Base de dados : LILACS
Pesquisa : G17.035.250 [Categoria DeCS]
Referências encontradas : 213 [refinar]
Mostrando: 1 .. 10   no formato [Detalhado]

página 1 de 22 ir para página                         

  1 / 213 LILACS  
              next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1285723
Autor: Rodrigues, Jonas Almeida; Krois, Joachim; Schwendicke, Falk.
Título: Demystifying artificial intelligence and deep learning in dentistry
Fonte: Braz. oral res. (Online);35:e094, 2021. graf.
Idioma: en.
Projeto: UFRGS.
Resumo: Abstract Artificial intelligence (AI) is a general term used to describe the development of computer systems which can perform tasks that normally require human cognition. Machine learning (ML) is one subfield of AI, where computers learn rules from data, capturing its intrinsic statistical patterns and structures. Neural networks (NNs) have been increasingly employed for ML complex data. The application of multilayered NN is referred to as "deep learning", which has been recently investigated in dentistry. Convolutional neural networks (CNNs) are mainly used for processing large and complex imagery data, as they are able to extract image features like edges, corners, shapes, and macroscopic patterns using layers of filters. CNN algorithms allow to perform tasks like image classification, object detection and segmentation. The literature involving AI in dentistry has increased rapidly, so a methodological guidance for designing, conducting and reporting studies must be rigorously followed, including the improvement of datasets. The limited interaction between the dental field and the technical disciplines, however, remains a hurdle for applicable dental AI. Similarly, dental users must understand why and how AI applications work and decide to appraise their decisions critically. Generalizable and robust AI applications will eventually prove helpful for clinicians and patients alike.
Descritores: Inteligência Artificial
Aprendizado Profundo
-Redes Neurais de Computação
Odontologia
Aprendizado de Máquina
Limites: Humanos
Responsável: BR1.1 - BIREME


  2 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo
Id: biblio-1047206
Autor: Araújo-Filho, José e Arimatéia Batista; Pinto, Ibraim Masciarelli Francisco; Nomura, Cesar Higa.
Título: Inteligência artificial e diagnóstico por imagem - o futuro chegou? / Artificial intelligence and diagnostic imaging - has the future come?
Fonte: Rev. Soc. Cardiol. Estado de Säo Paulo;29(4):346-349, out.-dez. 2019. ilus.
Idioma: pt.
Resumo: Na nova era da Medicina de Precisão, a inteligência artificial (IA) - um conjunto de sistemas e programas que permitem às máquinas serem capazes de executar tarefas que habitual mente exigiriam a participação humana - emerge como ferramenta capaz de criar novas maneiras de analisar as imagens médicas além dos parâmetros morfológicos convencionais. Embora ainda não estejam completamente disponíveis para o uso clínico, essa nova abordagem tem grande potencial de aplicação na prática clínica e de pesquisa médica. A discussão dos conceitos básicos, potenciais aplicações e limitações das novas técnicas de IA no diagnóstico por imagem é importante para a interpretação adequada do potencial efeito que essa tecnologia teria na medicina, contrapondo-se à excessiva ansiedade despertada por abordagens superficiais e apressadas. Este artigo tem por objetivo apresentar uma visão equilibrada e atual sobre o tema, com especial foco no presente e no futuro da imagenologia cardíaca

In the new era of Precision Medicine, artificial intelligence (AI) - a set of systems and programs that enable machines to be able to perform cognitive tasks that would usually require human participation emerges as a tool that can create new ways of analyzing images beyond the conventional morphological parameters. Although not yet ready for clinical use, these tools have a potential effect on clinical and research practice. The discussion of the basic concepts, potential applications and limitations of new AI techniques in imaging diagnosis is important for a balanced interpretation of their results, as opposed to the excessive anxiety recently observed among professionals dealing with the subject. In this brief article, we aim to take a balanced and attentive look on this subject, with special focus on the horizon of modern cardiac imaging
Descritores: Inteligência Artificial
Diagnóstico por Imagem/métodos
-Informática Médica/métodos
Cardiologia
Medicina de Precisão/métodos
Aprendizado de Máquina
Aprendizado Profundo
Responsável: BR44.1 - Serviço de Biblioteca, Documentação Científica e Didática Prof. Dr. Luiz Venere Décourt


