characteristic area
Recently Published Documents


TOTAL DOCUMENTS

53
(FIVE YEARS 35)

H-INDEX

7
(FIVE YEARS 3)

2021 ◽  
Vol 7 ◽  
pp. e822
Author(s):  
Zhisheng Yang ◽  
Jinyong Cheng

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.


Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000013211
Author(s):  
Yan Li ◽  
Suzanne E. Schindler ◽  
James G. Bollinger ◽  
Vitaliy Ovod ◽  
Kwasi G Mawuenyega ◽  
...  

Objective:To determine the diagnostic accuracy of a plasma Aβ42/Aβ40 assay in classifying amyloid PET status across global research studies using samples collected by multiple centers that utilize different blood collection and processing protocols.Methods:Plasma samples (n=465) were obtained from three large Alzheimer’s Disease (AD) research cohorts in the US (n=182), Australia (n=183), and Sweden (n=100). Plasma Aβ42/Aβ40 was measured by a high precision immunoprecipitation mass spectrometry (IPMS) assay and compared to the reference standards of amyloid PET and CSF Aβ42/Aβ40.Results:In the combined cohort of 465 participants, plasma Aβ42/Aβ40 had good concordance with amyloid PET status (Receiver Operating Characteristic Area Under the Curve [AUC] of 0.84, 95% confidence interval [CI] 0.80-0.87); concordance improved with the inclusion of APOE ε4 status (AUC 0.88, 95% CI 0.85-0.91). The AUC of plasma Aβ42/Aβ40 with CSF amyloid status was 0.85 (95% CI 0.78-0.91) and improved to 0.93 (95% CI 0.89-0.97) with APOE ε4 status. These findings were consistent across the three cohorts, despite differences in protocols. Further, the assay performed similarly in both cognitively unimpaired and impaired individuals.Conclusions:Plasma Aβ42/Aβ40 is a robust measure for detecting amyloid plaques and can be utilized to aid in the diagnosis of AD, identify those at risk for future dementia due to AD, and improve the diversity of populations enrolled in AD research and clinical trials.Classification of Evidence:This study provides Class II evidence that plasma Aβ42/Aβ40, as measured by a high precision IPMS assay, accurately diagnoses brain amyloidosis in both cognitively unimpaired and impaired research participants.


2021 ◽  
Vol 12 ◽  
Author(s):  
Shun Liao ◽  
Don Ragot ◽  
Sachin Nayyar ◽  
Adrian Suszko ◽  
Zhaolei Zhang ◽  
...  

Focal sources are potential targets for atrial fibrillation (AF) catheter ablation, but they can be time-consuming and challenging to identify when unipolar electrograms (EGM) are numerous and complex. Our aim was to apply deep learning (DL) to raw unipolar EGMs in order to automate putative focal sources detection. We included 78 patients from the Focal Source and Trigger (FaST) randomized controlled trial that evaluated the efficacy of adjunctive FaST ablation compared to pulmonary vein isolation alone in reducing AF recurrence. FaST sites were identified based on manual classification of sustained periodic unipolar QS EGMs over 5-s. All periodic unipolar EGMs were divided into training (n = 10,004) and testing cohorts (n = 3,180). DL was developed using residual convolutional neural network to discriminate between FaST and non-FaST. A gradient-based method was applied to interpret the DL model. DL classified FaST with a receiver operator characteristic area under curve of 0.904 ± 0.010 (cross-validation) and 0.923 ± 0.003 (testing). At a prespecified sensitivity of 90%, the specificity and accuracy were 81.9 and 82.5%, respectively, in detecting FaST. DL had similar performance (sensitivity 78%, specificity 89%) to that of FaST re-classification by cardiologists (sensitivity 78%, specificity 79%). The gradient-based interpretation demonstrated accurate tracking of unipolar QS complexes by select DL convolutional layers. In conclusion, our novel DL model trained on raw unipolar EGMs allowed automated and accurate classification of FaST sites. Performance was similar to FaST re-classification by cardiologists. Future application of DL to classify FaST may improve the efficiency of real-time focal source detection for targeted AF ablation therapy.


