Manual Reading Research Articles

Perspectives of Primary Care Clinicians on the Diagnosis and Treatment of Pediatric Hypertension.

The purpose of this study was to contextualize the challenges of diagnosing and managing pediatric hypertension (pHTN) in federally qualified health centers. We conducted a survey among primary care clinicians (N = 72) who treat children (3-17 years old) in a national network of health centers. Clinicians reported practices of blood pressure (BP) measurement, barriers to diagnosis and management of pHTN, and use of population health tools. Most clinicians (83%) used electronic devices to measure BP, only 49% used manual BP readings for follow-up measurements, and more than half measured BP at each encounter. The highest-rated barrier to pHTN management was lack of comfort with antihypertensive medications (71% of respondents). Few clinicians (10%) had used population health tools, but most (78%) indicated they would like to use them for pHTN. These results offer clinician-level insights regarding implementation of the pHTN guideline in pediatric primary care settings.

An optimized segmentation convolutional neural network with dynamic energy loss function for 3D reconstruction of lumbar spine MR images

3D reconstruction for lumbar spine based on segmentation of Magnetic Resonance (MR) images is meaningful for diagnosis of degenerative lumbar spine diseases. However, spine MR images with unbalanced pixel distribution often cause the segmentation performance of Convolutional Neural Network (CNN) reduced. Designing a composite loss function for CNN is an effective way to enhance the segmentation capacity, yet composition loss values with fixed weight may still cause underfitting in CNN training. In this study, we designed a composite loss function with a dynamic weight, called Dynamic Energy Loss, for spine MR images segmentation. In our loss function, the weight percentage of different loss values could be dynamically adjusted during training, thus CNN could fast converge in earlier training stage and focus on detail learning in the later stage. Two datasets were used in control experiments, and the U-net CNN model with our proposed loss function achieved superior performance with Dice similarity coefficient values of 0.9484 and 0.8284 respectively, which were also verified by the Pearson correlation, Bland-Altman, and intra-class correlation coefficient analysis. Furthermore, to improve the 3D reconstruction based on the segmentation results, we proposed a filling algorithm to generate contextually related slices by computing the pixel-level difference between adjacent slices of segmented images, which could enhance the structural information of tissues between slices, and improve the performance of 3D lumbar spine model rendering. Our methods could help radiologists to build a 3D lumbar spine graphical model accurately for diagnosis while reducing burden of manual image reading.

The value of artificial intelligence in the diagnosis of lung cancer: A systematic review and meta-analysis.

Lung cancer is a common malignant tumor disease with high clinical disability and death rates. Currently, lung cancer diagnosis mainly relies on manual pathology section analysis, but the low efficiency and subjective nature of manual film reading can lead to certain misdiagnoses and omissions. With the continuous development of science and technology, artificial intelligence (AI) has been gradually applied to imaging diagnosis. Although there are reports on AI-assisted lung cancer diagnosis, there are still problems such as small sample size and untimely data updates. Therefore, in this study, a large amount of recent data was included, and meta-analysis was used to evaluate the value of AI for lung cancer diagnosis. With the help of STATA16.0, the value of AI-assisted lung cancer diagnosis was assessed by specificity, sensitivity, negative likelihood ratio, positive likelihood ratio, diagnostic ratio, and plotting the working characteristic curves of subjects. Meta-regression and subgroup analysis were used to investigate the value of AI-assisted lung cancer diagnosis. The results of the meta-analysis showed that the combined sensitivity of the AI-aided diagnosis system for lung cancer diagnosis was 0.87 [95% CI (0.82, 0.90)], specificity was 0.87 [95% CI (0.82, 0.91)] (CI stands for confidence interval.), the missed diagnosis rate was 13%, the misdiagnosis rate was 13%, the positive likelihood ratio was 6.5 [95% CI (4.6, 9.3)], the negative likelihood ratio was 0.15 [95% CI (0.11, 0.21)], a diagnostic ratio of 43 [95% CI (24, 76)] and a sum of area under the combined subject operating characteristic (SROC) curve of 0.93 [95% CI (0.91, 0.95)]. Based on the results, the AI-assisted diagnostic system for CT (Computerized Tomography), imaging has considerable diagnostic accuracy for lung cancer diagnosis, which is of significant value for lung cancer diagnosis and has greater feasibility of realizing the extension application in the field of clinical diagnosis.