  3 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1290267
Autor: dos Santos Martins, Thiago Gonçalves; dos Santos Martins, Diogo Gonçalves; dos Santos Martins, Thomaz Gonçalves; Marinho, Paula; Schor, Paulo.
Título: COVID 19 repercussions in ophthalmology: a narrative review
Fonte: Säo Paulo med. j;139(5):535-542, May 2021. tab, graf.
Idioma: en.
Resumo: BACKGROUND: The new coronavirus of 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread globally and has repercussions within ophthalmological care. It has caused ocular manifestations in some patients, which can spread through eye secretions. OBJECTIVES: The purpose of this review was to summarize the currently available evidence on COVID-19 with regard to its implications for ophthalmology. DESIGN AND SETTING: Narrative review developed by a research group at Universidade Federal de São Paulo (UNIFESP), São Paulo (SP), Brazil, and at Ludwig-Maximilians-Universität, Munich, Germany. METHODS: We searched the literature on the repercussions of COVID-19 within ophthalmological care, using the MEDLINE and LILACS databases, with the keywords "COVID-19", "ophthalmology" and "coronavirus", from January 1, 2020, to March 27, 2021. Clinical trials, meta-analysis, randomized controlled trials, reviews and systematic reviews were identified. RESULTS: We retrieved 884 references, of which 42 were considered eligible for intensive review and critical analysis. Most of the studies selected reported the evidence regarding COVID-19 and its implications for ophthalmology. CONCLUSIONS: Knowledge of eye symptoms and ocular transmission of the virus remains incomplete. New clinical trials with larger numbers of patients may answer these questions in the future. Moreover, positively, implementation of innovative changes in medicine such as telemedicine and artificial intelligence may assist in diagnosing eye diseases and in training and education for students.
Descritores: Oftalmologia
COVID-19
-Brasil
Inteligência Artificial
SARS-CoV-2
Limites: Humanos
Tipo de Publ: Revisão
Metanálise
Responsável: BR1.1 - BIREME


  4 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1001898
Autor: Lapão, Luís Velez.
Título: Artificial intelligence: is it a friend or foe of physicians? / Inteligência artificial: parceira ou inimiga do médico?
Fonte: Einstein (Säo Paulo);17(2):eED4982, 2019.
Idioma: en.
Descritores: Médicos
Inteligência Artificial
-Competência Profissional
Medicina Baseada em Evidências
Educação Médica
Limites: Humanos
Tipo de Publ: Editorial
Responsável: BR1.1 - BIREME


  5 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1133761
Autor: Nistal-Nuño, Beatriz.
Título: A neural network for prediction of risk of nosocomial infection at intensive care units: a didactic preliminary model / Uma rede neural de previsão de riscos de infecção nosocomial em unidades de cuidado intensivo: um modelo preliminar didático
Fonte: Einstein (Säo Paulo);18:eAO5480, 2020. tab, graf.
Idioma: en.
Resumo: ABSTRACT Objective: To propose a preliminary artificial intelligence model, based on artificial neural networks, for predicting the risk of nosocomial infection at intensive care units. Methods: An artificial neural network is designed that employs supervised learning. The generation of the datasets was based on data derived from the Japanese Nosocomial Infection Surveillance system. It is studied how the Java Neural Network Simulator learns to categorize these patients to predict their risk of nosocomial infection. The simulations are performed with several backpropagation learning algorithms and with several groups of parameters, comparing their results through the sum of the squared errors and mean errors per pattern. Results: The backpropagation with momentum algorithm showed better performance than the backpropagation algorithm. The performance improved with the xor. README file parameter values compared to the default parameters. There were no failures in the categorization of the patients into their risk of nosocomial infection. Conclusion: While this model is still based on a synthetic dataset, the excellent performance observed with a small number of patterns suggests that using higher numbers of variables and network layers to analyze larger volumes of data can create powerful artificial neural networks, potentially capable of precisely anticipating nosocomial infection at intensive care units. Using a real database during the simulations has the potential to realize the predictive ability of this model.

