Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 25.688
Filtrar
1.
Washington, D.C.; OPS; 2020-07-02. (OPS/EIH/IS/COVID-19/20-0007).
en Español | PAHO-IRIS | ID: phr-52440

RESUMEN

Los modelos predictivos son útiles para estimar el número de casos y de muertes por la COVID-19; los recursos necesarios, como las camas de hospital y de UCI; y la demanda de suministros, como la de equipos de protección personal (EPP). Dado que los modelos predictivos para la COVID-19 deben basarse en situaciones y datos subyacentes que cambian rápidamente, los resultados que producen pueden cambiar repetidamente a medida que se actualizan y revisan los datos. No obstante, los modelos predictivos tienen interés y pueden aportar perspectivas que son cruciales para los responsables de las políticas. Es importante que conozcamos los puntos fuertes y las limitaciones de los modelos predictivos para usarlos de forma juiciosa como elementos de apoyo y herramientas de referencia para la planificación y la actuación en torno a la COVID-19.


Asunto(s)
Infecciones por Coronavirus , Coronavirus , Tecnología de la Información , Telemedicina , Informática en Salud Pública , Redes Neurales de la Computación
2.
Khirurgiia (Mosk) ; (5): 42-48, 2020.
Artículo en Ruso | MEDLINE | ID: mdl-32500688

RESUMEN

OBJECTIVE: To estimate the possibility of diagnosis of malignant pleural effusion using convolutional neural networks of facies images of pleural exudates obtained by the method of wedge-shaped dehydration. MATERIAL AND METHODS: We studied 163 images of pleural fluid facies obtained by wedge-shaped dehydration in patients with various pleural effusions (10 nosological groups). Recognition and analysis were carried out using convolutional neural network. The images were divided into two groups - malignant effusion (n=65; 40%) and other diseases (n=98; 60%). RESULTS: There were 131 photos selected for further investigation after pre-processing of images by eliminating defective ones, turning them into black and white format, cleaning of 'noise', cutting out the facies. Then the images were standardized. The method of rigid transformations with rotation for every 10 degrees was used. As a result, their number increased up to 4,585. Self-taught neural network analyzed the images of facies independently by separation of the fragments consisting of black and white dots and comparison of them with each other. Self-teaching and training of each neural network were ensured by random sampling of 80% of images from the initial sample. Then the remaining 20% of the images were used as a control sample to assess the possibilities of recognition pleural effusion cause. Four options of convolutional neural networks were used. An accuracy of cancer detection ranged from 82% to 95.6%, benign diseases - from 84% to 94.7%. The neural network with the highest sensitivity was chosen. CONCLUSION: Automated image analysis system of pleural effusion facies using convolutional neural network ensured an accuracy of diagnosis of malignant pleural effusion in 95,6% of cases and other diseases in 90% of cases. The method is simple, efficient, cheap and reagentless.


Asunto(s)
Exudados y Transudados/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador , Redes Neurales de la Computación , Derrame Pleural Maligno/diagnóstico por imagen , Humanos , Reproducibilidad de los Resultados , Sensibilidad y Especificidad
3.
Medicine (Baltimore) ; 99(22): e20316, 2020 May 29.
Artículo en Inglés | MEDLINE | ID: mdl-32481403

RESUMEN

Stomachache is not only disease name of Traditional Chinese medicine (TCM) but also the clinical symptom. It is a common and multiple diseases. TCM has its particular advantage in clinical treatment of stomachache. Syndrome differentiation is an important concept in TCM practice. The therapeutic process is virtually a nonlinear mapping process from clinical symptom to syndrome diagnosis with processing and seeking rules from mass data. Artificial neutral network has strong learning ability for nonlinear relationship. Artificial neutral network has been widely used to TCM area where the multiple factors, multilevel, nonlinear problem accompanied by a large number of optimization exist.We present an original experimental method to apply the improved third-order convergence LM algorithm to intelligent syndrome differentiation for the first time, and compare the predicted ability of Levenberg-Marquardt (LM) algorithm and the improved third-order convergence LM algorithm in syndrome differentiation.In this study, 2436 cases of stomachache electronic medical data from hospital information system, and then the real world data were normalized and standardized. Afterwards, LM algorithm and the improved third-order convergence LM algorithm were used to build the Back Propagation (BP) neural network model for intelligent syndrome differentiation of stomachache on Matlab, respectively. Finally, the differentiation performance of the 2 models was tested and analyzed.The testing results showed that the improved third-order convergence LM algorithm model has better average prediction and diagnosis accuracy, especially in predicting "liver-stomach disharmony" and "stomach yang deficiency", is above 95%.By effectively using the self-learning and auto-update ability of the BP neural network, the intelligent syndrome differentiation model of TCM can fully approach the real side of syndrome differentiation, and shows excellent predicted ability of syndrome differentiation.