Metabolites ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 484
Author(s):  
Isabel Gimeno ◽  
Pablo García‐Manrique ◽  
Susana Carrocera ◽  
Cristina López‐Hidalgo ◽  
Luis Valledor ◽  
...  

In vitro produced (IVP) embryos show large metabolic variability induced by breed, culture conditions, embryonic stage and sex and gamete donors. We hypothesized that the birth potential could be accurately predicted by UHPLC-MS/MS in culture medium (CM) with the discrimination of factors inducing metabolic variation. Day-6 embryos were developed in single CM (modified synthetic oviduct fluid) for 24 h and transferred to recipients as fresh (28 ETs) or frozen/thawed (58 ETs) Day-7 blastocysts. Variability was induced with seven bulls, slaughterhouse oocyte donors, culture conditions (serum + Bovine Serum Albumin [BSA] or BSA alone) prior to single culture embryonic stage records (Day-6: morula, early blastocyst, blastocyst; Day-7: expanding blastocyst; fully expanded blastocysts) and cryopreservation. Retained metabolite signals (6111) were analyzed as a function of pregnancy at Day-40, Day-62 and birth in a combinatorial block study with all fixed factors. We identified 34 accumulated metabolites through 511 blocks, 198 for birth, 166 for Day-62 and 147 for Day-40. The relative abundance of metabolites was higher within blocks from non-pregnant (460) than from pregnant (51) embryos. Taxonomy classified lipids (12 fatty acids and derivatives; 224 blocks), amino acids (12) and derivatives (3) (186 blocks), benzenoids (4; 58 blocks), tri-carboxylic acids (2; 41 blocks) and 5-Hydroxy-l-tryptophan (2 blocks). Some metabolites were effective as single biomarkers in 95 blocks (Receiver Operating Characteristic – Area Under the Curve [ROC-AUC]: 0.700–1.000). In contrast, more accurate predictions within the largest data sets were obtained with combinations of 2, 3 and 4 single metabolites in 206 blocks (ROC-AUC = 0.800–1.000). Pregnancy-prone embryos consumed more amino acids and citric acid, and depleted less lipids and cis-aconitic acid. Big metabolic differences between embryos support efficient pregnancy and birth prediction when analyzed in discriminant conditions.


2021 ◽  
Author(s):  
Bo Cheng ◽  
Wei Xiang ◽  
Ruhui Xue ◽  
Hang Yang ◽  
Laili Zhu

Abstract The new type of coronavirus is called COVID-19. The virus can cause respiratory diseases, accompanied by cough, fever, difficulty breathing, and in severe cases, it can also cause symptoms such as pneumonia. It began to spread at the end of 2019 and has now spread to all parts of the world. The limited test kits and increasing number of cases encourage us to propose a deep learning model that can help radiologists and clinicians use chest X-rays to detect COVID-19 cases and show the diagnostic features of pneumonia. In this study, our methods are: 1) Propose a data enhancement method to increase the diversity of the data set, thereby improving the generalization performance of the network. 2) Using the deep convolutional neural network model DPN-SE, an attention mechanism is added on the basis of the DPN network, which greatly improves the performance of the network. 3) Use the lime interpretable library to mark the X-ray, the characteristic area on the medical image that is helpful for the doctor to make a diagnosis. The model we proposed can obtain better results with the least amount of data preprocessing given limited data. In general, the proposed method and model can effectively become a very useful tool for clinical practitioners and radiologists.


2021 ◽  
Author(s):  
Paul F. Zierep ◽  
Randi Vita ◽  
Nina Blazeska ◽  
Jason A. Greenbaum ◽  
Bjoern Peters ◽  
...  

