Accurate Blood Research Articles

Comparative Analysis of Blood Transfusion Accuracy and Hemolysis Rate of Transfusion Cartridge Set Between Conventional Infusion Pumps and Cylinder-Type Infusion Pumps

Background: Infusion pumps are critical in delivering fluids, including medications and blood products, in controlled amounts. However, conventional pumps can cause hemolysis and other issues such as flow variations and infection risks, especially during blood transfusions. To address these limitations, a novel cylinder-type infusion pump, the Anyfusion H-100, was developed, which includes a specialized blood transfusion cartridge set that combines syringe and peristaltic infusion methods. This study evaluates the accuracy and hemolysis rates of the Anyfusion H-100 compared to conventional pumps, aiming to confirm its viability as a safe and effective medical device for blood transfusions. Methods: This study evaluated six different infusion rates (10–180 cc/hr) and conducted 57 transfusion trials, 20 of which used a 1:1 blood–saline dilution. Blood transfusion accuracy was measured using research-grade packed red blood cells, and hemolysis rates were assessed before and after transfusion by chi-square tests and independent sample t-tests. Results: Anyfusion demonstrated an average transfusion error rate of 3.77%, compared to 4.00% for the Terufusion, with no statistically significant difference in hemolysis rates (p = 0.697). Bland–Altman plots confirmed their equivalent performance, with hemolysis rates of 0.566 ± 0.095% for Anyfusion and 0.518 ± 0.126% for Terufusion. Conclusions: Anyfusion provides an accurate and reliable blood transfusion performance comparable to that of Terufusion, with no significant difference in hemolysis rates; its integration of syringe and infusion methods shows a potential for safer and more efficient transfusion practices, especially in pediatric and emergency settings.

RU-Net, Multi-Scale Feature Fusion and Transfer Learning: Unlocking the Potential of Cuffless Blood Pressure Monitoring with PPG and ECG.

This study introduces an innovative deep-learning model for cuffless blood pressure estimation using PPG and ECG signals, demonstrating state-of-the-art performance on the largest clean dataset, PulseDB. The rU-Net architecture, a fusion of U-Net and ResNet, enhances both generalization and feature extraction accuracy. Accurate multi-scale feature capture is facilitated by short-time Fourier transform (STFT) time-frequency distributions and multi-head attention mechanisms, allowing data-driven feature selection. The inclusion of demographic parameters as supervisory information further elevates performance. On the calibration-based dataset, our model excels, achieving outstanding accuracy (SBP MAE ± std: 4.49 ± 4.86 mmHg, DBP MAE ± std: 2.69 ± 3.10 mmHg), surpassing AAMI standards and earning a BHS Grade A rating. Addressing the challenge of calibration-free data, we propose a fine-tuning-based transfer learning approach. Remarkably, with only 10% data transfer, our model attains exceptional accuracy (SBP MAE ± std: 4.14 ± 5.01 mmHg, DBP MAE ± std: 2.48 ± 2.93 mmHg). This study sets the stage for the development of highly accurate and reliable wearable cuffless blood pressure monitoring devices.

Accurate and 30-plus days reliable cuffless blood pressure measurements with 9-minutes personal photoplethysmograph data and mixed deduction learning

Cuffless blood pressure (BP) measurements have long been anticipated, and the PPG (Photoplethysmography)-only method is the most promising one since already embedded in many wearable devices. To further meet the clinical accuracy requirements, PPG-only BP predictions with personalized modeling for overcoming personal deviations have been widely studied, but all required tens to hundreds of minutes of personal PPG measurements for training. Moreover, their accurate test periods without calibration practice were not reported. In this work, we collected records of PPG data from our recruited subjects in real-life scenarios instead of relying on the openly available MIMIC dataset obtained from intensive care unit (ICU) patients. Since our objective is commercial application and a substantial reduction in training data, we tailored our model training to closely mimic real-world usage. To achieve this, we developed a training approach that only requires 9-minutes of personal PPG signal recordings and mixed with other PPG data from our recruited 364 subjects. The modeling is conducted with two-channel paired inputs to the convolutional neural network (CNN)-based model, which we called Mixed Deduction Learning (MDL). The test results of 88 samples from 15 subjects, under testing period up to 30-plus days without extra calibration, revealed that MDL meets most of the standards of AAMI, BHS, and IEEE 1708–2014 (for static test only) for BP measurement devices, which indicates MDL’s long-term stability and consistency. Furthermore, we found that the model with two-channel inputs presents a trend of improving performance as the pool of mixed training data increased, while the conventional one-channel input revealed degraded performance. The outperformance of MDL is attributed to many significant features remained in the first CNN layer even when mixing personal 9-minutes data with the other 364 subjects. Consequently, PPG-only with MDL introduces a new avenue for overcoming challenges in training due to personal physiological variations. Given our consideration of real-life usage, this technology can be seamlessly translated to commercial applications.