RESUMO Objetivo: Propor um modelo preliminar de inteligência artificial, baseado em redes neurais artificiais, para previsão do risco de infecção hospitalar em unidades de cuidado intensivo. Métodos: Foi usada uma rede neural artificial, que utiliza aprendizagem supervisionada. A geração dos conjuntos de dados baseia-se em dados derivados do sistema Japanese Nosocomial Infection Surveillance . Estudamos como o Java Neural Network Simulator aprende a categorizar esses pacientes para prever o respectivo risco de infecção hospitalar. As simulações são realizadas com diferentes algoritmos de aprendizagem por retropropagação e diversos grupos de parâmetros, comparando-se os resultados com base na soma dos erros quadráticos e erros médios por padrão. Resultados: O algoritmo de retropropagação com momentum mostrou desempenho superior ao do algoritmo de retropropagação. O desempenho foi melhor com os valores de parâmetros do arquivo xor. README em comparação aos parâmetros default . Não houve falhas na categorização de pacientes quanto ao respectivo risco de infecção hospitalar. Conclusão: Embora esse modelo se baseie em um conjunto de dados sintéticos, o excelente desempenho observado com um pequeno número de padrões sugere que o uso de números maiores de variáveis e camadas de rede para analisar volumes maiores de dados pode criar redes neurais artificiais poderosas, possivelmente capazes de prever com precisão o risco de infecção hospitalar em unidades de cuidado intensivo. O uso de um banco de dados real durante as simulações torna possível a realização da capacidade preditiva desse modelo.
Descritores: Inteligência Artificial
Infecção Hospitalar
Redes Neurais de Computação
Medição de Risco/métodos
-Algoritmos
APACHE
Unidades de Terapia Intensiva
Limites: Humanos
Responsável: BR1.1 - BIREME


  6 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1142884
Autor: Martins, Thiago Gonçalves dos Santos; Schor, Paulo.
Título: Unpacking the black box / Desembalando a caixa preta
Fonte: Einstein (Säo Paulo);19:eED6037, 2021.
Idioma: en.
Descritores: Algoritmos
Inteligência Artificial
Limites: Humanos
Tipo de Publ: Editorial
Responsável: BR1.1 - BIREME


  7 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1285562
Autor: Pedretti, André; Santini, Mariana; Scolimoski, Josnei; Queiroz, Mauro Henrique Brito de; Toshioka, Frank; Rocha Junior, Eloy de Paula; Pauli Júnior, Nelson de; Yomura, Marcio Takashi; Costa, Clayton Hilgemberg da; Guerra, Fabio Alessandro; Mulinari, Bruna Machado; Grando, Flavio Lori; Mumbelli, Joceleide Dalla Costa; Costa, Cláudio Inácio Almeida; Torres, Germano Lambert; Ramos, Milton Pires.
Título: Robotic Process Automation Extended with Artificial Intelligence Techniques in Power Distribution Utilities
Fonte: Braz. arch. biol. technol;64(spe):e21210217, 2021. tab, graf.
Idioma: en.
Projeto: Companhia Paranaense de Energia.
Resumo: Abstract Robotic Process Automation (RPA) is one of the several important techniques currently available for companies in search of performance improvement. The step forward in RPA is its association with Artificial Intelligence for more skilled robots. This scenario is not different in Power Distribution Utilities, in which a multitude of complex processes must be executed over different data sources. Making such situation even more complex, these processes are frequently regulated and subject to audit by external bodies. However, an old question remains: what should be robotized and what should be done by humans? This paper aims at partially answering the question in the context of data analysis tasks used for making decisions in complex processes. The research development is conducted based on an Artificial Intelligence methodology incorporated into one software robot (RPA) which acquires data automatically, treats and analyzes these data, helping the human professional take decisions in the process. It is applied to a real case process that is important for validating the research. Four approaches are tested in the data analysis, but only two are really used. The robot analyzes a series of information from an energy consumption meter. The detection of possible behavior deviations in the meter data is made by comparison with its data series. The robot is capable of prioritizing the detected occurrences in the energy consumption data, indicating to the human operator the most critical situations that require attention. The association of Artificial Intelligence and RPA is viable and can really apport important benefits to the company and teams, valuing human work and bringing more efficiency to the processes.
Descritores: Robótica/métodos
Inteligência Artificial
Abastecimento de Energia
-Consumo de Energia
Aprendizado de Máquina
Responsável: BR1.1 - BIREME