Asunto(s)
Dolor Abdominal/diagnóstico , Medicina China Tradicional/métodos , Redes Neurales de la Computación , Gastropatías/diagnóstico , Dolor Abdominal/fisiopatología , Algoritmos , Diagnóstico Diferencial , Humanos , Gastropatías/fisiopatología
4.
Lancet Haematol ; 7(7): e541-e550, 2020 Jul.
Artículo en Inglés | MEDLINE | ID: mdl-32589980

RESUMEN

Machine learning is a branch of computer science and statistics that generates predictive or descriptive models by learning from training data rather than by being rigidly programmed. It has attracted substantial attention for its many applications in medicine, both as a catalyst for research and as a means of improving clinical care across the cycle of diagnosis, prognosis, and treatment of disease. These applications include the management of haematological malignancy, in which machine learning has created inroads in pathology, radiology, genomics, and the analysis of electronic health record data. As computational power becomes cheaper and the tools for implementing machine learning become increasingly democratised, it is likely to become increasingly integrated into the research and practice landscape of haematology. As such, machine learning merits understanding and attention from researchers and clinicians alike. This narrative Review describes important concepts in machine learning for unfamiliar readers, details machine learning's current applications in haematological malignancy, and summarises important concepts for clinicians to be aware of when appraising research that uses machine learning.


Asunto(s)
Neoplasias Hematológicas , Aprendizaje Automático , Algoritmos , Humanos , Redes Neurales de la Computación
5.
Artículo en Inglés | MEDLINE | ID: mdl-32545581

RESUMEN

Prediction of the COVID-19 incidence rate is a matter of global importance, particularly in the United States. As of 4 June 2020, more than 1.8 million confirmed cases and over 108 thousand deaths have been reported in this country. Few studies have examined nationwide modeling of COVID-19 incidence in the United States particularly using machine-learning algorithms. Thus, we collected and prepared a database of 57 candidate explanatory variables to examine the performance of multilayer perceptron (MLP) neural network in predicting the cumulative COVID-19 incidence rates across the continental United States. Our results indicated that a single-hidden-layer MLP could explain almost 65% of the correlation with ground truth for the holdout samples. Sensitivity analysis conducted on this model showed that the age-adjusted mortality rates of ischemic heart disease, pancreatic cancer, and leukemia, together with two socioeconomic and environmental factors (median household income and total precipitation), are among the most substantial factors for predicting COVID-19 incidence rates. Moreover, results of the logistic regression model indicated that these variables could explain the presence/absence of the hotspots of disease incidence that were identified by Getis-Ord Gi* (p < 0.05) in a geographic information system environment. The findings may provide useful insights for public health decision makers regarding the influence of potential risk factors associated with the COVID-19 incidence at the county level.


Asunto(s)
Infecciones por Coronavirus/epidemiología , Redes Neurales de la Computación , Neumonía Viral/epidemiología , Algoritmos , Betacoronavirus , Sistemas de Información Geográfica , Humanos , Incidencia , Modelos Logísticos , Aprendizaje Automático , Modelos Estadísticos , Pandemias , Salud Pública , Factores de Riesgo , Análisis Espacial , Estados Unidos/epidemiología
6.
Comput Math Methods Med ; 2020: 5714714, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32565882