A Novel Object Detection Method of Pointer Meter Based on Improved YOLOv4-Tiny

Pointer meters have been widely used in industrial field due to their strong stability; it is an important issue to be able to accurately read the meter. At present, patrol robots with computer vision function are often used to detect and read meters in some situations that are not suitable for manual reading of the meter. However, existing object detection algorithms are often misread and miss detection due to factors such as lighting, shooting angles, and complex background environments. To address these problems, this paper designs a YOLOv4-Tiny-based pointer meter detection model named pointer meter detection-YOLO (PMD-YOLO) for the goal of practical applications. Firstly, to reduce weight of the model and ensure the accuracy of object detection, a feature extraction network named GhostNet with a channel attention mechanism is implemented in YOLOv4-Tiny. Then, to enhance feature extraction ability of small- and medium-sized targets, an improved receptive field block (RFB) module is added after the backbone network, and a convolutional block attention module (CBAM) is introduced into the feature pyramid network (FPN). Finally, the FPN is optimized to improve the feature utilization, which further improves the detection accuracy. In order to verify the effectiveness and superiority of the PMD-YOLO proposed in this paper, the PMD-YOLO is used for experimental research on the constructed dataset of the pointer meter, and the target detection algorithms such as Faster region convolutional neural network (RCNN), YOLOv4, YOLOv4-Tiny, and YOLOv5-s are compared under the same conditions. The experimental results show that the mean average precision of the PMD-YOLO is 97.82%, which is significantly higher than the above algorithms. The weight of the PMD-YOLO is 9.38 M, which is significantly lower than the above algorithms. Therefore, the PMD-YOLO not only has high detection accuracy, but can also reduce the weight of the model and can meet the requirements of practical applications.

An interpretable transformer network for the retinal disease classification using optical coherence tomography

Retinal illnesses such as age-related macular degeneration and diabetic macular edema will lead to irreversible blindness. With optical coherence tomography (OCT), doctors are able to see cross-sections of the retinal layers and provide patients with a diagnosis. Manual reading of OCT images is time-consuming, labor-intensive and even error-prone. Computer-aided diagnosis algorithms improve efficiency by automatically analyzing and diagnosing retinal OCT images. However, the accuracy and interpretability of these algorithms can be further improved through effective feature extraction, loss optimization and visualization analysis. In this paper, we propose an interpretable Swin-Poly Transformer network for performing automatically retinal OCT image classification. By shifting the window partition, the Swin-Poly Transformer constructs connections between neighboring non-overlapping windows in the previous layer and thus has the flexibility to model multi-scale features. Besides, the Swin-Poly Transformer modifies the importance of polynomial bases to refine cross entropy for better retinal OCT image classification. In addition, the proposed method also provides confidence score maps, assisting medical practitioners to understand the models’ decision-making process. Experiments in OCT2017 and OCT-C8 reveal that the proposed method outperforms both the convolutional neural network approach and ViT, with an accuracy of 99.80% and an AUC of 99.99%.

Component segmentation of engineering drawings using Graph Convolutional Networks

We present a data-driven framework to automate the vectorization and machine interpretation of 2D engineering part drawings. In industrial settings, most manufacturing engineers still rely on manual reads to identify the topological and manufacturing requirements from drawings submitted by designers. The interpretation process is laborious and time-consuming, which severely inhibits the efficiency of part quotation and manufacturing tasks. While recent advances in image-based computer vision methods have demonstrated great potential in interpreting natural images through semantic segmentation approaches, the application of such methods in parsing engineering technical drawings into semantically accurate components remains a significant challenge. The severe pixel sparsity in engineering drawings also restricts the effective featurization of image-based data-driven methods. To overcome these challenges, we propose a deep learning based framework that predicts the semantic type of each vectorized component. Taking a raster image as input, we vectorize all components through thinning, stroke tracing, and cubic bezier fitting. Then a graph of such components is generated based on the connectivity between the components. Finally, a graph convolutional neural network is trained on this graph data to identify the semantic type of each component. We test our framework in the context of semantic segmentation of text, dimension and, contour components in engineering drawings. Results show that our method yields the best performance compared to recent image-based, and graph-based segmentation methods.

