include cerebrospinal fluid (CSF) biomarkers, imaging tools (MRI, PET), cognitive tests, and new blood-based markers. Integrating these technologies into multimodal diagnostic procedures enhances diagnostic accuracy and distinguishes dementia from other conditions. New technologies that hold promise for improving biomarker identification and diagnostic reliability include mass spectrometry and artificial intelligence. Advancements in AD diagnostics underscore the need for accessible, minimally invasive, and cost-effective techniques to facilitate early detection and intervention. The integration of novel technologies with traditional methods may significantly enhance the accuracy and feasibility of AD diagnosis.

Airport infrastructure and runway precision aids for forecasting flight arrival delays

Recent research has concentrated on using machine learning approaches to forecast flight delays. The majority of prior prediction algorithms were based on simple and standard attributes collected from the database from which the data were pulled. This article is the first attempt to propose novel features linked to airport capacity and infrastructure. The total runways, the total runway intersections, the longest runway length, the shortest runway length, the runway precision rate, the total terminals, and the total gates were all examined. In this paper, we suggest an optimized multilayer perceptron to predict flight arrival retards implementing data for domestic flights operated in United States airports. We employed data normalization, sampling techniques, and hyper-parameter tuning to strengthen the reliability of the suggested model. The experimental findings demonstrated that data normalization, sampling approaches, and Bayesian optimization produced the most accurate model with 92.49% accuracy. The achievements of the study were compared to other benchmark research from literature. The time complexity for the proposed model was computed and presented at the end of the investigation.

Automating container damage detection with the YOLO-NAS deep learning model.

Ensuring the integrity of shipping containers is crucial for maintaining product quality, logistics efficiency, and safety in the global supply chain. Damaged containers can lead to significant economic losses, delays, and safety hazards. Traditionally, container inspections have been manual, which are labor-intensive, time-consuming, and error-prone, especially in busy port environments. This study introduces an automated solution using the YOLO-NAS model, a cutting-edge deep learning architecture known for its adaptability, computational efficiency, and high accuracy in object detection tasks. Our research is among the first to apply YOLO-NAS to container damage detection, addressing the complex conditions of seaports and optimizing for high-speed, high-accuracy performance essential for port logistics. Our method showcases YOLO-NAS's superior efficacy in detecting container damage, achieving a mean average precision (mAP) of 91.2%, a precision rate of 92.4%, and a recall of 84.1%. Comparative analyses indicate that YOLO-NAS consistently outperforms other leading models like YOLOv8 and Roboflow 3.0, which showed lower mAP, precision, and recall values under similar conditions. Additionally, while models such as Fmask-RCNN and MobileNetV2 exhibit high training accuracy, they lack the real-time assessment capabilities critical for port applications, making YOLO-NAS a more suitable choice. The successful integration of YOLO-NAS for automated container damage detection has significant implications for the logistics industry, enhancing port operations with reliable, real-time inspection solutions that can seamlessly integrate into predictive maintenance and monitoring systems. This approach reduces operational costs, improves safety, and lessens the reliance on manual inspections, contributing to the development of "smart ports" with higher efficiency and sustainability in container management.

DermaSense AI: Revolutionizing Skin Disease Detection with Artificial Intelligence

The early detection and diagnosis of skin diseases are crucial for effective treatment and management. This paper presents DermaSense AI, an innovative platform that leverages Convolutional Neural Networks (CNNs), specifically the InceptionV3 architecture, to automate the detection of skin diseases with high accuracy. By integrating with Telegram, a popular messaging platform, DermaSense AI offers a user-friendly interface for preliminary diagnosis, enabling users to upload images for analysis. The system addresses challenges in dermatological care, such as limited access, high costs, and subjective diagnostics, by providing a scalable, cost-effective, and efficient solution. This study outlines the development, implementation, and testing of the DermaSense AI platform, demonstrating its potential to enhance dermatological care globally through accessible and reliable diagnostics.