  8 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo SciELO Brasil
Texto completo
Id: biblio-1278463
Autor: Torres, Norah Nadia Sánchez; Diaz, Valentin Nicolas Silvera; Ando Junior, Oswaldo Hideo; Ledesma, Jorge Javier Gimenez.
Título: Analysis of the technical feasibility of using artificial intelligence for smoothing active power in a photovoltaic system connected to the power system
Fonte: Braz. arch. biol. technol;64(spe):e21210196, 2021. tab, graf.
Idioma: en.
Projeto: Institutional Program Triple Agenda; . Federal University of Integration of Latin America; . CAPES; . CNPq; . ITAI; . P&D COPEL.
Resumo: Abstract Recent technological advances and increased participation of energy systems based on photovoltaic solar energy place this renewable energy source in a prominent position in the current scenario. With the increase in the share of solar photovoltaic systems, the impact of power fluctuations in these sources has worsened, which can affect the quality of electrical energy and the reliability of the electrical power system. Therefore, with the use of energy storage together with control algorithms based on artificial intelligence, it is possible to control and perform power smoothing. In this context, the study presents a technical feasibility study on the use of artificial neural network (ANN) to perform the power smoothing of the photovoltaic system connected to the network. Being studied the performance of a real photovoltaic system operating in conjunction with an ideal energy storage for comparative analysis of the performance of the artificial neural network when the numbers of neurons and layers are modified for different real operating conditions considered as temperature variation, humidity, irradiation, pressure and wind speed, which are considered to be ANN input data. The results obtained point to the feasibility of using ANN, with acceptable precision, for power smoothing. According to the analyzes carried out, it is clear that ANN's with few neurons, the smoothing profile tends to be more accurate when compared to larger amounts of neurons. In the current state of the study, it was not possible to determine a relationship between the variations in the number of neurons with the most accurate results, it is important to note that the development of the curve pointed by the neural network can be influenced by the database. It should be noted that, when ANN exceeds or does not reach the optimal smoothing curve, the storage system compensates for the lack or excess of power, and there is a need for other mechanisms to optimize power smoothing.
Descritores: Energia Solar
Redes Neurais de Computação
Fontes Geradoras de Energia
Sistemas Microeletromecânicos/métodos
-Inteligência Artificial
Estudos de Viabilidade
Responsável: BR1.1 - BIREME


  9 / 213 LILACS  
              first record previous record next record last record
seleciona
para imprimir
Fotocópia
Texto completo
Id: biblio-1251516
Autor: Gómez-Zuleta, Martín Alonso; Cano-Rosales, Diego Fernando; Bravo-Higuera, Diego Fernando; Ruano-Balseca, Josué André; Romero-Castro, Eduardo.
Título: Detección automática de pólipos colorrectales con técnicas de inteligencia artificial / Artificial intelligence techniques for the automatic detection of colorectal polyps
Fonte: Rev. colomb. gastroenterol;36(1):7-17, ene.-mar. 2021. tab, graf.
Idioma: es.
Resumo: Resumen El cáncer colorrectal (CCR) es uno de los tumores malignos con mayor prevalencia en Colombia y el mundo. Estas neoplasias se originan en lesiones adenomatosas o pólipos que deben resecarse para prevenir la enfermedad, lo cual se puede realizar con una colonoscopia. Se ha reportado que durante una colonoscopia se detectan pólipos en el 40 % de los hombres y en el 30 % de las mujeres (hiperplásicos, adenomatosos, serrados, entre otros), y, en promedio, un 25 % de pólipos adenomatosos (principal indicador de calidad en colonoscopia). Sin embargo, estas lesiones no son fáciles de observar por la multiplicidad de puntos ciegos en el colon y por el error humano asociado con el examen. Diferentes investigaciones han reportado que alrededor del 25 % de pólipos colorrectales no son detectados o se pasan por alto durante la colonoscopia y, como consecuencia, el paciente puede tener un cáncer de intervalo. Estas cifras muestran la necesidad de contar con un segundo observador (sistema de inteligencia artificial) que reduzca al mínimo la posibilidad de no detectar estos pólipos y, de este modo, sea posible prevenir al máximo el cáncer de colon. Objetivo: crear un método computacional para la detección automática de pólipos colorrectales usando inteligencia artificial en videos grabados de procedimientos reales de colonoscopia. Metodología: se usaron bases de datos públicas con pólipos colorrectales y una colección de datos construida en un Hospital Universitario. Inicialmente, se normalizan todos los cuadros de los videos para disminuir la alta variabilidad entre bases de datos. Posteriormente, la tarea de detección de pólipos se hace con un método de aprendizaje profundo usando una red neuronal convolucional. Esta red se inicia con pesos aprendidos en millones de imágenes naturales de la base de datos ImageNet. Los pesos de la red se actualizan usando imágenes de colonoscopia, siguiendo la técnica de ajuste fino. Finalmente, la detección de pólipos se realiza asignando a cada cuadro una probabilidad de contener un pólipo y determinando el umbral que define cuando el pólipo se encuentra presente en un cuadro. Resultados: este enfoque fue entrenado y evaluado con 1875 casos recopilados de 5 bases de datos públicas y de la construida en el hospital universitario, que suman aproximadamente 123 046 cuadros. Los resultados obtenidos se compararon con las marcaciones de diferentes expertos en colonoscopia y se obtuvo 0,77 de exactitud, 0,89 de sensibilidad, 0,71 de especificidad y una curva ROC (receiver operating characteristic) de 0,87. Conclusión: este método logra detectar pólipos de manera sobresaliente, superando la alta variabilidad dada por los distintos tipos de lesiones, condiciones diferentes de la luz del colon (asas, pliegues o retracciones) con una sensibilidad muy alta, comparada con un gastroenterólogo experimentado, lo que podría hacer que se disminuya el error humano, el cual es uno de los principales factores que hacen que no se detecte o se escapen los pólipos durante un examen de colonoscopia.