SCKansformer: Fine-Grained Classification of Bone Marrow Cells via Kansformer Backbone and Hierarchical Attention Mechanisms.

The incidence and mortality rates of malignant tumors, such as acute leukemia, have risen significantly. Clinically, hospitals rely on cytological examination of peripheral blood and bone marrow smears to diagnose malignant tumors, with accurate blood cell counting being crucial. Existing automated methods face challenges such as low feature expression capability, poor interpretability, and redundant feature extraction when processing highdimensional microimage data. We propose a novel finegrained classification model, SCKansformer, for bone marrow blood cells, which addresses these challenges and enhances classification accuracy and efficiency. The model integrates the Kansformer Encoder, SCConv Encoder, and Global-Local Attention Encoder. The Kansformer Encoder replaces the traditional MLP layer with the KAN, improving nonlinear feature representation and interpretability. The SCConv Encoder, with its Spatial and Channel Reconstruction Units, enhances feature representation and reduces redundancy. The Global-Local Attention Encoder combines Multi-head Self-Attention with a Local Part module to capture both global and local features. We validated our model using the Bone Marrow Blood Cell FineGrained Classification Dataset (BMCD-FGCD), comprising over 10,000 samples and nearly 40 classifications, developed with a partner hospital. Comparative experiments on our private dataset, as well as the publicly available PBC and ALL-IDB datasets, demonstrate that SCKansformer outperforms both typical and advanced microcell classification methods across all datasets.

Blood Pressure Cuff Sizes for Pregnant Women in the United States: Findings from the National Health and Nutrition Examination Survey.

The use of correctly-sized blood pressure (BP) cuffs is important to ensure accurate measurement and effective management of hypertension. The goals of this study were to determine the proportions of pregnant women that would require small, adult, large, and extra-large (XL) cuff sizes, and to examine the demographic characteristics associated with need for a large or XL cuff. This cross-sectional study analyzed 1,176 pregnant women (≥18 years) included in the National Health and Nutrition Examination Survey (NHANES) 1999-2006 cycles. Recommended BP cuff sizes, based on American Heart Association recommendations, were categorized by mid-arm circumference: small adult (≤26cm), adult (>26 to ≤34cm), large (>34 to ≤44cm), and extra-large (XL) (>44cm). Among US pregnant women, recommended cuff sizes were: 17.9% small adult, 57.0% adult, and 25.1% for large or XL. About 38.5% of non-Hispanic Black, 21.6% of Mexican American and 21.0% of non-Hispanic White pregnant women required a large or XL cuff. About 81.8% of women in the highest quartile for BMI required large or XL cuffs, which was significantly higher than women in other quartiles. Roughly one out of every four pregnant women required large or XL BP cuffs. The requirement for large or XL cuffs was highest among non-Hispanic Black women and women with the highest BMI. For pregnant women, measuring the arm circumference and selecting an appropriately-sized cuff is important to facilitate accurate blood pressure monitoring and hypertension management.