Comparing the accuracy and safety of automated CO2 angiography to iodine angiography in peripheral arterial disease with chronic limb ischemia: a prospective cohort study

Introduction: Diagnostic angiography of peripheral arteries using carbon dioxide (CO2) is feasible in nearly all areas below the diaphragm. Using carbon dioxide as a contrast material in angiography provides the highest quality diagnostic results in the vascular segments above the knee. However, its diagnostic reliability decreases as it moves toward the distal side of the vessels below the knee. This study investigated the diagnostic accuracy and consistency between CO2 and iodine contrast angiography in patients with peripheral vascular disease (PVD) with chronic limb ischemia (CLI). Methods: The study prospectively enrolled 35 patients with PVD and CLI and performed both CO2 and iodine contrast angiography, comparing the results for each patient. Image quality, stenosis severity, and anatomical location were analyzed. Results: In this study, a total of 35 patients (19 male) with an average age of 56.91 ± 10.73 were examined. Among them, 13 patients (37.1%) had involvement in the femoral region, 8 patients (22.9%) in the popliteal region, 8 patients (22.9%) in the tibial region, and 6 patients (17.1%) in the foot region. CO2 angiography produced excellent image quality in 40% of cases, with good quality in another 25.7%. The quality decreased in the popliteal and foot regions. While stenosis assessment was comparable between the two methods in the femoral, popliteal, and tibial regions, there was a significant difference in the foot region. The sensitivity, specificity, positive predictive value, and negative predictive value of CO2 angiography were all 100% in the femoral and popliteal areas. However, these values were lower in the tibial and foot areas. Discussion: The study concluded that the use of CO2 angiography, particularly for vascular lesions above the popliteal cavity, is a valuable and safe method for peripheral vascular examination of the lower limbs. It can serve as an alternative to iodine contrast angiography, especially in patients with kidney failure.

Object Detection &amp; Analysis with Deep CNN and Yolov8 in Soft Computing Frameworks

Object detection is one of the major roles in deep learning and soft computing which contributes to many real time cases in healthcare, agriculture etc. This study proposes a deep learning-based approach for object detection to detect lung cancer and diagnosis by utilizing deep Convolutional Neural Networks (CNN) and the YOLOv8 model, with DICOM (Digital Imaging and Communications in Medicine) images for robust image analysis. Lung cancer remains one of the leading causes of mortality worldwide, necessitating early and accurate detection to improve patient outcomes. The primary objective of the research is to enhance the accuracy, precision, and recall rates in lung cancer detection, while reducing false positives and false negatives, through advanced machine learning techniques. In the proposed work, CNN is employed for feature extraction, enabling the model to capture the intricate patterns present in the DICOM images. YOLOv8, a cutting-edge object detection algorithm, is integrated to detect cancerous regions with high efficiency and speed. A comparative analysis is conducted with traditional machine learning classifiers such as Support Vector Machine (SVM), AdaBoost, Random Forest, and K-Nearest Neighbors (KNN), demonstrating the superior performance of the proposed deep learning models. The experimental results reveal that the CNN-YOLOv8 model achieves remarkable accuracy of 94 Parsant, with a precision of 93.56 Parsant, recall of 92 Parsant, ROC score of 93 Parsant, and an F-score of 94.60 Parsant. These findings underscore the effectiveness of deep learning in lung cancer detection, significantly outperforming conventional models in terms of accuracy and reliability. The novelty of this research lies in the integration of CNN with YOLOv8, specifically optimized for medical DICOM images, which allows for real-time, accurate identification of lung cancer while maintaining computational efficiency.

Application of the Microwave Interferometry for Diagnostics of Chemical Ionization Reactions in Low-Temperature Plasma

ABSTRACT Ionization processes in chemically reacting systems attract much attention from researchers as one of the ways to create low-temperature plasma. Reliable quantitative diagnostics, i.e. determining the absolute concentrations of charged particles (ions and electrons) and their collisions frequencies with neutral components in low-temperature plasma with reactions of chemical ionization, is also of great interest. One of the most direct methods for determining the concentration of free electrons is the microwave interferometry technique. In the current paper, we carried out kinetic modeling of the formation of free electrons in the process of chemical ionization during the oxidation of various hydrocarbons, in particular methane, acetylene, ethylene and propane in reflected shock waves. The simulated profiles of the concentration of free electrons for methane and acetylene were compared with the results of our own experiments carried out using a microwave interferometer, and their good agreement was obtained. We also compared the results of our kinetic simulations with the results of experiments on a microwave interferometer of a different design carried out by other authors for chemical ionization of a number of aliphatic hydrocarbons such as methane, acetylene, ethylene and propane.