Deep learning based detection of enlarged perivascular spaces on brain MRI

Deep learning has been demonstrated effective in many neuroimaging applications. However, in many scenarios, the number of imaging sequences capturing information related to small vessel disease lesions is insufficient to support data-driven techniques. Additionally, cohort-based studies may not always have the optimal or essential imaging sequences for accurate lesion detection. Therefore, it is necessary to determine which imaging sequences are crucial for precise detection. This study introduces a deep learning framework to detect enlarged perivascular spaces (ePVS) and aims to find the optimal combination of MRI sequences for deep learning-based quantification. We implemented an effective lightweight U-Net adapted for ePVS detection and comprehensively investigated different combinations of information from SWI, FLAIR, T1-weighted (T1w), and T2-weighted (T2w) MRI sequences. The experimental results showed that T2w MRI is the most important for accurate ePVS detection, and the incorporation of SWI, FLAIR and T1w MRI in the deep neural network had minor improvements in accuracy and resulted in the highest sensitivity and precision (sensitivity = 0.82, precision = 0.83). The proposed method achieved comparable accuracy at a minimal time cost compared to manual reading. The proposed automated pipeline enables robust and time-efficient readings of ePVS from MR scans and demonstrates the importance of T2w MRI for ePVS detection and the potential benefits of using multimodal images. Furthermore, the model provides whole-brain maps of ePVS, enabling a better understanding of their clinical correlates compared to the clinical rating methods within only a couple of brain regions.

Worldwide Overview and Country Differences in Metaverse Research: A Bibliometric Analysis

As a research topic integrating various subjects and technologies, Metaverse research has been a global concern in recent years. This study explores the hotspots and frontiers of academic research on the Metaverse based on a bibliometric analysis from 2012 to 2021. A keyword retrieval dataset related to Metaverse research was constructed based on expert consultation and manual reading of the literature, retrieving articles and conference papers from the Scopus database. Critical points in Metaverse research are represented in terms of research scale, keyword co-occurrence networks, keyword citation bursts, and international collaborative networks with the application of VOSviewer and CiteSpace’s bibliometric visualization software. The results indicate that Metaverse research is experiencing rapid growth, with countries/regions increasing their production at varying speeds. The results also indicate the three most prolific countries, the United States, China and Germany, for comparison, showing the leading topic as virtual reality in Metaverse research, and we find that there are differences in topic clustering and hotspot evolution among the three countries over the past decade. By determining the current research status and the overall development path of the Metaverse field, the paper intends to provide a reference for the future research development and technical application of the Metaverse.

Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy

Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis. To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time. A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet. The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s. Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

Experimental Study on Oil Colour Grading Based on Uniform Colour Space

Though the Lovibond colorimetric method is effective for determining oil colour, it is a visual comparison method which relies on manual visual reading. As a result, this method is vulnerable to the influence of subjective factors of testers and is of low accuracy. In this paper, the original index of oil colour grading based on Lovibond colour space is changed to the index of oil colour grading based on uniform colour space, and a new method is proposed to determine oil colour by spectrophotometry. The experimental results show that there is a strong correlation between Lovibond red value and the chroma index a*, and a strong correlation between Lovibond yellow value and the chroma index b*. So the method greatly improves the detection efficiency and avoids a series of disadvantages of the visual method.

Internet of Things (IoT)-Based Environmental Monitoring and Control System for Home-Based Mushroom Cultivation

The control and monitoring of the environmental conditions in mushroom cultivation has been a challenge in the mushroom industry. Currently, research has been conducted to implement successful remote environmental monitoring, or, in some cases, remote environmental control, yet there is not yet a combination of both these systems providing live stream images or video. As a result, this research aimed to design and develop an Internet of things (IoT)-based environmental control and monitoring system for mushroom cultivation, whereby the growth conditions of the mushrooms, such as temperature, humidity, light intensity, and soil moisture level, are remotely monitored and controlled through a mobile and web application. Users would be able to visualize the growth of the mushroom remotely by video and images through the Internet. The respective sensors are implemented into the mushroom cultivation process and connected to the NodeMCU microcontroller, which collects and transfers the data to the cloud server, enabling remote access at any time through the end device with internet connection. The control algorithm regulates the equipment within the cultivational chamber autonomously, based on feedback from the sensors, in order to retain the optimum environment for the cultivation of mushrooms. The sensors were tested and compared with manual readings to ensure their accuracy. The implementation of IoT toward mushroom cultivation would greatly contribute to the advancement of the current mushroom industry which still applies the traditional cultivation approach.