S986 Quality Initiative to Instate Accurate Guaiac Fecal Occult Blood Test Requests and Interpretation to Decrease Unnecessary Testing, Misdiagnosing, and Improve Cost in a Large Community Hospital

S986 Quality Initiative to Instate Accurate Guaiac Fecal Occult Blood Test Requests and Interpretation to Decrease Unnecessary Testing, Misdiagnosing, and Improve Cost in a Large Community Hospital

Automated Digital Sfigmomanometer Prototype Testing

Abstract Blood pressure is the pressure of blood flow in the arteries generated by the heart. Abnormal blood pressure can lead to hypertension and hypotension. Hypotension, or low blood pressure, has a prevalence of 5% to 34% among individuals aged 17 to 19, and over 50% in the elderly. Hypertension can cause death in patients with heart disease. About 39.7% of people suffer from hypertension, especially those over the age of 60. Blood pressure measurement needs to be done regularly because it has impact such as early detection of blood pressure health conditions and monitoring of health conditions for those already diagnosed with abnormal blood pressure. Unfortunately, only 59% of the population in Indonesia regularly measure their blood pressure. Accurate blood pressure measurement can be performed using an invasive method. Another method is non-invasive, which can be done using a sphygmomanometer that applies the oscillometric method. This method uses pressure oscillations in the cuff influenced by the pulse in the blood vessels. When using this method, several factors need to be considered, such as body position, cuff size, and the technique used during the measurement. In this study, a fully automatic digital sphygmomanometer has been developed with a cuff attached to the device, equipped with a thermal printer to print out the measurement results and classify blood pressure categories. The advantage of the developed prototype is that it has a smaller relative error value, with 1.03% for systolic blood pressure and 1.45% for diastolic blood pressure, and has already been integrated with a thermal printer to directly print the measurement results.

EFFECTIVENESS OF CONTINUOUS GLUCOSE MONITORING IN UNCONTROLLED TYPE-2 DIABETICS IN TERTIARY HEALTHCARE CENTRE

Long term diabetic complications can be prevented or reduced by achieving good metabolic control, reflected by HbA1c <6.5–7.0%.1-3 Glucose excursions might also contribute to the development of diabetic complications.4,5 Fear of hypoglycemia limits the ability to reach strict glycemic control, because it is usually accompanied by reluctance of the patient to intensify insulin therapy. Indeed, the goal of intensive therapy is to normalize HbA1c and control fasting and postprandial glycemia, while concurrently limiting the number and severity of hypoglycemic events. To reach tight glycemic control, frequent self- monitoring of blood glucose (SMBG) must be performed.6 SMBG devices provide the patient with accurate but discreet blood glucose levels. They do not provide trend information nor do they reflect glycemic fluctuations, which is possible by using continuous glucose monitoring (CGM) systems. Thus, implementation of strict glycemic control may be facilitated by a CGM device. This manuscript critically reviews the proposed benefits and indications of CGM and the current evidence of CGM on health outcomes in diabetic patients.

Textile Organic Electrochemical Transistor for Non-Invasive Glucose Sensing

The global rise in diabetes has highlighted the urgent need for continuous, non-invasive health monitoring solutions. Traditional glucose monitoring methods, which are invasive and often inconvenient, have created a demand for alternative technologies that can offer comfort, accuracy, and real-time data. In this study, the development of a textile-based organic electrochemical transistor (OECT) is presented, designed for non-invasive glucose sensing, aiming to integrate this technology seamlessly into everyday clothing. The document details the design, optimization, and testing of a one-component textile-based OECT, featuring a porous PEDOT:PSS structure and a glucose oxidase-modified electrolyte for effective glucose detection in sweat. The research demonstrates the feasibility of using this textile-based OECT for non-invasive glucose monitoring, with enhanced sensitivity and specificity achieved through the integration of glucose oxidase within the electrolyte and the innovative porous PEDOT:PSS design. These findings suggest a significant advancement in wearable health monitoring technologies, providing a promising pathway for the development of smart textiles capable of non-invasively tracking glucose levels. Future work should focus on refining this technology for clinical use, including individual calibration for accurate blood glucose correlation and its integration into commercially available smart textiles.

Noninvasive multi-cancer detection using blood-based cell-free microRNAs.