Advanced neural network systems for analysis of blood-based biomarkers in metastatic disease detection

Neural network systems have become the gold provocative standard in blood-based biomarker analysis for metastatic disease diagnosis, providing higher sensitivity and specificity for early cancer detection. The lexical method also showed that recent developments in artificial intelligence and machine learning technologies allow for the complex interpretation of various types of biomarkers, such as circulating tumor cells, cell-free DNA, microRNAs, and proteins. Many biochemical patterns of biomarkers could be easily handled through sophisticated algorithms and depending on these active approaches in diagnosing metastatic outcomes more accurately at earlier stages. Literature analysis involved a targeted selection of scientific peer-reviewed articles dedicated to neural network utilization in blood-based biomarker screening for cancer. Doing a systematic evaluation critically assessed methodologies associated with artificial intelligence, types of biomarkers, methods of detecting biomarkers, and clinical validation strategies. Filtering was done based on several factors including the identification of new architectures for neural networks, new biomarker analysis methods, and clinical applications primarily focusing on the early detection of metastatic diseases. Analysis of reviewed studies showed a high diagnostic accuracy when neural network systems are used for biomarker analysis. Volumes in Cancer Computational Biology Vol reported that the machine learning models have achieved different sensitivity rates of over 90% including the ability to detect early-stage metastatic disease. The use of several categories of biomarkers and application-improved neural networks for their evaluation showed that the combined use of markers yields better diagnostic results than using single biomarkers. Neural network systems have significant potential to transform metastatic disease diagnosis using circulating biomarker detection. Using sophisticated computational models biomarker patterns are analyzed in detail and the diagnosis is made earlier, thus contributing to better treatment outcomes. Some complexities that are potential barriers include enforcing analysis protocols as standards, correcting and calibrating, and embracing routine technological practice. High-end artificial neural networks are the new frontier in blood-based biomarker analysis of metastatic disease diagnosis. Applying AI within the classic biomarker detection approach increases diagnostic reliability, detection timeliness, and the overall outlook for patient treatment. The advancement in neural network architectures as well as biomarker analysis techniques provides for further improvement in cancer diagnostics in the future.

P-129. Evaluation of the Mannheim Peritonitis Index, the Neutrophil/Lymphocyte Ratio, and the Platelet/Lymphocyte Ratio as Predictive Parameters of Clinical Outcomes of Patients with Intra-Abdominal Infection in a Teaching Hospital in Nicaragua

Abstract Background Intra-abdominal infections are associated worldwide with relatively high mortality. Decisions in patient management and clinical outcomes may be determined by specific risk factors that can be assessed in the form of scores or indices, and ratios. The objective of this study was to evaluate the Mannheim Peritonitis Index (MPI), the Neutrophil/Lymphocyte Ratio (NLR), and the Platelet/Lymphocyte Ratio (PLR) as predictors of mortality and other clinical outcomes in this type of patients at a teaching and referral hospital (Dr. Fernando Vélez Paiz Hospital) in Managua, Nicaragua.Table 1.Mannheim Peritonitis Index and Surgical Reintervention, Admission to ICU, and Mortality Methods This is a retrospective, cross-sectional, analytical study. Patients hospitalized for complicated intra-abdominal infection (cIAI)an between November 2021 and November 2023 were included. The relationship of MPI, NLR, and PLR with mortality and other clinical outcomes as need for reoperation, requiring admission to intensive care unit, and length of hospital stay was analyzed. The cut-off points of previous reference studies for MPI (≥ 26 points), NLR (≥ 11), and PLR (≥ 222) were used. Sensitivity, specificity and a ROC curve (AUC) were calculated for each of the predictive instruments evaluatedTable 2.Neutrophiles/Lymphocytes Ratio and Surgical Reintervention, Admission to ICU, and Mortality Results 102 patients with cIAI were included in the study. The mean age was 56.05 ± 21.25 years-old. The most common etiology was acute appendicitis (39.2%). Overall mortality was 34.3%. The need for surgical reintervention was observed in 72.7% of patients with MPI ≥ 26 points, 31.3% of patients with NLR ≥ 11, and 45.0% of patients with PLR ≥ 222. Regarding requiring admission to the intensive care unit, it was observed in 84.0% of patients with MPI ≥ 26 points, 57.8% of patients with NLR ≥ 11, and 27.5% of patients with PLR ≥ 222. Mortality in patients with MPI ≥ 26 points was 75.0%, and 46.9% in patients with NLR ≥ 11 (Table 1 and 2). Theand specificity of MPI for mortality was 94.3% and 47.9% respectively, with an AUC of 0.95. The sensitivity and specificity of NLR for mortality were 85.7% and 49.3% respectively (Table 3).Table 3.Sensitivity and Specificity of MPI and NLR for Mortality Prediction. Conclusion The MPI ≥ 26 points predicts mortality, a higher probability of surgical reoperation, ICU admission, and prolonged hospital stay. In the population of this study, the cut-off point with the best diagnostic reliability was MPI ≥ 25 points. The NLR ≥ 11 points is also a significant predictor of mortality. Disclosures All Authors: No reported disclosures