GSM Based Electricity Meter with Instant Billing System

The GSM-based electricity meter with an instant billing system is a project designed to provide an efficient and convenient method for monitoring and billing electricity consumption. This system utilizes the Global System for Mobile communication (GSM) technology to enable remote monitoring and control of electricity meters. The main objective of this project is to overcome the limitations of traditional electricity metering systems, such as manual meter reading and delayed billing processes. By integrating GSM technology, the system enables real-time communication between the electricity meter and the utility provider, allowing for instant meter readings and billing calculations. The proposed system consists of three main components: the GSM-based electricity meter, a central server, and a user interface. The GSM-based electricity meter is installed at the consumer's location and is equipped with a GSM module, which enables it to transmit meter readings to the central server. The central server receives the meter readings from multiple electricity meters and performs billing calculations based on predefined tariff rates. The server also stores the consumption data for future reference and generates instant bills for each consumer. These bills can be sent to the consumer's mobile phone via SMS or accessed through a web-based user interface. The user interface provides consumers with access to their consumption data, billing information, and payment options. Consumers can view their current and historical electricity usage, monitor their bills, and make payments through various payment gateways integrated into the system. The GSM-based electricity meter with an instant billing system offers several advantages over traditional metering systems. It eliminates the need for manual meter reading, reduces billing errors and delays, and provides consumers with real-time information about their electricity consumption. Additionally, it enables utility providers to optimize their billing processes and improve overall customer satisfaction.

Behavior of fiber reinforced polymer laminates strengthening prestressed concrete beams

Pre-stressed concrete constructions' service life may be extended considerably by using fibre reinforced polymer (FRP) reinforcement. It is necessary to have knowledge of the real performance of the strengthened members in order to deploy the technology properly. Determining the static response of pre-stressed concrete beams with externally bonded fiber-reinforced polymer is the main objective of this work. A total of 14 beams of 3 m long, 150 mm × 250 mm cross-sectional beams were cast and put to the test in the lab. Twelve other beams had Glass Fiber Reinforced Polymer laminates added to their soffits to strengthen them, while the other two post-tensioned beams that weren't bonded functioned as reference beams. Three distinct GFRP laminates of two different thicknesses (3 mm and 5 mm) were used to reinforce seven M 35 concrete beams. The strengthened beams were put to the test with loads that increased monotonically as manual readings were collected. The remaining seven M60 concrete beams were reinforced using three different GFRP laminates of two different thicknesses 3 mm and 5 mm, and they were put to test with monotonically increasing loads while having hand readings obtained. All of the variables—concrete grade, GFRP laminate type, and GFRP laminate thickness—were assessed. Uni-Directional Cloth, Woven Roving, and Chopped Strand Mat were some of the GFRP laminates with various configurations (UDC). According to strength, stiffness, ductility, the combined action of the concrete and external reinforcement, and associated failure, all the beams that were tested under static stress underwent evaluation. Deflection ductility, yield load, deflection at yield load, ultimate load, and deflection at ultimate load were the main subjects of this work. According to static testing, pre-stressed concrete beams reinforced with externally bonded GFRP laminates have increased strength, flexural stiffness, ductility, and composite action until failure. The experiment's outcomes were discovered to be rather closely connected. Laminates were suggested for pre-stressed concrete beams with and without externally bonded GFRP in order to forecast the crucial performance factors.

Performance characteristics and operational feasibility assessment of a CRISPR based tata MD CHECK diagnostic test for SARS-CoV-2 (COVID-19).