Patients diagnosed with early-stage cancers have a substantially higher chance of survival than those with late-stage diseases. However, the option for early cancer screening is limited, with most cancer types lacking an effective screening tool. Here we report a miRNA-based blood test for multi-cancer early detection based on examination of serum microRNA microarray data from cancer patients and controls. First, a large multi-cancer training set that included 1,408 patients across 7 cancer types and 1,408 age- and gender-matched non-cancer controls was used to develop a 4-microRNA diagnostic model using 10-fold cross-validation. In three independent validation sets comprising a total of 4,875 cancer patients across 13 cancer types and 3,722 non-cancer participants, the 4-microRNA model achieved greater than 90% sensitivity for 9 cancer types (lung, biliary tract, bladder, colorectal, esophageal, gastric, glioma, pancreatic, and prostate cancers) and 75-84% sensitivity for 3 cancer types (sarcoma, liver, and ovarian cancer), while maintaining greater than 99% specificity. The sensitivity remained to be > 99% for patients with stage 1 lung cancer. Our study provided novel evidence to support the development of an inexpensive and accurate miRNA-based blood test for multi-cancer early detection.

Comparative Study on Precision and Interference of Maltose and Vitamin C among three Glucometers Commonly Used in United Arab Emirates [U.A.E

Aim: To evaluate the suitability of commercially available glucometers in the UAE in terms of accurate and reliable blood glucose measurements. Background: Portable glucometers are employed for measuring blood glucose levels, offering distinct advantages such as providing instant results and being user-friendly when compared to laboratory reference analyzers. However, certain molecules, such as those found in medications, can interfere with the accuracy of glucometer readings. Objective: To evaluate the precision and interference in the presence of maltose and vitamin C of three glucometers commercially available in the UAE. Results: Accu-Chek InstantTM demonstrated the highest precision among the glucometers tested, with a coefficient of variation of less than 5% for all measured glucose values. In contrast, OneTouch Select Plus FlexTM and Trister GlucoscanTM exhibited higher variability in precision, with coefficients of variation of 11.4% and 11%, respectively. Accu-Chek InstantTM consistently performed well in terms of bias and precision in the presence of interferences, and does not display glucose readings above 50mg/dL of Vitamin C. Notably, Ascorbic acid induced a greater bias compared to Maltose for all three glucometers. Methods: We utilized plasma samples to conduct two types of experiments: a precision experiment and an interference experiment. We compared the precision of three glucometer brands available in the United Arab Emirates [Accu-Chek InstantTM, One Touch Select Plus FlexTM, and Trister GlucoScanTM] in the presence or not of various interfering molecules, such as Maltose and Ascorbic Acid [Vitamin C]. Conclusion: The performance of the glucometer is affected by its testing methodology. Accu-Chek InstantTM shows improved precision and is able to detect the presence of Vitamin C. When it comes to Maltose interference, it results in a higher bias change but lower variability, which can be addressed by applying a correction factor.

In-vitro blood purification using tiny pinch holographic optical tweezers based on deep learning

In-vitro blood purification is essential to a wide range of medical treatments, requiring fine-grained analysis and precise separation of blood components. Despite existing methods that can extract specific components from blood by size or by magnetism, there is not yet a general approach to efficiently filter blood components on demand. In this work, we introduce the first programmable non-contact blood purification system for accurate blood component detection and extraction. To accurately identify different cells and artificial particles in the blood, we collected and annotated a new blood component object detection dataset and trained a collection of deep-learning-based object detectors upon it. To precisely capture and extract desired blood components, we fabricated a microfluidic chip and set up a customized holographic optical tweezer to trap and move cells/particles in the blood. Empirically, we demonstrate that our proposed system can perform real-time blood fractionation with high precision reaching up to 96.89%, as well as high efficiency. Its scalability and flexibility open new research directions in blood treatment.

Quantification of physiological effect of respiration on automated measurement of blood pressure among normotensive adult individuals.