RESUMEN

Coronavirus (COVID-19) is a highly infectious disease that has captured the attention of the worldwide public. Modeling of such diseases can be extremely important in the prediction of their impact. While classic, statistical, modeling can provide satisfactory models, it can also fail to comprehend the intricacies contained within the data. In this paper, authors use a publicly available dataset, containing information on infected, recovered, and deceased patients in 406 locations over 51 days (22nd January 2020 to 12th March 2020). This dataset, intended to be a time-series dataset, is transformed into a regression dataset and used in training a multilayer perceptron (MLP) artificial neural network (ANN). The aim of training is to achieve a worldwide model of the maximal number of patients across all locations in each time unit. Hyperparameters of the MLP are varied using a grid search algorithm, with a total of 5376 hyperparameter combinations. Using those combinations, a total of 48384 ANNs are trained (16128 for each patient group-deceased, recovered, and infected), and each model is evaluated using the coefficient of determination (R2). Cross-validation is performed using K-fold algorithm with 5-folds. Best models achieved consists of 4 hidden layers with 4 neurons in each of those layers, and use a ReLU activation function, with R2 scores of 0.98599 for confirmed, 0.99429 for deceased, and 0.97941 for recovered patient models. When cross-validation is performed, these scores drop to 0.94 for confirmed, 0.781 for recovered, and 0.986 for deceased patient models, showing high robustness of the deceased patient model, good robustness for confirmed, and low robustness for recovered patient model.


Asunto(s)
Infecciones por Coronavirus/transmisión , Modelos Biológicos , Redes Neurales de la Computación , Neumonía Viral/transmisión , Algoritmos , Biología Computacional , Infecciones por Coronavirus/epidemiología , Bases de Datos Factuales , Humanos , Conceptos Matemáticos , Pandemias/estadística & datos numéricos , Neumonía Viral/epidemiología , Análisis de Regresión
7.
Zhonghua Wei Chang Wai Ke Za Zhi ; 23(6): 572-577, 2020 Jun 25.
Artículo en Chino | MEDLINE | ID: mdl-32521977

RESUMEN

Objective: To explore the feasibility of using faster regional convolutional neural network (Faster R-CNN) to evaluate the status of circumferential resection margin (CRM) of rectal cancer in the magnetic resonance imaging (MRI). Methods: This study was registered in the Chinese Clinical Trial Registry (ChiCTR-1800017410). Case inclusion criteria: (1) the positive area of CRM was located between the plane of the levator ani, anal canal and peritoneal reflection; (2) rectal malignancy was confirmed by electronic colonoscopy and histopathological examination; (3) positive CRM was confirmed by postoperative pathology or preoperative high-resolution MRI. Exclusion criteria: patients after neoadjuvant therapy, recurrent cancer after surgery, poor quality images, giant tumor with extensive necrosis and tissue degeneration, and rectal tissue construction changes in previous pelvic surgery. According to the above criteria, MRI plain scan images of 350 patients with rectal cancer and positive CRM in The Affiliated Hospital of Qingdao University from July 2016 to June 2019 were collected. The patients were classified by gender and tumor position, and randomly assigned to the training group (300 cases) and the validation group (50 cases) at a ratio of 6:1 by computer random number method. The CRM positive region was identified on the T2WI image using the LabelImg software. The identified training group images were used to iteratively train and optimize parameters of the Faster R-CNN model until the network converged to obtain the best deep learning model. The test set data were used to evaluate the recognition performance of the artificial intelligence platform. The selected indicators included accuracy, sensitivity, positive predictive value, receiver operating characteristic (ROC) curves, areas under the ROC curves (AUC), and the time taken to identify a single image. Results: The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CRM status determined by the trained Faster R-CNN artificial intelligence approach were 0.884, 0.857, 0.898, 0.807, and 0.926, respectively; the AUC was 0.934 (95% CI: 91.3% to 95.4%). The Faster R-CNN model's automatic recognition time for a single image was 0.2 s. Conclusion: The artificial intelligence model based on Faster R-CNN for the identification and segmentation of CRM-positive MRI images of rectal cancer is established, which can complete the risk assessment of CRM-positive areas caused by in-situ tumor invasion and has the application value of preliminary screening.