In-silico methods for the prediction of epitopes can support and improve workflows for vaccine design, antibody production, and disease therapy. So far, the scope of B cell and T cell epitope prediction has been directed exclusively towards peptidic antigens. Nevertheless, various non-peptidic molecular classes can be recognized by immune cells. These compounds have not been systematically studied yet, and prediction approaches are lacking. The ability to predict the epitope activity of non-peptidic compounds could have vast implications; for example, for immunogenic risk assessment of the vast number of drugs and other xenobiotics. Here we present the first general attempt to predict the epitope activity of non-peptidic compounds using the Immune Epitope Database (IEDB) as a source for positive samples. The molecules stored in the Chemical Entities of Biological Interest (ChEBI) database were chosen as background samples. The molecules were clustered into eight homogeneous molecular groups, and classifiers were built for each cluster with the aim of separating the epitopes from the background. Different molecular feature encoding schemes and machine learning models were compared against each other. For those models where a high performance could be achieved based on simple decision rules, the molecular features were then further investigated. Additionally, the findings were used to build a web server that allows for the immunogenic investigation of non-peptidic molecules (http://tools-staging.iedb.org/np_epitope_predictor). The prediction quality was tested with samples from independent evaluation datasets, and the implemented method received noteworthy Receiver Operating Characteristic-Area Under Curve (ROC-AUC) values, ranging from 0.69-0.96 depending on the molecule cluster.


Energies ◽  
2021 ◽  
Vol 14 (10) ◽  
pp. 2960
Author(s):  
Marcus Vinícius Coelho Vieira da Costa ◽  
Osmar Luiz Ferreira de Carvalho ◽  
Alex Gois Orlandi ◽  
Issao Hirata ◽  
Anesmar Olino de Albuquerque ◽  
...  

Brazil is a tropical country with continental dimensions and abundant solar resources that are still underutilized. However, solar energy is one of the most promising renewable sources in the country. The proper inspection of Photovoltaic (PV) solar plants is an issue of great interest for the Brazilian territory’s energy management agency, and advances in computer vision and deep learning allow automatic, periodic, and low-cost monitoring. The present research aims to identify PV solar plants in Brazil using semantic segmentation and a mosaicking approach for large image classification. We compared four architectures (U-net, DeepLabv3+, Pyramid Scene Parsing Network, and Feature Pyramid Network) with four backbones (Efficient-net-b0, Efficient-net-b7, ResNet-50, and ResNet-101). For mosaicking, we evaluated a sliding window with overlapping pixels using different stride values (8, 16, 32, 64, 128, and 256). We found that: (1) the models presented similar results, showing that the most relevant approach is to acquire high-quality labels rather than models in many scenarios; (2) U-net presented slightly better metrics, and the best configuration was U-net with the Efficient-net-b7 encoder (98% overall accuracy, 91% IoU, and 95% F-score); (3) mosaicking progressively increases results (precision-recall and receiver operating characteristic area under the curve) when decreasing the stride value, at the cost of a higher computational cost. The high trends of solar energy growth in Brazil require rapid mapping, and the proposed study provides a promising approach.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Saabah B. Mahbub ◽  
Long T. Nguyen ◽  
Abbas Habibalahi ◽  
Jared M. Campbell ◽  
Ayad G. Anwer ◽  
...  

AbstractOptimally preserved urinary exfoliated renal proximal tubule cells were assessed by multispectral imaging of cell autofluorescence. We demonstrated different multispectral autofluorescence signals in such cells extracted from the urine of patients with healthy or diseased kidneys. Using up to 10 features, we were able to differentiate cells from individuals with heathy kidneys and impaired renal function (indicated by estimated glomerular filtration rate (eGFR) values) with the receiver operating characteristic area under the curve (AUC) of 0.99. Using the same method, we were also able to discriminate such urine cells from patients with and without renal fibrosis on biopsy, where significant differences in multispectral autofluorescence signals (AUC = 0.90) were demonstrated between healthy and diseased patients (p < 0.05). These findings show that multispectral assessment of the cell autofluorescence in urine exfoliated proximal tubule kidney cells has the potential to be developed as a sensitive, non-invasive diagnostic method for CKD.