Accurate blood pressure measurement necessitates meticulous methodology, as even minor variations like speaking or sitting can impact the readings. Additionally, respiration plays a role in blood pressure, exhibiting a dip during inhalation and a subsequent increase during exhalation. However, the influence of breathing patterns, duration, and rate on blood pressure remains largely unexplored. In this study, we have attempted to quantify the changes in blood pressure and heart rate (HR) of normotensive individuals while performing predefined respiratory patterns - slow, medium, and fast (respiratory rates of 5, 10, and 20/m, respectively). For each respiratory pattern, age-matched and gender-matched (18-40 years) volunteered normotensive individuals were selected as volunteers. Baseline readings were recorded and each volunteer was randomly allotted a respiratory pattern. The volunteers performed the assigned respiratory pattern while the BP and HR were recorded. A fall in both SBP and DBP was observed in all three patterns of respiration. There was no inter-pattern difference in the blood pressure change. A novel finding in our study was a trend of respiratory rate and HR - the change in HR linearly increased with a rise in respiratory rate difference. We also proposed a linear regression equation for this increase in HR with the increase in respiratory rate which was statistically significant. The findings suggest the decline in blood pressure is independent of the respiratory pattern employed. The study also demonstrates that the HR is a linear function of respiratory rate.

Abstract P315: Using Home Blood Pressure Monitors in the Office Setting as an Alternative to Automated Office Blood Pressure: A Quality Improvement Project

Background: Accurate blood pressure (BP) measurement is key to the diagnosis and effective treatment of hypertension (HTN). The U.S. HTN guideline recommends having patients rest for 5 minutes before measuring BP and obtaining at least two measurements 1-2 minutes apart. This is difficult to achieve in a busy primary care practice, and while automated office BP (AOBP) has been advanced as a solution, the required device may be cost-prohibitive. As home BP monitors are much less expensive, a protocol employing them in the office setting could prove to be an attractive alternative to AOBP. Objective: To promote the recording of multiple BP readings in primary care visits by using home BP monitors for measurement. Methods: Our primary care practice hosts 110 internal medicine residents and completes more than 35,000 patient visits annually. Prior to the intervention, medical assistants (MAs) obtained vital signs (VS) at every visit using a VS cart. In the first version of the new protocol, MAs measured all VS except BP using the VS cart, then measured BP once using an Omron 5 series BP monitor and recorded that reading in the chart. MAs left the cuff on the patient’s arm and instructed him/her to rest quietly for 5 minutes before taking a second BP reading him/herself while waiting for the provider after the MA exited the room. The patient took a third reading 1-2 minutes after the second. The provider recorded the second and third readings in the chart. Results: We implemented the new protocol in November 2023. In February 2024, we met with MAs to solicit feedback. They found the protocol easy to follow overall but had two concerns: (1) It was cumbersome to use two different devices to obtain a full set of VS; and (2) since many patients had normal BP, it did not seem worthwhile to obtain multiple BP measurements for all patients. After this meeting, we began measuring heart rate and oxygen saturation with a portable pulse oximeter instead of the VS cart, which is now only used in special circumstances. We also modified the protocol so that patients with systolic BP < 120 mm Hg and diastolic BP < 80 mm Hg are not required to obtain any repeat BP measurements. Conclusions: A new BP measurement protocol using home BP monitors to obtain multiple readings at each visit was feasible in our large academic primary care practice. We plan to investigate its effect on frequency of repeat BP measurement and likelihood of intensifying therapy for uncontrolled HTN.

O84 BLOOD PRESSURE MEASUREMENT VIA IMPEDANCE CARDIOGRAPHY: AN ARTIFICIAL INTELLIGENCE BASED PROOF-OF-CONCEPT

Objective: Accurate blood pressure (BP) measurement is crucial for the diagnosis, risk assessment, treatment decision-making, and monitoring of cardiovascular diseases. Unfortunately, the gold-standard, cuff-based BP measurement suffer from inaccuracies and discomfort. As a result, continuous, cuff-less, and non-invasive BP assessment methods are merging as promising alternatives. This study is the first to comprehensively assess impedance cardiography (ICG) for Machine Learning enabled BP measurement. Methods: We analysed ICG data from 71 young and healthy adults. Nine different Machine Learning algorithms were evaluated for their BP estimation performance. Accuracy measures comprised mean difference, standard deviation, Limits of Agreement, mean absolute error, and root mean squared error. Additionally, the B-Score was calculated to evaluate the “true”, relative performance of the best-performing model. Results: The Multi-Linear Regression model showed the highest performance (mean difference = -0.01, r = 0.82) for systolic BP. The Support Vector Regressor model achieved the best results (mean difference = 0.15, r = 0.51) for diastolic BP. Both models exhibited positive B-Scores, indicative of their predictive capability. All tested models’ estimations correlated with both systolic and diastolic reference BP (r > 0.72 / r > 0.34, p < 0.001). Conclusion: The study highlights the potential of ICG based Machine Learning algorithms for accurately estimating arterial BP. Such algorithms can provide accurate and continuous BP data. This offers the possibility of enhancing patient care, timely diagnostics, and treatment decision-making. Our approach is especially promising for post-surgical and intensive care environments.