Tata MD CHECK SARS-CoV-2 kit 1.0, a CRISPR based reverse transcription PCR (TMC-CRISPR) test was approved by Indian Council of Medical Research (ICMR) for COVID-19 diagnosis in India. To determine the potential for rapid roll-out of this test, we conducted performance characteristic and an operational feasibility assessment (OFA) at a tertiary care setting. The study was conducted at an ICMR approved COVID-19 RT-PCR laboratory of King Edward Memorial (KEM) hospital, Mumbai, India. The TMC-CRISPR test was evaluated against the gold-standard RT-PCR test using the same RNA sample extracted from fresh and frozen clinical specimens collected from COVID-19 suspects for routine diagnosis. TMC-CRISPR results were determined manually and using the Tata MD CHECK application. An independent agency conducted interviews of relevant laboratory staff and supervisors for OFA. Overall, 2,332 (fresh: 2,121, frozen: 211) clinical specimens were analysed of which, 140 (6%) were detected positive for COVID-19 by TMC-CRISPR compared to 261 (11%) by RT-PCR. Overall sensitivity and specificity of CRISPR was 44% (95% CI: 38.1%-50.1%) and 99% (95% CI: 98.2%-99.1%) respectively when compared to RT-PCR. Discordance between TMC-CRISPR and RT-PCR results increased with increasing Ct values and corresponding decreasing viral load (range: <20% to >85%). In the OFA, all participants indicated no additional requirements of training to set up RT PCR. However, extra post-PCR steps such as setting up the CRISPR reaction and handling of detection strips were time consuming and required special training. No significant difference was observed between manual and mobile app-based readings. However, issues such as erroneous results, difficulty in interpretation of faint bands, internet connectivity, data safety and security were highlighted as challenges with the app-based readings. The evaluated version-Tata MD CHECK SARS-CoV-2 kit 1.0 of TMC-CRISPR test cannot be considered as an alternative to the RT-PCR. There is a definite scope for improvement in this assay.

Research and Application of Automatic Crude Oil Metering System

At present, China’s crude oil metering still adopts manual reading (temperature, pressure and flow), manual compensation and correction methods. The workload is heavy, and the calculation results are easy to make mistakes and difficult to manage. In order to change this situation, this paper studies and proposes an automatic compensation calculation method for crude oil metering, and develops an automatic metering and management system for crude oil. The system has the functions of automatic collection and storage of on-site data (temperature, pressure and flow), offline metering, online metering, real-time monitoring of metering process flow, query and analysis of historical data, etc., which greatly reduces the workload of workers. At the same time, through the analysis of the system uncertainty and the comparative analysis of the field experimental data, the accuracy of the automatic metering system is verified, which provides a theoretical support for the system parameter selection and operation.

Physiological Challenges of Space Travel and Ground-Based Simulation Possibilities for Monitoring Brain Circulatory Changes: A Rheoencephalography Study

The functional integrity of brain perfusion and oxygen transport profoundly determines mental performance during military flight missions and spaceflight. Presently, at the selection phase of pilot candidates, there are no screening methods to evaluate cerebral circulation and its autonomous regulation (AR), meanwhile the pilot information processing capacity could be insufficient in dangerous flight situations with high mental workload or during high “head-to-foot” G loads. On-board ISS (International Space Station) and during deep-space missions circulatory changes can be evolved in the opposite direction due to the microgravity: blood shift toward the head-neck region can increase ICP (Intracranial Pressure) and tenfold increase of carbon-dioxide concentration can provoke complaints and disturbances in eye and brain blood circulation (Space Associated Neuro-Ocular Syndrome – SANS). The alteration of brain perfusion dynamics and oxygen utilisation was investigated on the head-down tilting table (HDT) test and in the hypobaric (low-pressure) chamber. We registered the brain regional pulse wave changes by the bioimpedance (Rheoencephalography – REG) on 19 volunteers in rest and after the breath-holding manoeuvre. We found that during the head-down tilt (HDT) position, the amplitude of the second peak of the REG pulse wave increased, like the ICP pulse wave, being an unfavourable sign for intracranial pressure increase in clinical cases. Manual readings resulted in significant differences during HDT between the female (P = 0.0007) and male (P &lt; 0.0001) groups. With automated analysis, the increase in REG P2 wave was significant, and the ratio was 4/5 (80%) for women and 10/14 (71%) for men. The newly written automatic program script was able to detect this in 92% of the cases. The calculated values detected the state of cerebral circulatory autoregulation and the identity between the male and female groups. Based on this result and previous REG correlation studies, it can be concluded that REG could be used to monitor fighter pilots, astronauts, and neurocritical care patients in real-time as emergency alert in the transitory cessation of brain perfusion.