Enhancing lung cancer diagnostic accuracy and reliability with LCDViT: an expressly developed vision transformer model featuring explainable AI

Enhancing lung cancer diagnostic accuracy and reliability with LCDViT: an expressly developed vision transformer model featuring explainable AI

Analyzing the impact of blood collection errors on patient safety and clinical outcomes⁠

Errors in blood collection processes pose a significant challenge to healthcare systems, contributing to diagnostic inaccuracies, compromised patient safety, and adverse clinical outcomes. Pre-analytical errors, including patient misidentification, improper labeling, hemolysis, and sample contamination, are among the most common sources of laboratory mistakes. These errors can delay diagnosis, lead to unnecessary medical interventions, and increase healthcare costs. Misidentification and labeling errors, for example, have been linked to life-threatening outcomes in transfusion medicine, while hemolysis often results in falsely elevated laboratory values that can mislead clinical decision-making. Effective strategies to address blood collection errors include leveraging technological innovations, such as barcoding systems and automated labeling, which have demonstrated success in reducing mislabeling incidents. Adherence to standardized guidelines, including protocols established by the Clinical and Laboratory Standards Institute (CLSI), plays a crucial role in maintaining sample integrity. Additionally, phlebotomy training programs and competency assessments ensure that healthcare staff consistently follow best practices, minimizing errors during the collection process. Quality management tools, including Six Sigma and Lean methodologies, further enhance laboratory processes by identifying root causes of errors and implementing targeted improvements. Patient engagement also contributes to error prevention, with informed and active participation serving as an additional safeguard against potential mistakes. The integration of these strategies has shown promise in improving diagnostic reliability and reducing the clinical and economic burden of blood collection errors. By addressing systemic, procedural, and technological factors, healthcare systems can ensure safer and more accurate diagnostic practices, ultimately enhancing patient outcomes. A multidisciplinary focus remains essential for achieving sustainable improvements in blood collection processes and mitigating risks associated with pre-analytical errors.

P-2166. Sensitivity and Specificity of Nanopore Sequencing for Detection of Methicillin-Resistant Staphylococcus aureus and Methicillin-Resistant Staphylococcus epidermidis in Positive Blood Culture Samples

Abstract Background Nanopore sequencing enables rapid DNA/RNA analysis without amplification. Implementing this for point-of-care diagnostics reduces time delays in traditional AST methods, potentially enhancing patient outcomes. We aim to evaluate the performance of Oxford Nanopore Technologies sequencing from positive blood culture for bacterial identification and antimicrobial susceptibility prediction in S. aureus and S. epidermidis by detecting the mecA gene. Methods We conducted a cross-sectional descriptive study on individuals with positive blood cultures identifying S. aureus and S. epidermidis over a 12-month period from April 2023 to March 2024. Bacterial DNA was extracted from the blood culture specimens, and then sequenced using the PromethION Flow Cell to identify the organisms and mecA genes, comparing the results to routine blood cultures and standard AST. Results 108 blood culture samples were initially collected. After applying the exclusion criteria, 80 samples qualified for DNA extraction and sequencing. 45 samples were identified as S. aureus (6 MRSA and 39 MSSA) and 35 as S. epidermidis (27 MRSE and 8 MSSE). Notably, 67.5% of samples contained less than 0.5 ng/μl of DNA. Sensitivity and specificity of mecA gene detection were 35.5% (95% CI: 18.6%–52.3%) and 83.7% (95% CI: 73.3%–94.0%), respectively, with an accuracy of 65.0% (95% CI: 54.5%–75.5%). Upon excluding samples with DNA less than 0.5 ng/μl accuracy improved to 73.1% (95% CI: 56.0%–90.1%). The specimen that showed a false-positive result will proceed to phenotypic confirmation using methicillin-infused mannitol-salt agar. After phenotypic confirmation, the accuracy improved to of 88.5% (95% CI: 76.2%–100.0%). In this study, we also found 5 samples in which the mecA gene was shown to be genotypically oxacillin-sensitive after phenotypic confirmation. The median time for detecting the mecA gene was 198 minutes (IQR: 37.5–458.7) after the onset of sequencing. Conclusion Our study on nanopore sequencing for MRSA and MRSE detection from blood cultures found promising but limited sensitivity and specificity in detecting mecA gene. Challenges in DNA extraction from Gram-positive bacteria affected overall accuracy. Further improvements are needed for enhanced diagnostic reliability. Disclosures All Authors: No reported disclosures