Machine learning-based noninvasive diagnostic classifiers for the prediction of cancer tissue of origin using serum microRNAs.

101 Background: Noninvasive multi-cancer early detection (MCED) with or without tissue of origin (TOO) has the potential to reduce cancer-related mortality by analyzing circulating cell-free nucleic acids and/or proteins in blood. Accurate prediction of TOO following a positive MCED test would guide selection of confirmatory tests, thereby expediting the definitive diagnosis and prompt initiation of the most appropriate treatment, tailored to the specific cancer type. Here, we report the development of machine learning-based diagnostic classifiers that predict TOO for 13 cancer types with high accuracy using serum microRNAs. Methods: Eight serum miRNA microarray datasets from GEO totaling 6,283 patients across 13 cancer types were used in this study. The patients were split, with an approximate 3:2 ratio, into a training (n=3,844) and a validation set (n=2,439). An ensemble of classifiers was constructed in the training set via the “one vs. rest” approach, thus one classifier for each cancer type. Random forest models with recursive feature elimination (RFE) selected the optimal set of miRNAs that was fed into support vector machine models to generate a prediction probability for each cancer type. The type with the highest probability was considered the predicted cancer type. The performance of these classifiers was evaluated in the validation set in two steps with the 1st using all cancer types and the 2nd using the top 2 or 3 cancer types from the 1st step to achieve a refined prediction. Results: RFE selected 426 miRNAs for building the 13 classification models. In the validation set comprising 2,439 patients across 12 cancer types, the classifiers correctly predicted cancer types for 1,922 (79%) samples based on the highest prediction probability. The accuracy increased to 92% and 95% based on top 2 and 3 predictions. In particular, based on top 3 predictions, the accuracy was >95% for bladder, breast, prostate, gastric, glioma and lung cancers, >85% for ovarian, liver and esophageal cancers, 78% for pancreatic cancer and sarcoma, and 67% for colorectal cancer. Conclusions: With 95% accuracy in narrowing TOO down to 3 organ sites, the miRNA-based TOO classifiers could be used clinically as a reflex test for the simple and highly accurate MCED screening models previously developed ( Cancers 2022,14:1450; ESMO 2024). Together, they support the development of an inexpensive, accurate and noninvasive blood test for MCED with TOO.

Predictive value of the early postoperative hemoglobin-to-red blood cell distribution width ratio for acute kidney injury in elderly intertrochanteric fracture patients

BackgroundHemoglobin-to-red blood cell distribution width ratio (HRR) had great predictive value for the prognosis of malignant tumors and cardiovascular disease. However, its predictive value for the occurrence of acute kidney injury (AKI) in elderly intertrochanteric fracture patients remains unclear. This study aims to analyze the correlation between the early postoperative HRR and the risk of postoperative AKI in elderly intertrochanteric fracture patients.MethodsWe reviewed the medical records of 307 elderly intertrochanteric fracture patients in this single-center retrospective cohort study. We performed univariate analysis on the relevant parameters, and parameters with significant differences were included in the following logistic regression model for multivariate analysis. Then, we used a receiver operating characteristic (ROC) curve to evaluate the predictive value of the early postoperative HRR level for AKI in elderly intertrochanteric fracture patients. Patients were divided into a high HRR group and a low HRR group according to the cutoff point determined by ROC curve analysis. Subsequently, the relevance between postoperative HRR and AKI was further determined using propensity score matching (PSM) and inverse probability of treatment weighting (IPTW).ResultsThe area under the curve of the early postoperative HRR for predicting postoperative AKI was 0.714 (95% CI: 0.618–0.809). The cutoff value was 5.44. The sensitivity was 72.7%, and the specificity was 70.8%. Patients were divided into low HRR (⩽ 5.44) and high HRR (> 5.44) groups according to the cutoff value. PSM and IPTW analysis indicated that the risk of AKI in the low HRR group was significantly higher than that in the high HRR group in both the matched cohort (OR = 6.914, 95% CI: 1.714–46.603, p = 0.016) and the weighted group (OR = 2.784, 95% CI: 1.415–5.811, p = 0.040).ConclusionsEarly postoperative HRR is an accurate, accessible, and economical blood test parameter that can predict the risk of postoperative AKI in elderly patients with femoral intertrochanteric fracture.