342. Multicenter Evaluation of Fosfomycin MIC Results for Enterobacterales Using EUCAST V11 Breakpoints (i.v. and oral for uncomplicated UTI only, E. coli) on MicroScan Dried Gram Negative MIC Panels

Abstract Background EUCAST V11 fosfomycin breakpoints for Enterobacterales (i.v. and oral for uncomplicated UTI only, E. coli) were evaluated against data from a multicenter clinical study on a MicroScan Dried Gram Negative MIC (MSDGN) Panel. MIC results were compared to results obtained with agar dilution reference prepared according to CLSI methodology. Methods A total of 344 Gram negative clinical isolates including 191 Enterobacterales were tested using the turbidity and Prompt® methods of inoculation during the efficacy phase at three clinical sites. An evaluation was conducted by comparing MIC values obtained using the MSDGN panels to MICs utilizing the CLSI agar dilution reference. MSDGN panels were incubated at 35 ± 1°C and read on the WalkAway System, the autoSCAN-4 instrument, and read visually at 16-20 hours. Agar dilution plates were prepared according to CLSI methodology, incubated for 16-20 hours and read visually. EUCAST v11.0 fosfomycin breakpoints (mg/L) used for interpretation of MIC results were: i.v. for Enterobacterales ≤ 32 S, &amp;gt; 32 R and oral for uncomplicated UTI only, E. coli ≤ 8 S, &amp;gt; 8 R. Results Essential agreement, categorical agreement and categorical errors were calculated compared to MIC results from agar dilution plates. Results for all efficacy isolates with turbidity inoculation and manual read are found in Table 1. Table 1- Results Conclusion This multicenter study showed that fosfomycin MIC results for i.v. for Enterobacterales and E. coli (oral, for uncomplicated UTI only) obtained with the MSDGN panel correlate well with MICs obtained using CLSI agar dilution reference using EUCAST interpretive criteria. © 2022 Beckman Coulter. All rights reserved. All other trademarks are the property of their respective owners. Beckman Coulter, the stylized logo, and the Beckman Coulter product and service marks mentioned herein are trademarks or registered trademarks of Beckman Coulter, Inc. in the United States and other countries. Disclosures Omai Garner, PhD, Beckman Coulter, Inc.: Clinical trial data collection funded by Beckman Coulter, Inc. Amanda Harrington, PhD, Beckman Coulter, Inc.: Clinical trial data collection funded by Beckman Coulter, Inc.|bioMeriuex/BioFire: Grant/Research Support Sharon DesJarlais, BS, Beckman Coulter, Inc.: Clinical trial data collection funded by Beckman Coulter, Inc. Maria Traczewski, BS, Beckman Coulter, Inc.: Clinical trial data collection funded by Beckman Coulter, Inc. Denise Beasley, BS, Beckman Coulter, Inc.: Clinical trial data collection funded by Beckman Coulter, Inc. Jose Diaz, BS, Beckman Coulter, Inc.: Employee of Beckman Coulter Regina Brookman, BS, Beckman Coulter, Inc.: Employee of Beckman Coulter Zabrina Lockett, PhD, Beckman Coulter, Inc.: Employee of Beckman Coulter Jennifer Chau, PhD, Beckman Coulter, Inc.: Employee of Beckman Coulter.

Application of deep learning ultrasound imaging in monitoring bone healing after fracture surgery

ObjectiveUltrasound imaging can be used to monitor bone healing after fracture. It has the advantages of simplicity, rapidity, non-radiation, and real-time dynamic observation of fracture healing. It is increasingly valued and developed in clinical applications. Deep learning is an essential branch of artificial intelligence widely used in the medical field. MethodsAfter fracture surgery, 134 patients were selected for ultrasonic imaging at 2 weeks, 4 weeks, 8 weeks, and 12 weeks after surgery. Among them, 104 patients were selected for ultrasonic imaging to establish a prediction model for ultrasonic deep learning, and then 30 patients were used for imaging to verify and improve the model. Finally, 30 patients were selected for ultrasonic imaging and X-ray imaging at 2 weeks, 4 weeks, 8 weeks, and 12 weeks after fracture surgery for the same patient; test the ultrasonic imaging prediction model, compare the ultrasonic imaging and X-ray imaging manual reading, and evaluate the ultrasonic imaging prediction model by accuracy, loss curve, F1 score value, roc curve, AUC value, etc. ResultsThe accuracy of the ultrasonic imaging deep learning prediction model in the test set was 0.73. In the test set, the predicted AUC values for 2 weeks, 4 weeks, 8 weeks, and 12 weeks after fracture surgery were 0.82, 0.90, 0.86, and 0.67, respectively. The accuracy of ultrasonic imaging manual film reading was 0.7, and the AUC values for the four periods were 0.76, 0.81,0.81, and 0.86, respectively. X-ray imaging manual film reading accuracy was 0.7, and the AUC values for the four periods were 0.86, 0.76, 0.81, and 0.84, respectively. ConclusionBased on the artificial intelligence framework, a deep learning prediction model is constructed by preprocessing the ultrasonic imaging after fracture surgery to predict fracture healing, and its application value is discussed. The prediction model of ultrasonic imaging based on deep learning can be used as an effective monitoring method for bone healing after fracture surgery.