2021 ◽  
Vol 9 ◽  
Author(s):  
Alireza Arabameri ◽  
Saro Lee ◽  
Subodh Chandra Pal ◽  
Omid Asadi Nalivan ◽  
Asish Saha ◽  
...  

The optimal prediction of land subsidence (LS) is very much difficult because of limitations in proper monitoring techniques, field-base surveys and knowledge related to functioning and behavior of LS. Thus, due to the lack of LS susceptibility maps it is almost impossible to identify LS prone areas and as a result it influences severe economic and human losses. Hence, preparation of LS susceptibility mapping (LSSM) can help to prevent natural and human catastrophes and reduce the economic damages significantly. Machine learning (ML) techniques are becoming increasingly proficient in modeling purpose of such kinds of occurrences and they are increasing used for LSSM. This study compares the performances of single and hybrid ML models to preparation of LSSM for future prediction of performance analysis. In this study, the spatial prediction of LS was assessed using four ML models of maximum entropy (MaxEnt), general linear model (GLM), artificial neural network (ANN) and support vector machine (SVM). Alongside, the possible numbers of novel ensemble models were integrated through the aforementioned four ML models for optimal analysis of LSSM. An inventory LS map was prepared based on the previous occurrences of LS points and the dataset were divvied into 70:30 ratios for training and validating of the modeling process. To identify the robust and best LSSMs, receiver operating characteristic-area under curve (ROC-AUC) curve was employed. The ROC-AUC result indicated that ANN model gives the highest ROC-AUC (0.924) in training accuracy. The highest AUC (0.823) of the LSSMs was determined based on validation datasets identified by SVM followed by ANN-SVM (0.812).


Author(s):  
Jeffrey S Hyams ◽  
Michael Brimacombe ◽  
Yael Haberman ◽  
Thomas Walters ◽  
Greg Gibson ◽  
...  

Abstract Background Develop a clinical and biological predictive model for colectomy risk in children newly diagnosed with ulcerative colitis (UC). Methods This was a multicenter inception cohort study of children (ages 4-17 years) newly diagnosed with UC treated with standardized initial regimens of mesalamine or corticosteroids (CS) depending upon initial disease severity. Therapy escalation to immunomodulators or infliximab was based on predetermined criteria. Patients were phenotyped by clinical activity per the Pediatric Ulcerative Colitis Activity Index (PUCAI), disease extent, endoscopic/histologic severity, and laboratory markers. In addition, RNA sequencing defined pretreatment rectal gene expression and high density DNA genotyping by the Affymetrix UK Biobank Axiom Array. Coprimary outcomes were colectomy over 3 years and time to colectomy. Generalized linear models, Cox proportional hazards multivariate regression modeling, and Kaplan-Meier plots were used. Results Four hundred twenty-eight patients (mean age 13 years) started initial theapy with mesalamine (n = 136), oral CS (n = 144), or intravenous CS (n = 148). Twenty-five (6%) underwent colectomy at ≤1 year, 33 (9%) at ≤2 years, and 35 (13%) at ≤3 years. Further, 32/35 patients who had colectomy failed infliximab. An initial PUCAI ≥ 65 was highly associated with colectomy (P = 0.0001). A logistic regression model predicting colectomy using the PUCAI, hemoglobin, and erythrocyte sedimentation rate had a receiver operating characteristic area under the curve of 0.78 (95% confidence interval [0.73, 0.84]). Addition of a pretreatment rectal gene expression panel reflecting activation of the innate immune system and response to external stimuli and bacteria to the clinical model improved the receiver operating characteristic area under the curve to 0.87 (95% confidence interval [0.82, 0.91]). Conclusions A small group of children newly diagnosed with severe UC still require colectomy despite current therapies. Our gene signature observations suggest additional targets for management of those patients not responding to current medical therapies.


Sign in / Sign up

Export Citation Format

Share Document