A multiblock (MIB) finite element method for accurate and efficient blood flow simulation

We present an efficient and accurate immersed boundary (IB) finite element (FE) method for internal flow problems with complex geometries (e.g. blood flow in the vascular system). In this study, we use a voxelized flow domain (discretized with hexahedral and tetrahedral elements) instead of a box domain, which is frequently used in IB methods. We highlight the applicability and efficiency of the proposed method in generating the flow domain mesh and removing unnecessary portions of the domain, compared to the standard IB methods that rely on a full Cartesian mesh. Our approach is attractive for internal flow problems that use IB methods. The proposed method accurately satisfies the boundary conditions on the immersed object using velocity and pressure correction procedures. The velocity correction applies implicitly such that the velocity on the immersed boundary (Lagrangian points) interpolated from the corrected velocity values computed on the mesh nodes (Eulerian nodes) accurately satisfies the prescribed velocity boundary conditions. The proposed method utilizes the well-established incremental pressure correction scheme (IPCS) FE solver, and the boundary condition-enforced IB (BCE-IB) method to numerically solve the transient, incompressible Navier-Stokes (NS) flow equations. We verify the accuracy of our numerical method using the analytical solution for the Poiseuille flow in a cylinder, and the available experimental data (laser Doppler velocimetry) for the flow in a three-dimensional 90° angle tube bend. We further examine the accuracy and applicability of the proposed method by considering flow within complex geometries, such as blood flow in aneurysmal vessels and the aorta, flow configurations that would otherwise be difficult to solve by most IB methods. Our method offers high accuracy, as demonstrated by the verification examples, and high applicability, as demonstrated through the solution of blood flow within complex geometry. The proposed method is efficient, since it is as fast as the traditional finite element method used to solve the Navier–Stokes flow equations, with a small overhead (not more than 5%) due to the numerical solution of a linear system formulated for the IB method.

An attention-based deep learning for acute lymphoblastic leukemia classification

The bone marrow overproduces immature cells in the malignancy known as Acute Lymphoblastic Leukemia (ALL). In the United States, about 6500 occurrences of ALL are diagnosed each year in both children and adults, comprising nearly 25% of pediatric cancer cases. Recently, many computer-assisted diagnosis (CAD) systems have been proposed to aid hematologists in reducing workload, providing correct results, and managing enormous volumes of data. Traditional CAD systems rely on hematologists’ expertise, specialized features, and subject knowledge. Utilizing early detection of ALL can aid radiologists and doctors in making medical decisions. In this study, Deep Dilated Residual Convolutional Neural Network (DDRNet) is presented for the classification of blood cell images, focusing on eosinophils, lymphocytes, monocytes, and neutrophils. To tackle challenges like vanishing gradients and enhance feature extraction, the model incorporates Deep Residual Dilated Blocks (DRDB) for faster convergence. Conventional residual blocks are strategically placed between layers to preserve original information and extract general feature maps. Global and Local Feature Enhancement Blocks (GLFEB) balance weak contributions from shallow layers for improved feature normalization. The global feature from the initial convolution layer, when combined with GLFEB-processed features, reinforces classification representations. The Tanh function introduces non-linearity. A Channel and Spatial Attention Block (CSAB) is integrated into the neural network to emphasize or minimize specific feature channels, while fully connected layers transform the data. The use of a sigmoid activation function concentrates on relevant features for multiclass lymphoblastic leukemia classification The model was analyzed with Kaggle dataset (16,249 images) categorized into four classes, with a training and testing ratio of 80:20. Experimental results showed that DRDB, GLFEB and CSAB blocks’ feature discrimination ability boosted the DDRNet model F1 score to 0.96 with minimal computational complexity and optimum classification accuracy of 99.86% and 91.98% for training and testing data. The DDRNet model stands out from existing methods due to its high testing accuracy of 91.98%, F1 score of 0.96, minimal computational complexity, and enhanced feature discrimination ability. The strategic combination of these blocks (DRDB, GLFEB, and CSAB) are designed to address specific challenges in the classification process, leading to improved discrimination of features crucial for accurate multi-class blood cell image identification. Their effective integration within the model contributes to the superior performance of DDRNet.