Asunto(s)
Imagen por Resonancia Magnética/métodos , Márgenes de Escisión , Redes Neurales de la Computación , Neoplasias del Recto/diagnóstico por imagen , Simulación por Computador , Estudios de Factibilidad , Humanos , Modelos Biológicos , Terapia Neoadyuvante , Neoplasias del Recto/patología , Neoplasias del Recto/cirugía , Neoplasias del Recto/terapia , Medición de Riesgo
8.
Phys Eng Sci Med ; 43(2): 635-640, 2020 Jun.
Artículo en Inglés | MEDLINE | ID: mdl-32524445

RESUMEN

In this study, a dataset of X-ray images from patients with common bacterial pneumonia, confirmed Covid-19 disease, and normal incidents, was utilized for the automatic detection of the Coronavirus disease. The aim of the study is to evaluate the performance of state-of-the-art convolutional neural network architectures proposed over the recent years for medical image classification. Specifically, the procedure called Transfer Learning was adopted. With transfer learning, the detection of various abnormalities in small medical image datasets is an achievable target, often yielding remarkable results. The datasets utilized in this experiment are two. Firstly, a collection of 1427 X-ray images including 224 images with confirmed Covid-19 disease, 700 images with confirmed common bacterial pneumonia, and 504 images of normal conditions. Secondly, a dataset including 224 images with confirmed Covid-19 disease, 714 images with confirmed bacterial and viral pneumonia, and 504 images of normal conditions. The data was collected from the available X-ray images on public medical repositories. The results suggest that Deep Learning with X-ray imaging may extract significant biomarkers related to the Covid-19 disease, while the best accuracy, sensitivity, and specificity obtained is 96.78%, 98.66%, and 96.46% respectively. Since by now, all diagnostic tests show failure rates such as to raise concerns, the probability of incorporating X-rays into the diagnosis of the disease could be assessed by the medical community, based on the findings, while more research to evaluate the X-ray approach from different aspects may be conducted.


Asunto(s)
Betacoronavirus , Infecciones por Coronavirus/diagnóstico por imagen , Redes Neurales de la Computación , Neumonía Viral/diagnóstico por imagen , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Bases de Datos Factuales , Aprendizaje Profundo , Humanos , Pandemias , Neumonía Bacteriana/diagnóstico por imagen , Radiografía Torácica
9.
Water Sci Technol ; 81(5): 1090-1098, 2020 Mar.
Artículo en Inglés | MEDLINE | ID: mdl-32541125

RESUMEN

The real time estimation of effluent indices of papermaking wastewater is vital to environmental conservation. Ensemble methods have significant advantages over conventional single models in terms of prediction accuracy. As an ensemble method, multi-grained cascade forest (gcForest) is implemented for the prediction of wastewater indices. Compared with the conventional modeling methods including partial least squares, support vector regression, and artificial neural networks, the gcForest model shows prediction superiority for effluent suspended solid (SSeff) and effluent chemical oxygen demand (CODeff). In terms of SSeff, gcForest achieves the highest correlation coefficient with a value of 0.86 and the lowest root-mean-square error (RMSE) value of 0.41. In comparison with the conventional models, the RMSE value using gcForest is reduced by approximately 46.05% to 50.60%. In terms of CODeff, gcForest achieves the highest correlation coefficient with a value of 0.83 and the lowest root-mean-square error value of 4.05. In comparison with the conventional models, the RMSE value using gcForest is reduced by approximately 10.60% to 18.51%.


Asunto(s)
Eliminación de Residuos Líquidos , Aguas Residuales , Análisis de la Demanda Biológica de Oxígeno , Bosques , Redes Neurales de la Computación
10.
Stud Health Technol Inform ; 270: 203-207, 2020 Jun 16.
Artículo en Inglés | MEDLINE | ID: mdl-32570375

RESUMEN

Radiology reports include various types of clinical information that are used for patient care. Reports are also expected to have secondary uses (e.g., clinical research and the development of decision support systems). For secondary use, it is necessary to extract information from the report and organize it in a structured format. Our goal is to build an application to transform radiology reports written in a free-text form into a structured format. To this end, we propose an end-to-end method that consists of three elements. First, we built a neural network model to extract clinical information from the reports. We experimented on a dataset of chest X-ray reports. Second, we transformed the extracted information into a structured format. Finally, we built a tool that enabled the transformation of terms in reports to standard forms. Through our end-to-end method, we could obtain a structured radiology dataset that was easy to access for secondary use.