Abstract Colorectal cancer (CRC) is one of the most prevalent malignant tumors worldwide. These neoplasms originate from adenomatous lesions or polyps that must be resected to prevent the development of the disease, and that can be done through a colonoscopy. Polyps are reported during colonoscopy in 40% of men and 30% of women (hyperplastic, adenomatous, serrated, among others), and, on average 25% are adenomatous polyps (the main indicator of quality in colonoscopy). However, these lesions are not easy to visualize because of the multiplicity of blind spots in the colon and human errors associated with the performance of the procedure. Several research works have reported that about 25% of colorectal polyps are overlooked or undetected during colonoscopy, and as a result, the patient may have interval cancer. These figures show the need for a second observer (artificial intelligence system) to reduce the possibility of not detecting polyps and prevent colon cancer as much as possible. Objective: To create a computational method for the automatic detection of colorectal polyps using artificial intelligence using recorded videos of colonoscopy procedures. Methodology: Public databases of colorectal polyps and a data collection constructed in a university hospital were used. Initially, all the frames in the videos were normalized to reduce the high variability between databases. Subsequently, polyps were detected using a deep learning method with a convolutional neural network. This network starts with weights learned from millions of natural images taken from the ImageNET database. Network weights are updated using colonoscopy images, following the fine-tuning technique. Finally, polyps are detected by assigning each box a probability of polyp presence and determining the threshold that defines when the polyp is present in a box. Results: This approach was trained and evaluated with 1 875 cases collected from 5 public databases and the one built in the university hospital, which total approximately 123 046 frames. The results obtained were compared with the markings of different experts in colonoscopy, obtaining 0.77 accuracy, 0.89 sensitivity, 0.71 specificity, and a receiver operating characteristic curve of 0.87. Conclusion: This method detected polyps in an outstanding way, overcoming the high variability caused by the types of lesions and bowel lumen condition (loops, folds or retractions) and obtaining a very high sensitivity compared with an experienced gastroenterologist. This may help reduce the incidence of human error, as it is one of the main factors that cause polyps to not be detected or overlooked during a colonoscopy.
Descritores: Pólipos
Inteligência Artificial
Pólipos Adenomatosos
-Recursos Audiovisuais
Neoplasias Colorretais
Determinação
CYCLAMATESABDOMINAL INJURIES
Limites: Humanos
Tipo de Publ: Estudo Observacional
Responsável: CO354 - Sociedad Colombiana de Gastroenterología


  10 / 213 LILACS  
              first record previous record
seleciona
para imprimir
Fotocópia
Texto completo
Id: biblio-1251515
Autor: Cepeda-Vásquez, Ricardo.
Título: Inteligencia artificial en la detección de pólipos colónicos: qué dicen los estudios / Artificial intelligence in the detection of colonic polyps: what the studies say
Fonte: Rev. colomb. gastroenterol;36(1):2-6, ene.-mar. 2021.
Idioma: es.
Descritores: Inteligência Artificial
Pólipos do Colo
Determinação
Limites: Humanos
Tipo de Publ: Editorial
Responsável: CO354 - Sociedad Colombiana de Gastroenterología



página 1 de 22 ir para página                         
   


Refinar a pesquisa
  Base de dados : Formulário avançado   

    Pesquisar no campo  
1  
2
3
 
           



Search engine: iAH v2.6 powered by WWWISIS

BIREME/OPAS/OMS - Centro Latino-Americano e do Caribe de Informação em Ciências da Saúde