Blood Biomarkers to Detect Alzheimer Disease in Primary Care and Secondary Care

An accurate blood test for Alzheimer disease (AD) could streamline the diagnostic workup and treatment of AD. To prospectively evaluate a clinically available AD blood test in primary care and secondary care using predefined biomarker cutoff values. There were 1213 patients undergoing clinical evaluation due to cognitive symptoms who were examined between February 2020 and January 2024 in Sweden. The biomarker cutoff values had been established in an independent cohort and were applied to a primary care cohort (n = 307) and a secondary care cohort (n = 300); 1 plasma sample per patient was analyzed as part of a single batch for each cohort. The blood test was then evaluated prospectively in the primary care cohort (n = 208) and in the secondary care cohort (n = 398); 1 plasma sample per patient was sent for analysis within 2 weeks of collection. Blood tests based on plasma analyses by mass spectrometry to determine the ratio of plasma phosphorylated tau 217 (p-tau217) to non-p-tau217 (expressed as percentage of p-tau217) alone and when combined with the amyloid-β 42 and amyloid-β 40 (Aβ42:Aβ40) plasma ratio (the amyloid probability score 2 [APS2]). The primary outcome was AD pathology (determined by abnormal cerebrospinal fluid Aβ42:Aβ40 ratio and p-tau217). The secondary outcome was clinical AD. The positive predictive value (PPV), negative predictive value (NPV), diagnostic accuracy, and area under the curve (AUC) values were calculated. The mean age was 74.2 years (SD, 8.3 years), 48% were women, 23% had subjective cognitive decline, 44% had mild cognitive impairment, and 33% had dementia. In both the primary care and secondary care assessments, 50% of patients had AD pathology. When the plasma samples were analyzed in a single batch in the primary care cohort, the AUC was 0.97 (95% CI, 0.95-0.99) when the APS2 was used, the PPV was 91% (95% CI, 87%-96%), and the NPV was 92% (95% CI, 87%-96%); in the secondary care cohort, the AUC was 0.96 (95% CI, 0.94-0.98) when the APS2 was used, the PPV was 88% (95% CI, 83%-93%), and the NPV was 87% (95% CI, 82%-93%). When the plasma samples were analyzed prospectively (biweekly) in the primary care cohort, the AUC was 0.96 (95% CI, 0.94-0.98) when the APS2 was used, the PPV was 88% (95% CI, 81%-94%), and the NPV was 90% (95% CI, 84%-96%); in the secondary care cohort, the AUC was 0.97 (95% CI, 0.95-0.98) when the APS2 was used, the PPV was 91% (95% CI, 87%-95%), and the NPV was 91% (95% CI, 87%-95%). The diagnostic accuracy was high in the 4 cohorts (range, 88%-92%). Primary care physicians had a diagnostic accuracy of 61% (95% CI, 53%-69%) for identifying clinical AD after clinical examination, cognitive testing, and a computed tomographic scan vs 91% (95% CI, 86%-96%) using the APS2. Dementia specialists had a diagnostic accuracy of 73% (95% CI, 68%-79%) vs 91% (95% CI, 88%-95%) using the APS2. In the overall population, the diagnostic accuracy using the APS2 (90% [95% CI, 88%-92%]) was not different from the diagnostic accuracy using the percentage of p-tau217 alone (90% [95% CI, 88%-91%]). The APS2 and percentage of p-tau217 alone had high diagnostic accuracy for identifying AD among individuals with cognitive symptoms in primary and secondary care using predefined cutoff values. Future studies should evaluate how the use of blood tests for these biomarkers influences clinical care.