The Potential Threat of Vertical Transmission in Methicillin-Resistant Staphylococcus Aureus Infection: A Systematic Review 2022.

This systematic review paper aimed to assess and analyze the prevalence of maternal colonization of Staphylococcus aureus (S. aureus) also known as methicillin-sensitive Staphylococcus aureus (MSSA) and methicillin-resistant Staphylococcus aureus (MRSA) in the peripartum period and its significance on vertical transmission to the neonate and if it is a potential threat to the health of newborns. For this, multiple databases, such as PubMed, MEDLINE, ScienceDirect, and the database of Elsevier, were used to scout for relevant articles, and results were reported adhering to the principles set by Preferred Items for Systematic reviews and Meta-Analysis (PRISMA) guidelines 2020. A specific medical subject headings (MeSH) criterion was designed to search for relevant publications on PubMed. A total of 26 articles were finally selected after a meticulous screening process, including detailed inclusion and exclusion criteria, manual reading of titles and abstracts, and availability of accessible full-text articles. A few articles were also selected after going through the citations section of the initially selected papers. Quality appraisal was done on the selected publications. Maternal colonization of S. aureus is determined to be highly prevalentwith the hypothesis that nasal colonization had higher rates than recto-vaginal sites. Increasing maternal age, history of vaginitis, and multiparity were the most common risk factors for MRSA and MSSA colonization. Premature babies were at the highest risk of MRSA colonization. Breast milk is also a risk factor for neonatal MRSA transmission. Through this systematic review, we concluded that although the rate of vertical transmission of MRSA is lower than that of MSSA, we felt that it held significance as neonates with the bug have poor outcomes due to skin and soft tissue infections and there is spread of MRSA to other neonates in the wardsand spread to siblings in cases of triplets and quadruplets and even death due to potential MRSA sepsis. Women in Africa and China had high prevalence rates of MRSA and S. aureus which can probably be attributed to a lack of access to adequate healthcare facilities. We recommend screening with regular recto-vaginal swabs and nasal swabs especially in regions with a high burden of MRSA to be performed at regular intervals after confirmation of pregnancy, as prevention and screening are effective to avoid serious complications.

Design of Automatic Management System of Electric Power Marketing Charges and Accounts Based on Robot Process Automation

In the automation construction of marketing charge accounts in power supply enterprises, the key is the automation system of electric energy measurement. It covers all levels of measurement points and collection terminals in the whole network, and integrates measurement management, analysis, monitoring and information collection. The traditional electricity charge management of electric power enterprises is the process of manual meter reading, accounting and charging. Meter readers go to each customer every month to read the meter according to the meter reading time and meter reading card, record the number of electric energy meters on the meter reading card, and then copy the data of the meter reading card on the accounting card. Manual meter reading can't meet the current demand. Therefore, this paper will study the automatic management of electric power marketing charges based on RPA (Robot process automation), and build an automatic management system of electric power marketing charges. Through the comparative analysis of experimental data, the experimental results of the response accuracy of different systems show that this system is still more advantageous, and the accuracy of this system is the highest, with an average accuracy of 81.59%. However, the accuracy of reference method and reference method are 62.72% and 46.95% respectively. A perfect charging system based on RPA can not only improve the service level and corporate image of power supply companies, but also improve the management level of power supply companies, thus improving the economic benefits of enterprises.