Asunto(s)
Procesamiento de Lenguaje Natural , Redes Neurales de la Computación , Sistemas de Información Radiológica , Radiología , Humanos , Informe de Investigación , Programas Informáticos , Escritura
11.
Comput Biol Med ; 121: 103792, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32568675

RESUMEN

The novel coronavirus 2019 (COVID-2019), which first appeared in Wuhan city of China in December 2019, spread rapidly around the world and became a pandemic. It has caused a devastating effect on both daily lives, public health, and the global economy. It is critical to detect the positive cases as early as possible so as to prevent the further spread of this epidemic and to quickly treat affected patients. The need for auxiliary diagnostic tools has increased as there are no accurate automated toolkits available. Recent findings obtained using radiology imaging techniques suggest that such images contain salient information about the COVID-19 virus. Application of advanced artificial intelligence (AI) techniques coupled with radiological imaging can be helpful for the accurate detection of this disease, and can also be assistive to overcome the problem of a lack of specialized physicians in remote villages. In this study, a new model for automatic COVID-19 detection using raw chest X-ray images is presented. The proposed model is developed to provide accurate diagnostics for binary classification (COVID vs. No-Findings) and multi-class classification (COVID vs. No-Findings vs. Pneumonia). Our model produced a classification accuracy of 98.08% for binary classes and 87.02% for multi-class cases. The DarkNet model was used in our study as a classifier for the you only look once (YOLO) real time object detection system. We implemented 17 convolutional layers and introduced different filtering on each layer. Our model (available at (https://github.com/muhammedtalo/COVID-19)) can be employed to assist radiologists in validating their initial screening, and can also be employed via cloud to immediately screen patients.


Asunto(s)
Betacoronavirus , Infecciones por Coronavirus/diagnóstico por imagen , Infecciones por Coronavirus/diagnóstico , Aprendizaje Profundo , Redes Neurales de la Computación , Neumonía Viral/diagnóstico por imagen , Neumonía Viral/diagnóstico , Interpretación de Imagen Radiográfica Asistida por Computador , Biología Computacional , Infecciones por Coronavirus/clasificación , Bases de Datos Factuales , Diagnóstico por Computador , Femenino , Humanos , Pulmón/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Pandemias/clasificación , Neumonía/diagnóstico , Neumonía/diagnóstico por imagen , Neumonía Viral/clasificación
12.
Comput Biol Med ; 121: 103795, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32568676

RESUMEN

Fast diagnostic methods can control and prevent the spread of pandemic diseases like coronavirus disease 2019 (COVID-19) and assist physicians to better manage patients in high workload conditions. Although a laboratory test is the current routine diagnostic tool, it is time-consuming, imposing a high cost and requiring a well-equipped laboratory for analysis. Computed tomography (CT) has thus far become a fast method to diagnose patients with COVID-19. However, the performance of radiologists in diagnosis of COVID-19 was moderate. Accordingly, additional investigations are needed to improve the performance in diagnosing COVID-19. In this study is suggested a rapid and valid method for COVID-19 diagnosis using an artificial intelligence technique based. 1020 CT slices from 108 patients with laboratory proven COVID-19 (the COVID-19 group) and 86 patients with other atypical and viral pneumonia diseases (the non-COVID-19 group) were included. Ten well-known convolutional neural networks were used to distinguish infection of COVID-19 from non-COVID-19 groups: AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xception. Among all networks, the best performance was achieved by ResNet-101 and Xception. ResNet-101 could distinguish COVID-19 from non-COVID-19 cases with an AUC of 0.994 (sensitivity, 100%; specificity, 99.02%; accuracy, 99.51%). Xception achieved an AUC of 0.994 (sensitivity, 98.04%; specificity, 100%; accuracy, 99.02%). However, the performance of the radiologist was moderate with an AUC of 0.873 (sensitivity, 89.21%; specificity, 83.33%; accuracy, 86.27%). ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.


Asunto(s)
Betacoronavirus , Infecciones por Coronavirus/diagnóstico por imagen , Infecciones por Coronavirus/diagnóstico , Aprendizaje Profundo , Redes Neurales de la Computación , Neumonía Viral/diagnóstico por imagen , Neumonía Viral/diagnóstico , Adulto , Anciano , Anciano de 80 o más Años , Inteligencia Artificial , Biología Computacional , Femenino , Humanos , Pulmón/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Pandemias , Neumonía/diagnóstico , Neumonía/diagnóstico por imagen , Interpretación de Imagen Radiográfica Asistida por Computador , Tomografía Computarizada por Rayos X
13.
Ying Yong Sheng Tai Xue Bao ; 31(5): 1525-1534, 2020 May.
Artículo en Chino | MEDLINE | ID: mdl-32530230

RESUMEN

To explore the water consumption characteristics of trees, the thermal dissipation probe technology was used to monitor sap flow of Populus bolleana in east sandy land of Yellow River, from July to November in 2017. Microclimate variables were monitored. We analyzed the diurnal and seasonal variations of water consumption, and proposed the models for water consumption with back propagation neural network (BPNN) and Elman neural network (ENN) based on fuzzy rules. Results showed that the average sap flow rate of P. bolleana was 4.98 g·cm-2·h-1 in growing season (July to October), with solar radiation (Rs), temperature (T), vapor pressure deficit (VPD) and relative humidity (RH) as the main factors affecting sap flow. Due to the influence of meteorological factors, water consumption was characterized by obvious seasonal variation, with that in summer (July-August) being 1.4 times of that in autumn (September-October). BPNN and ENN models based on fuzzy rules were used to simulate water consumption of P. euphratica. The optimal parameter calibration of two models explained more than 80% of the total variation, which indicated that these two models could more accurately simulate water consumption. Compared with the BP neural network model, the simulated results of ENN model showed that the relative error was reduced by 27.0%, RMSE was reduced by 24.3%, Nash-Sutclife efficiency coefficient increased by 67.9%, R2 was higher than 0.80. The ENN model performed better than BPNN model with a higher efficiency and goodness of fitness. ENN model effectively improved the simulating accuracy of water consumption. Therefore, it could be used as an optimal model to estimate water consumption of P. bolleana in east sandy land of Yellow River.


Asunto(s)
Populus , China , Ingestión de Líquidos , Redes Neurales de la Computación , Transpiración de Plantas , Árboles , Agua
14.
Int J Comput Dent ; 23(2): 139-148, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32555767

RESUMEN

Frontal cephalometric radiography (frontal ceph) is one of the important diagnostic methods in orthodontics and maxillofacial surgery. It allows one to determine occlusion anomalies in the transverse and vertical planes and to evaluate the symmetry of the facial skeleton relative to the median plane, including analysis of the position of the jawbone. AIM: The aim of this study was to develop an artificial neural network (ANN) for placing cephalometric points (CPs) on frontal cephs and to compare the accuracy of its performance against humans. MATERIALS AND METHODS: The study included 330 depersonalized frontal cephs: 300 cephs for training ANNs and 30 for research. Each image was imported into the ViSurgery software (Skolkovo, Russia) and the 45 CPs were arranged. The CPs were divided into three groups: 1) precise anatomical landmarks; 2) complex anatomical landmarks; and 3) indistinct anatomical landmarks. Two ANNs were used to improve the accuracy of CP placement. The first ANN solved the problem of multiclass image segmentation, and the second regression ANN was used to correct the predictions of the first ANN. The accuracy of CP placement was compared between the ANN and three groups of doctors: expert, regular, and inexperienced. Then, using the Wilcoxon t test, the hypothesis that an ANN makes fewer or as many errors as doctors in the three groups of points was tested. RESULTS: The deviation was estimated by the mean absolute error (MAE). The MAE for the points placed by the ANN, as compared with the control, was close to the average result for the regular doctor group: 2.87 mm (ANN) and 2.85 mm (regular group); 2.47 mm (expert group), and 3.61 mm (inexperienced group). The results for individual groups of points are presented. On average, the ANN places CPs no less accurately than the regular doctor group in each group of points. However, calculating all points in total, this hypothesis was rejected because the P value was 0.0056. A different result was observed among the inexperienced doctor group. Points from groups 2 and 3, as well as all points in total, were placed more accurately by the ANN (P = 0.9998, 0.2628, and 0.9982, respectively). The exception was group 1, where the points were more accurately placed by the inexperienced doctors (P = 0.0006). CONCLUSION: The results of the present study show that ANNs can achieve accuracy comparable to humans in placing CPs, and in some cases surpass the accuracy of inexperienced doctors (students, residents, graduate students).


Asunto(s)
Redes Neurales de la Computación , Programas Informáticos , Cefalometría , Humanos
15.
Eur J Endocrinol ; 183(1): 41-49, 2020 Jun 01.
Artículo en Inglés | MEDLINE | ID: mdl-32504495

RESUMEN

Objective: Automatic diabetic retinopathy screening system based on neural networks has been used to detect diabetic retinopathy (DR). However, there is no quantitative synthesis of performance of these methods. We aimed to estimate the sensitivity and specificity of neural networks in DR grading. Methods: Medline, Embase, IEEE Xplore, and Cochrane Library were searched up to 23 July 2019. Studies that evaluated performance of neural networks in detection of moderate or worse DR or diabetic macular edema using retinal fundus images with ophthalmologists' judgment as reference standard were included. Two reviewers extracted data independently. Risk of bias of eligible studies was assessed using QUDAS-2 tool. Results: Twenty-four studies involving 235 235 subjects were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed a pooled sensitivity of 91.9% (95% CI: 89.6% to 94.3%) and specificity of 91.3% (95% CI: 89.0% to 93.5%). Subgroup analyses and meta-regression did not provide any statistically significant findings for the heterogeneous diagnostic accuracy in studies with different image resolutions, sample sizes of training sets, architecture of convolutional neural networks, or diagnostic criteria. Conclusions: State-of-the-art neural networks could effectively detect clinical significant DR. To further improve diagnostic accuracy of neural networks, researchers might need to develop new algorithms rather than simply enlarge sample sizes of training sets or optimize image quality.


Asunto(s)
Inteligencia Artificial , Retinopatía Diabética/diagnóstico , Tamizaje Masivo/métodos , Redes Neurales de la Computación , Retinopatía Diabética/patología , Fondo de Ojo , Humanos , Edema Macular/diagnóstico , Sensibilidad y Especificidad
16.
Fa Yi Xue Za Zhi ; 36(2): 210-215, 2020 Apr.
Artículo en Inglés, Chino | MEDLINE | ID: mdl-32530169

RESUMEN

Abstract: Objective To develop a convolutional neural network (CNN) that can identify isokinetic knee exercises moment of force-time diagrams under different levels of efforts. Methods The 200 healthy young volunteers performed concentric isokinetic right knee flexion-extension reciprocating exercises with maximal effort as well as half the effort at angular velocities of 30°/s and 60°/s twice, respectively, with an interval of 45 min. The moment of force-time diagrams were collected. The 200 subjects were randomly divided into the training set (140 subjects) and the testing set (60 subjects). The moment of force-time diagrams from subjects in the training set were used to train CNN model, and then the fully trained model was used to predict types of curves from the testing set. Random sampling of subjects along with subsequent development of models were performed 3 times. Results Under the circumstances of isokinetic knee exercises with maximal effort and half the effort, 2 400 moment of force-time diagrams were produced, respectively. Classification accuracy rates of the CNN models after the 3 trainings were 91.11%, 90.49% and 92.08%, respectively, and the average accuracy rate was 91.23%. Conclusion The CNN models developed in this study have a good effect on differentiating isokinetic moment of force-time diagrams of maximal effort exercises from those made with half the effort, which can contribute to identifying levels of efforts exerted by subjects during isokinetic knee exercises.


Asunto(s)
Articulación de la Rodilla , Músculo Esquelético , Humanos , Rodilla , Contracción Muscular , Redes Neurales de la Computación
17.
J Environ Manage ; 265: 110485, 2020 Jul 01.
Artículo en Inglés | MEDLINE | ID: mdl-32421551

RESUMEN

Across the world, the flood magnitude is expected to increase as well as the damage caused by their occurrence. In this case, the prediction of areas which are highly susceptible to these phenomena becomes very important for the authorities. The present study is focused on the evaluation of flood potential within Trotuș river basin in Romania using six ensemble models created by the combination of Analytical Hierarchy Process (AHP), Certainty Factor (CF) and Weights of Evidence (WOE) on one hand, and Gradient Boosting Trees (GBT) and Multilayer Perceptron (MLP) on the other hand. A number of 12 flood predictors, 172 flood locations and 172 non-flood locations were used. A percentage of 70% of flood and non-flood locations were used as input in models. From the input data, 70% were used as training sample and 30% as validating sample. The highest accuracy was obtained by the MLP-CF model in terms of both training (0.899) and testing (0.889) samples. A percentage between 21.88% and 36.33% of study area is covered with high and very high flood potential. The results validation, performed through the ROC Curve method, highlights that the MLP-CF model provided the most accurate results.


Asunto(s)
Inundaciones , Redes Neurales de la Computación , Algoritmos , Curva ROC , Rumanía
18.
Waste Manag ; 109: 1-9, 2020 May 15.
Artículo en Inglés | MEDLINE | ID: mdl-32361385

RESUMEN

This study investigates an image recognition system for the identification and classification of waste electrical and electronic equipment from photos. Its main purpose is to facilitate information exchange regarding the waste to be collected from individuals or from waste collection points, thereby exploiting the wide acceptance and use of smartphones. To improve waste collection planning, individuals would photograph the waste item and upload the image to the waste collection company server, where it would be recognized and classified automatically. The proposed system can be operated on a server or through a mobile app. A novel method of classification and identification using neural networks is proposed for image analysis: a deep learning convolutional neural network (CNN) was applied to classify the type of e-waste, and a faster region-based convolutional neural network (R-CNN) was used to detect the category and size of the waste equipment in the images. The recognition and classification accuracy of the selected e-waste categories ranged from 90 to 97%. After the size and category of the waste is automatically recognized and classified from the uploaded images, e-waste collection companies can prepare a collection plan by assigning a sufficient number of vehicles and payload capacity for a specific e-waste project.


Asunto(s)
Aprendizaje Profundo , Residuos Electrónicos , Humanos , Redes Neurales de la Computación
19.
Environ Monit Assess ; 192(6): 375, 2020 May 16.
Artículo en Inglés | MEDLINE | ID: mdl-32417970

RESUMEN

Few studies have evaluated the impact of climate change on groundwater resources for a region with no pumping well. Indeed, the uncertainty of pumping wells may undesirably influence the results. Therefore, a region without any pumping well was selected to assess the impact of climate change on the karstic spring flow rates. NASA Earth Exchange Global Daily Downscaled Projections (NEX-GDDP) dataset was used to extract the climatic variables for the present (1961-1990) and future (2021-2050) time periods by two Representative Concentration Pathways (RCPs), i.e., RCP4.5 and RCP8.5, in Lali region, southwest Iran. Although this dataset has been already verified, its output was evaluated for Lali region. Then, the impact of climate change on the discharge of Bibitarkhoun karstic spring was examined by the Artificial Neural Network (ANN). In this regard, if considering the daily data, ANN is not trained satisfactorily, because of the spring's lag time response to the precipitation; if monthly time step is considered, the data would not be adequate. Therefore, the average of some previous days was considered to calculate the variables. The average precipitation is 344, 329, and 324 mm/year and the average temperature is 14.18, 15.98, and 16.3 °C both for the present, future time period under RCP4.5 and future time period under RCP8.5, respectively. The network selected demonstrated no climate change impact on the average of spring discharge. However, the discharge increased by about + 8% in spring and summer and decreased by about - 7% in autumn and winter in the future time period.


Asunto(s)
Cambio Climático , Monitoreo del Ambiente , Manantiales Naturales , Irán , Redes Neurales de la Computación , Estaciones del Año , Movimientos del Agua
20.
BMC Bioinformatics ; 21(1): 213, 2020 May 24.
Artículo en Inglés | MEDLINE | ID: mdl-32448122

RESUMEN

BACKGROUND: Semantic resources such as knowledge bases contains high-quality-structured knowledge and therefore require significant effort from domain experts. Using the resources to reinforce the information retrieval from the unstructured text may further exploit the potentials of such unstructured text resources and their curated knowledge. RESULTS: The paper proposes a novel method that uses a deep neural network model adopting the prior knowledge to improve performance in the automated extraction of biological semantic relations from the scientific literature. The model is based on a recurrent neural network combining the attention mechanism with the semantic resources, i.e., UniProt and BioModels. Our method is evaluated on the BioNLP and BioCreative corpus, a set of manually annotated biological text. The experiments demonstrate that the method outperforms the current state-of-the-art models, and the structured semantic information could improve the result of bio-text-mining. CONCLUSION: The experiment results show that our approach can effectively make use of the external prior knowledge information and improve the performance in the protein-protein interaction extraction task. The method should be able to be generalized for other types of data, although it is validated on biomedical texts.


Asunto(s)
Algoritmos , Atención/fisiología , Bases del Conocimiento , Semántica , Bases de Datos Genéticas , Humanos , Redes Neurales de la Computación , Publicaciones
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA