Aplicación de sistemas fuzzy para la toma de decisiones del Plan Paso a Paso: análisis de los indicadores para la comuna de Valdivia / Artificial intelligence fuzzy system for the design of confinements during quarantines

BACKGROUND: Different modalities of quarantines were one of the main measures implemented worldwide to avoid the spread of SARS-CoV2 virus. AIM: To analyze and compare retrospectively the implementation of the Step- to-Step plan devised by the Chilean Ministry of Health during the pandemic. To propose a decision-making path based on an artificial intelligence fuzzy system to determine confinements in specific territories. MATERIAL AND METHODS: The Step-to-Step Plan threshold values such hospital network capacity, epidemic spreading, testing and contact tracing capability were modeled using fuzzy numbers and fuzzy rule-based systems. RESULTS: Ministry of Health's decision-making opportuneness were unrelated with the Step-to-Step Plan indicators for deconfinement. Such disagreements undermined epidemiological indicators. CONCLUSIONS: Using an artificial intelligence system could improve decision-making transparency, emergency governance, and risk communication to the population.

Biotechnical system based on fuzzy logic prediction for surgical risk classification using analysis of current-voltage characteristics of acupuncture points / 中西医结合学报

OBJECTIVE@#This study aimed to develop expert fuzzy logic model to assist physicians in the prediction of postoperative complications of prostatic hyperplasia before surgery.@*METHODS@#A method for classification of surgical risks was developed. The effect of rotation of the current-voltage characteristics at biologically active points (acupuncture points) was used for the formation of classifier descriptors. The effect determined reversible and non-reversible changes in electrical resistance at acupuncture points with periodic exposure to a sawtooth probe current. Then, the developed method was tested on the prediction of the success of surgical treatment of benign prostatic hyperplasia.@*RESULTS@#Input descriptors were obtained from collected data including current-voltage characteristics of 5 acupuncture points and composed of 27 arrays feeding in the model. The maximum diagnostic sensitivity of the classifier for the success of a surgical operation in the control sample was 88% and for testing data set prediction accuracy was 97%.@*CONCLUSION@#The use of tuples of current-voltage characteristic descriptors of acupuncture points in the classifiers could be used to predict the success of surgical treatment with satisfactory accuracy. The model can be a valuable tool to support physicians' diagnosis.

Application of fuzzy analytic hierarchy process in risk assessment in medicine related fields / 中华流行病学杂志

Risks exist in medicine related fields, which cannot be defined and quantified precisely. It is necessary to adopt a method for the risk assessment of uncertain and fuzzy phenomenon. This paper summarizes the thinking, procedure, advantage and application of fuzzy analytic hierarchy process in the risk assessment in medicine related fields for the purpose of providing reference for its further application.

Lógica difusa: metodología cuantitativa útil para determinar el consenso entre expertos de ciencias estomatológicas / Fuzzy logic: a useful quantitative methodology to determine consensus among dental science experts

RESUMEN La lógica difusa trata de copiar la forma en que los humanos toman decisiones. Específicamente en el área médica, se utiliza desde hace varios años en estudios aplicados a áreas como: ingeniería biomédica, sistemas expertos, modelos epidemiológicos y sistemas diagnósticos. Se confeccionó un cuestionario para medir la calidad de vida relacionada con la salud oral en adolescentes cubanos; se utilizó la lógica difusa en el proceso de validación por expertos, mediante el software PROCESA_CE (2013). En el nivel de concordancia de los expertos se rechazó la hipótesis nula de que no existe comunidad de preferencia entre ellos, para un nivel de significación de 0,01; esto garantizó, con un 99% de confiabilidad, que es posible hacer valoraciones a partir del consenso de estos expertos. Además, se corroboró la existencia de un consenso de 5 en todos los ítems.

ABSTRACT Fuzzy logic tries to copy the way humans make decisions. It has been used for several years, specifically in the medical field, in studies applied to areas such as biomedical engineering, expert systems, epidemiological models and diagnostic systems. A questionnaire was prepared to measure the quality of life related to oral health in Cuban adolescents; Fuzzy logic was used in the validation process based on expert criteria, using the PROCESA_CE (2013) software. According to expert agreements, the null hypothesis that there is no community of preference among them was rejected, for a significance level of 0.01; this guaranteed, with 99% reliability, that it is possible to make assessments based on their consensuses. In addition, the existence of a consensus of five in all items was corroborated.

Super Resolution of MR Brain Images Using Compressive Sensing and Fuzzy Logical Rules

Abstract The proficiency of image processing is of extreme importance in perceiving and collecting information from the images, which includes the process of changing or interpreting existing images. In medical image processing, imaging with more accuracy plays a crucial role in better diagnosis or for the posterior analysis of treatment. Magnetic Resonance Imaging (MRI) is a medicinal creative tool for studying the internal structures and functionalities of human brain, knee, heart, liver, etc. Typical MR scans are essential now for better diagnosis but, limited resolution that is often inadequate for extracting detailed and reliable information. So, for the super resolution (SR) of MR brain images concepts of compressive sensing (CS) & fuzzy logical rules to improve data quality are proposed in this paper. Usually, reconstruction of an SR image is the formation of high resolution (HR) image which is obtained from one or few low resolution (LR) images. In the proposed method, with the help of compressive sensing a very limited number of images are considered even though it's a challenging task and fuzzy logical rules for a specific membership function are applied to improve the resolution of the image. To assess the performance of the proposal, different metrics are evaluated and achieved better results.

Modelo difuso de madurez de la Información y comunicación como apoyo al enfrentamiento a la Covid 19 / Diffuse model of Information and communication maturity for confronting Covid 19

La información y la comunicación son indispensables en momentos en que la humanidad está enfrentando un nuevo Coronavirus, SARS-Cov2, que ha ocasionado la pandemia denominada COVID-19. Este nuevo evento pone en tensión al sistema de salud de los países, así como las organizaciones de estos. El objetivo es modelar la madurez de la Información y comunicación en el enfrentamiento a la Covid 19. Se diseñó un modelo matemático difuso que tiene como base las normas del control interno relacionado con la Información y la comunicación, apoyado en la Lógica difusa compensatoria. Se tiene un modelo de madurez con seis estados para la Información y comunicación en el sistema de Salud como entidad presupuestada, basada en cuatro elementos: tecnología de la Información y comunicación, sistema de información, calidad de la información, así como responsabilidad y rendición de cuentas. Se resalta su necesidad actual en tiempos de enfrentamiento a la Covid 19(AU)

Information and communication are essential at a time when humanity is facing a new Coronavirus, SARS-Cov2, which has caused the pandemic called COVID-19. This new event puts tension in the health system of all countries, as well as their organizations. The objective is to model the maturity of Information and communication in the confrontation with Covid 19. A fuzzy mathematical model was designed based on the internal control standards related to Information and Communication, supported by the Fuzzy Compensatory Logic. There is a maturity model with six states for Information and Communication in the Health System as a budgeted entity, based on four elements: Information and Communication Technology, Information System, Quality of Information, and Responsibility and Accountability Bill. It is high lightened its current need in times of confrontation with the Covid 19(AU)

Gaze vaselinada para prevenção de lesões por pressão em pessoas com dermatoses imunobolhosas / Vaseline gauze for prevention of pressure injuries in people with immunobullous dermatoses / Gasa con vaselina para la prevención de lesiones por presión en personas con dermatosis inmunobulosa

Objetivo: avaliar a mobilidade do cliente com dermatose imunobolhosa antes e após aplicação do curativo com gaze vaselinada. Método: estudo quase experimental, interinstitucional, com clientes com dermatoses imunobolhosas hospitalizados em um hospital estadual e um hospital federal do Estado do Rio de Janeiro e uma instituição do Mato Grosso do Sul. Utilizou-se a lógica fuzzy para classificar a mobilidade dos sujeitos antes, 24 horas após e uma semana após aplicação do curativo. A pesquisa foi aprovada pelo Comitê de Ética em Pesquisa. Resultados: Incluídos 14 participantes, sendo nove com pênfigo vulgar, dois com pênfigo foliáceo e três com penfigóide bolhoso, entre 27 e 82 anos, predominando 11 mulheres. Após 24 horas, nenhum participante se considerou com baixa mobilidade, sete passaram a mobilidade média, e sete, alta, o que foi mantido uma semana após aplicação do curativo. Conclusão: constatou-se significativo aumento da mobilidade logo nas primeiras 24 horas após aplicação do curativo.

Objective: to assess the mobility of clients with immunobullous dermatoses, before and after applying vaseline gauze dressings. Method: in this quasi-experimental, interinstitutional study of inpatients with immunobullous dermatoses at a state hospital and a federal hospital in Rio de Janeiro State and an institution in Mato Grosso do Sul (Brazil), patient mobility before, 24 hours after, and one week after applying the dressing was classified using fuzzy logic. The study was approved by the research ethics committee. Results: 14 participants, nine with pemphigus vulgaris, two with pemphigus foliaceus, and three with bullous pemphigoid, aged between 27 and 82 years old, and predominantly (11) women. After 24 hours, none of the participants considered their mobility to be poor, seven began to be moderately mobile, and seven were highly mobile, and continued so one week after applying the dressing. Conclusion: mobility increased significant in the first 24 hours after applying the dressing.

Objetivo: evaluar la movilidad de clientes con dermatosis inmunobullosa, antes y después de la aplicación de apósitos de gasa con vaselina. Método: en este estudio cuasi-experimental, interinstitucional de pacientes hospitalizados con dermatosis inmunobullosa en un hospital estatal y un hospital federal en el estado de Río de Janeiro y una institución en Mato Grosso do Sul (Brazil), la movilidad del paciente antes, 24 horas después y una semana después la aplicación del apósito se clasificó mediante lógica difusa. El estudio fue aprobado por el comité de ética en investigación. Resultados: se incluyeron 14 participantes, nueve con pénfigo vulgar, dos con pénfigo foliáceo y tres con penfigoide ampolloso, con edades comprendidas entre 27 y 82 años, y predominantemente mujeres (n=11). Después de 24 horas, ninguno de los participantes consideró que su movilidad fuera pobre, siete comenzaron a ser moderadamente móviles y siete eran altamente móviles, y así continuaron una semana después de la aplicación del apósito. Conclusión: la movilidad aumentó significativamente en las primeras 24 horas después de la aplicación del apósitoconsideraba con baja movilidad, siete comenzaron a tener movilidad media y siete, alta, que se mantuvo una semana después de aplicar el apósito. Conclusión: hubo un aumento significativo en la movilidad en las primeras 24 horas después de aplicar el apósito.

A Fuzzy Approach for Diabetes Mellitus Type 2 Classification

Abstract This paper proposes an automatic fuzzy classification system for glycemic index, which indicates the level of Diabetes Mellitus type 2. Diabetes is a chronic disease occurred when there is deficiency in insulin production or in its action, or both, causing complications. Neuro-fuzzy systems and Decision Trees are used to obtain, respectively, the numerical parameters of the membership functions and the linguistic based rules of the fuzzy classification system. The results goal to categorize the glycemic index into 4 classes: decrease a lot, decrease, stable and increase. Real database from [1] is used and the input attributes of the system are defined. In addition, the proposed automatic fuzzy classification system is compared with an "expert" fuzzy classification system, which is totally modeled using expert knowledge. From linguistic based rules obtained from fuzzy inference process, new scenarios are simulated in order to obtain a larger data set which provides a better evaluation of the classification systems. Results are promising, since they indicate the best treatment - intervention or comparative - for each patient, assisting in the decision-making process of the health care professional.

Fuzzy logic and hospital admission due to respiratory diseases using estimated values by mathematical model / Lógica fuzzy e internações por doenças respiratórias usando dados estimados por modelo matemático

Abstract Hospitalizations due to respiratory diseases generate financial costs for the Health System in addition to social costs. Objective of this study was to develop and validate a fuzzy linguistic model for prediction of hospitalization due to respiratory diseases. We constructed a fuzzy model for prediction of hospitalizations due to pneumonia, bronchitis, bronchiolitis and asthma second exposure to fine particulate matter (PM2.5) in residents of Volta Redonda, RJ, in 2012. The model contains two inputs, PM2.5 and temperature, with three membership functions for each input, and an output with three membership functions for admissions, which were obtained from DATASUS. There were 752 hospitalizations in the period, the average concentration of PM2.5 was 17.1 µg/m3 (SD = 4.4). The model showed a good accuracy with PM2.5, the result was between 90% and 76.5% for lags 1, 2 and 3, a sensitivity of up to 95%. This study provides support for creating executable software with a low investment, along with the use of a portable instrument could allow number of hospital admission due to respiratory diseases and provide support to local health managers. Furthermore, the fuzzy model is very simple and involves low computational costs, an implementation making possible.

Resumo Internações por doenças respiratórias geram custos financeiros para o Sistema de Saúde além de custos sociais. O objetivo deste estudo foi elaborar e validar um modelo linguístico "fuzzy" para previsão do número de internações por doenças respiratórias. Foi construído um modelo "fuzzy" para predição de internações por pneumonias, bronquite, bronquiolite e asma segundo exposição ao material particulado fino (PM2,5) em residentes de Volta Redonda, RJ, em 2012. O modelo contém duas entradas PM2,5 e temperatura, com três funções de pertinência para cada entrada, e uma saída com três funções de pertinência para internações, que foram obtidas do DATASUS. Foram 752 internações no período, a concentração média do PM2,5 foi 17,1 µg/m3 (dp = 4,4). O modelo mostrou uma boa acurácia com PM2,5, o resultado foi entre 90% e 76,5% para os lags 1, 2 e 3, com sensibilidade de até 95%. Este estudo fornece subsídios para a criação de programa executável, que não exige um grande investimento, juntamente com o uso de um instrumento portátil pode permitir uma estimativa do número de internações e prestar apoio aos gestores municipais de saúde. Além disso, o modelo "fuzzy" é muito simples e implica em baixas despesas computacionais, tornando possível uma implementação.

Design of Portable Fuzzy Diagnosis Instrument for ECG Signal Based on Internet of Things / 中国医疗器械杂志

OBJECTIVE@#A method for dynamically collecting and processing ECG signals was designed to obtain classification information of abnormal ECG signals.@*METHODS@#Firstly, the ECG eigenvectors were acquired by real-time acquisition of ECG signals combined with discrete wavelet transform, and then the ECG fuzzy information entropy was calculated. Finally, the Euclidean distance was used to obtain the semantic distance of ECG signals, and the classification information of abnormal signals was obtained.@*RESULTS@#The device could effectively identify abnormal ECG signals on an embedded platform based on the Internet of Things, and improved the diagnosis accuracy of heart diseases.@*CONCLUSIONS@#The fuzzy diagnosis device of ECG signal could accurately classify the abnormal signal and output an online signal classification matrix with a high confidence interval.

Research on the cardiovascular function evaluation system based on noninvasive detection indices / 生物医学工程学杂志

Based on the noninvasive detection indeices and fuzzy mathematics method, this paper studied the noninvasive, convenient and economical cardiovascular health assessment system. The health evaluation index of cardiovascular function was built based on the internationally recognized risk factors of cardiovascular disease and the noninvasive detection index. The weight of 12 indexes was completed by the analytic hierarchy process, and the consistency test was passed. The membership function, evaluation matrix and evaluation model were built by fuzzy mathematics. The introducted methods enhanced the scientificity of the evaluation system. Through the Kappa consistency test, McNemer statistical results ( = 0.995 > 0.05) and Kappa values (Kappa = 0.616, < 0.001) suggest that the comprehensive evaluation results of model in this paper are relatively consistent with the clinical, which is of certain scientific significance for the early detection of cardiovascular diseases.

Cuidados de enfermagem para conforto de pessoas com dermatoses imunobolhosas: avaliação pela lógica fuzzy / Nursing care to comfort people with immunobullous dermatoses: evaluation by fuzzy logic / Cuidados de enfermería para la comodidad de personas con dermatosis inmunoampollares: evaluación por la lógica fuzzy

Objetivos: avaliar se as intervenções propostas na tecnologia de cuidados de enfermagem ao cliente com dermatoses imunobolhosas contribuem para reduzir o desconforto, reconhecer padrões de desconforto antes e após aplicação da tecnologia. Método: aplicação do protocolo de avaliação em 14 clientes hospitalizados em enfermarias de dermatologia do Rio de Janeiro e Mato Grosso do Sul, Brasil. Os cuidados foram realizados mediante diagnósticos identificados e recomendações da tecnologia. A subjetividade em reco¬nhecer padrões de conforto em clientes com doenças raras direcionou o uso da lógica fuzzy em função dos atributos dor, mobilidade, padrão de sono, exposição do corpo/lesões. Aprovado conforme CAAE: 0258.0.228.000-11. Resultados: dos 14 participantes, oito verbalizaram redução da dor após 24 horas. Após uma semana, três declararam maior redução, cinco manutenção e cinco aumento. Conclusão: a análise inferencial fuzzy propiciou avaliar padrões de desconforto, apontando para a veracidade da hipótese de que a tecnologia contribui para promover o conforto da clientela.

Objectives: to evaluate whether interventions proposed in nursing care technology for clients with immunobullous dermatoses contribute to reducing discomfort, and to recognize patterns of discomfort before and after application of the technology. Method: the evaluation protocol was applied to 14 patients hospitalized in dermatology wards in Rio de Janeiro and Mato Grosso do Sul, Brazil, from June 2012 to April 2013. Care was performed by way of identified diagnoses and recommendations in the technology. The role of subjectivity in rec¬ognizing comfort patterns in clients with rare diseases indicated the use of fuzzy logic with attributes of pain, mobility, sleep pattern, and body exposure/lesions. The study was approved under CAAE: 0258.0.228.000-11. Results: of the 14 patients, eight reported diminished pain after 24 hours. After one week, three reported larger reductions; five, no change; and five, increased pain. Conclusion: evaluation of patterns of discomfort by fuzzy inferential analysis supported the hypothesis that the technology contributes to promoting client comfort.

Objetivos: evaluar si las intervenciones propuestas en la tecnología de cuidados de enfermería al cliente con dermatosis inmunoampollares contribuyen a reducir el incómodo; reconocer patrones de incomodidad antes y después de la aplicación de la tecnología. Método: aplica¬ción del protocolo de evaluación en 14 pacientes hospitalizados en enfermerías de dermatología de Río de Janeiro y Mato Grosso do Sul, Brasil, de junio/2012 a abril/2013. Los cuidados se han realizado mediante diagnósticos identificados y recomendaciones de la tecnología. La subjetividad en reconocer patrones de comodidad en pacientes con enfermedades raras dirigió el uso de la lógica fuzzy en función de los atributos dolor, movilidad, patrón de sueño, exposición del cuerpo / lesiones. Aprobado conforme CAAE: 0258.0.228.000-11. Resultados: de los 14, ocho reportaron reducción del dolor después de 24 horas. Tras una semana, tres declararon una mayor reducción, cinco mantu¬vieron y cinco aumentaron. Conclusión: el análisis inferencial fuzzy propició evaluar patrones de incomodidad, señalando la veracidad de la hipótesis de que la tecnología contribuye a promover la comodidad de los pacientes.

Modelos computacionais fuzzy para avaliar efeitos da poluição do ar em crianças / Fuzzy computational models to evaluate the effects of air pollution on children

RESUMO Objetivo: Construir um modelo computacional fuzzy para estimar o número de internações de crianças até 10 anos por doenças respiratórias, com base nos dados de poluentes e fatores climáticos da cidade de São José do Rio Preto, Brasil. Métodos: Foi construído modelo computacional utilizando a lógica fuzzy. O modelo tem 4 entradas, cada uma com 2 funções de pertinência gerando 16 regras, e a saída com 5 funções de pertinência, baseado no método de Mamdani, para estimar a associação entre os poluentes e o número de internações. Os dados de internações, de 2011-2013, foram obtidos no Departamento de Informática do Sistema de Saúde (DATASUS) e os poluentes material particulado (PM10) e dióxido de nitrogênio (NO2), a velocidade do vento e a temperatura foram obtidos pela Companhia Ambiental do Estado de São Paulo (Cetesb). Resultados: Foram internadas 1.161 crianças no período analisado, e a média dos poluentes foi 36 e 51 µg/m3 - PM10 e NO2, respectivamente. Os melhores valores da correlação de Pearson (0,34) e da acurácia avaliada pela curva Receiver Operating Characteristic - ROC (NO2 - 96,7% e PM10 - 90,4%) foram para internações no mesmo dia da exposição. Conclusões: O modelo mostrou-se eficaz na predição do número de internações de crianças, podendo ser utilizado como ferramenta na gestão hospitalar da região estudada.

ABSTRACT Objective: To build a fuzzy computational model to estimate the number of hospitalizations of children aged up to 10 years due to respiratory conditions based on pollutants and climatic factors in the city of São José do Rio Preto, Brazil. Methods: A computational model was constructed using the fuzzy logic. The model has 4 inputs, each with 2 membership functions generating 16 rules, and the output with 5 pertinence functions, based on the Mamdani's method, to estimate the association between the pollutants and the number of hospitalizations. Data from hospitalizations, from 2011-2013, were obtained in DATASUS - and the pollutants Particulate Matter (PM10) and Nitrogen Dioxide (NO2), wind speed and temperature were obtained by the Environmental Company of São Paulo State (Cetesb). Results: A total of 1,161 children were hospitalized in the period and the mean of pollutants was 36 and 51 µg/m3 - PM10 and NO2, respectively. The best values of the Pearson correlation (0.34) and accuracy measured by the Receiver Operating Characteristic (ROC) curve (NO2 - 96.7% and PM10 - 90.4%) were for hospitalizations on the same day of exposure. Conclusions: The model was effective in predicting the number of hospitalizations of children and could be used as a tool in the hospital management of the studied region.

Fuzzy Visa: um modelo de lógica fuzzy para a avaliação de risco da Vigilância Sanitária para inspeção de resíduos de serviços de saúde / Fuzzy Visa: a fuzzy logic model for risk assessment of Health Surveillance for health services waste inspection

Resumo A inspeção sanitária de Gerenciamento de Resíduos de Serviços de Saúde (GRSS) carece de metodologia de trabalho padronizada que proporcione bases seguras de avaliação de risco potencial (RP). O objetivo deste trabalho foi propor um instrumento baseado em lógica fuzzy capaz de padronizar a inspeção e gerar indicadores de controle sanitário. O modelo foi desenvolvido com 18 subsistemas relacionados ao GRSS, que resultaram da aglutinação de elementos identificados na inspeção, como aqueles que interferem na avaliação e permeiam todas as etapas do GRSS. A validação do modelo foi realizada em dez unidades de saúde no Rio de Janeiro, de maio a novembro de 2009. Os resultados obtidos no sistema seguiram os diagnósticos realizados pelos especialistas, mostrando a possibilidade de sistematização e racionalização das avaliações de RP. Esse sistema de apoio à decisão torna mais eficiente a gestão e o planejamento de ações na avaliação do RP.

Abstract The sanitary inspection of Health Services Waste Management (HSWM) lacks a standardized work methodology that provides a secure basis for evaluating potential risk (PR). This study aimed to propose an instrument based on fuzzy logic that could standardize inspection and generate indicators of sanitary control. The model was developed with 18 subsystems related to HSWM obtained from the assembly of elements identified in the inspection as those that interfere with the assessment and permeate all stages of HSWM. The validation of the model was conducted in 10 health establishments in Rio de Janeiro between May to November 2009. The results obtained by this model were consistent with the diagnoses made by experts and clearly indicated the possibility of the systematization and rationalization of PR assessments. This decision support system makes management and planning of actions more efficient in PR evaluation.

Interpretación de saberes ancestrales sobre plantas medicinales con lógica difusa / Interpretation of ancestral knowledge about medicinal plants with fuzzy logic

En el presente trabajo ha sido desarrollado pensando en los saberes ancestrales, que han sido transmitidos de generación en generación en nuestro país, una de ellas es la medicina tradicional con plantas medicinales, ante la cual tienen un papel importante en la solución de un número considerable de problemas inmediatos a la salud. Con base en éste planteamiento, se considera que es importante revalorar el uso y preparación de plantas medicinales, por el cual, el interés principal de ésta investigación es analizar, almacenar e interpretar el conocimiento tradicional de las mismas. El presente prototipo está implementado en base a los relatos del club de personas de la tercera edad de Cotahuma. Con referente a herramientas se utilizó Visual Studio 2010, para el desarrollo de la base de conocimientos, y parte de la interpretación con lógica difusa, a la vez se usó Matlab para la representación de gráficas difusas. El objetivo de la presente tesis era utilizar técnicas de lógica difusa para la interpretación de saberes ancestrales sobre el uso de plantas medicinales para relatos ambiguos y tener una base de conocimientos como repositorio digital. Los resultados alcanzados de la investigación fueron: obtener una nueva interpretación menos ambigua y llegar a una certeza sobre los relatos del caso de estudio, a la vez una base de conocimientos con una variedad de plantas medicinales para su respectivo uso en distintas enfermedades. (AU)

Fuzzy model to estimate the number of hospitalizations for asthma and pneumonia under the effects of air pollution / Modelo fuzzy para estimar o número de internações por asma e pneumonia sob os efeitos da poluição do ar

ABSTRACT OBJECTIVE Predict the number of hospitalizations for asthma and pneumonia associated with exposure to air pollutants in the city of São José dos Campos, São Paulo State. METHODS This is a computational model using fuzzy logic based on Mamdani’s inference method. For the fuzzification of the input variables of particulate matter, ozone, sulfur dioxide and apparent temperature, we considered two relevancy functions for each variable with the linguistic approach: good and bad. For the output variable number of hospitalizations for asthma and pneumonia, we considered five relevancy functions: very low, low, medium, high and very high. DATASUS was our source for the number of hospitalizations in the year 2007 and the result provided by the model was correlated with the actual data of hospitalization with lag from zero to two days. The accuracy of the model was estimated by the ROC curve for each pollutant and in those lags. RESULTS In the year of 2007, 1,710 hospitalizations by pneumonia and asthma were recorded in São José dos Campos, State of São Paulo, with a daily average of 4.9 hospitalizations (SD = 2.9). The model output data showed positive and significant correlation (r = 0.38) with the actual data; the accuracies evaluated for the model were higher for sulfur dioxide in lag 0 and 2 and for particulate matter in lag 1. CONCLUSIONS Fuzzy modeling proved accurate for the pollutant exposure effects and hospitalization for pneumonia and asthma approach.

RESUMO OBJETIVO Prever o número de internações por asma e pneumonia associadas à exposição a poluentes do ar no município em São José dos Campos, estado de São Paulo. MÉTODOS Trata-se de um modelo computacional que utiliza a lógica fuzzy baseado na técnica de inferência de Mamdani. Para a fuzzificação das variáveis de entrada material particulado, ozônio, dióxido de enxofre e temperatura aparente foram consideradas duas funções de pertinência para cada variável com abordagem linguísticas: bom e ruim. Para a variável de saída número internações por asma e pneumonia, foram consideradas cinco funções de pertinências: muito baixo, baixo, médio, alto e muito alto. O número de internações no ano de 2007 foi obtido do Datasus e o resultado fornecido pelo modelo foi correlacionado com os dados reais de internação com defasagem (lag) de zero a dois dias. A acurácia do modelo foi estimada pela curva ROC para cada poluente e nestas defasagens. RESULTADOS No ano de 2007 foram registradas 1.710 internações por pneumonia e asma em São José dos Campos, SP, com média diária de 4,9 internações (dp = 2,9). Os dados de saída do modelo mostraram correlação positiva e significativa (r = 0,38) com os dados reais; as acurácias avaliadas para o modelo foram maiores para o dióxido de enxofre nos lag 0 e 2 e para o material particulado no lag 1. CONCLUSÕES Modelagem fuzzy se mostrou acurada para a abordagem de efeitos da exposição aos poluentes e internação por pneumonia e asma.

Evaluation of the composition effect of harvested coffee in the organoleptic properties of coffee drink / Evaluación del efecto de la composición del café cosechado en las propiedades organolépticas de la bebida de café

Background: The current flourishing of the specialty coffee market has motivated the development of this research on the basis that the harvested coffee fruits are a determining factor in drink quality. Objectives: The aim of this study was to evaluate the effect of the composition of harvested coffee (Coffea arabica L.) regarding the organoleptic quality of the coffee drink for the varieties Caturra and Colombia. Methods: Treatments for the assessed varieties were defined with different percentage compositions of coffee fruits M1 (100R), M2 (80R, 13OV, 7SR), M3 (60R, 26OV, 12SR, 2UR) and the control M4, which included fruits in different ripening stages, ripe (R), overripe (OV), semi-ripe (SR) and unripe (UR), in different proportions in experimental units of 10 kg of harvested coffee. The experimental design envisaged 3 rounds (repetitions) of harvest. The harvested coffee was classified manually according to its ripening stage using a previously developed scale based on colorimetry and recording the degrees Brix of 50 fruits in each ripening stage. The standardized wet processing method was carried out; a Q Grader cupping panel of five members was used for the sensory analysis of the coffee drink. Results: The results showed that for the variety Caturra statistical differences in cup quality between treatments were not found, whereas for the variety Colombia, treatments M1 and M3 showed similar behavior, with statistically significant differences regarding M2 and M4. Finally, the mathematical modeling obtained to predict the cup score depending on the coffee ripening stages composition, counted with coefficients of determination R2 of 0.946 and 0.852 with an error of 1.40 and 1.03% for the varieties Caturra and Colombia, respectively. Conclusions: The model developed with fuzzy logic and validated with information from other farms, presented an error of less than 2% in the estimation of the cup as a function of the ripening stages composition of the coffee varieties Caturra and Colombia.

Antecedentes: El progreso en el mercado de los cafés especiales, ha motivado el desarrollo de la presente investigación tomando como base que los frutos de café cosechados son un factor determinante en la calidad de la bebida. Objetivo: El objetivo del estudio fue la evaluación del efecto de la composición del café (Coffea arabica L.) cosechado respecto a la calidad organoléptica de la bebida para las variedades Caturra y Colombia. Métodos:, se definieron los tratamientos (composiciones en porcentaje) de café cereza M1 (100M), M2 (80M, 13SM, 7P), M3 (60M, 26SM, 12P, 2V) y testigo M4, las cuales contemplan para los estados de maduración maduro (M), sobremaduro (SM), pintón (P) y verde (V) en proporciones diferentes en unidades experimentales de 10 kg de café cereza. El diseño experimental contempló 3 pases (replicas) de cosecha. Una vez cosechado al café se realizó la clasificación manual de los estados de maduración con ayuda de una escala previamente elaborada, así como la verificación objetiva por colorimetría y el registro de los grados Brix para 50 frutos en cada estado de maduración. Se realizó un proceso de beneficio húmedo estandarizado; se utilizó un panel de catación Q Grader de cinco integrantes para el análisis sensorial de la bebida. Un análisis de varianza fue empleado para comparar los resultados y se usó lógica difusa para elaborar un modelo matemático predictivo de la calidad en taza en las dos variedades. Resultados: Los resultados mostraron que para la variedad Caturra no se encontraron diferencias estadísticas de calidad en taza entre los tratamientos, mientras que para variedad Colombia los tratamientos M1 y M3 presentaron igual efecto con diferencias estadísticas significativas respecto a M2 y M4. Finalmente, el modelamiento matemático obtenido para predecir la puntuación de la taza en función de la composición de los estados de maduración del café, contó con coeficientes de determinación R2 de 0,946 y 0,852 con errores de 1,40 y 1,03% en variedad Caturra y variedad Colombia, respectivamente. Conclusiones: El modelo desarrollado con lógica difusa validado con información de otras fincas presentó un error menor al 2% en la estimación de la taza en función de la composición de los estados de maduración del café variedad Caturra y Colombia.

analysis of gene expression variations in lymphoma, using a fuzzy classification model

Introduction: Cancer is a major cause of mortality in the modern world, and one of the most important health problems in societies. During recent years, research on cancer as a system biology disease is focused on molecular differences between cancer cells and healthy cells. Most of the proposed methods for classifying cancer using gene expression data act as black boxes and lack biological interpretability. The goal of this study is to design an interpretable fuzzy model for classifying gene expression data of Lymphoma cancer

Method: In this research, the investigated microarray contained 45 samples of lymphoma. Total number of genes was 4026 samples. At first, we offer a hybrid approach to reduce the data dimension for detecting genes involved in lymphoma cancer. In lymphoma microarray, six out of 4029 genes were selected. Then, a fuzzy interpretable classifier was presented for classification of data. Fuzzy inference was performed using two rules which had the highest scores. Weka3.6.9 software was used to reduce the features and the fuzzy classifier model was implemented in MATLAB R2010a. Results of this study were assessed by two measures of accuracy and precision

Results: In pre-processing stage, in order to classify gene expression data of Lymphoma, six out of 4026 genes were identified as cancer-causing genes, and then the fuzzy classifier model was applied on the obtained data. The accuracy of the results of classification was 96 percent using 10 rules with the highest scores and that using 2 rules with the highest scores was about 98 percent

Conclusion: In the proposed approach, for the first time, a fully fuzzy method named a minimal rule fuzzy classification [MRFC] was introduced for extracting fuzzy rules with biological interpretability and meaning extraction from gene expression data. Among the most outstanding features of this method is the ability of extracting a small set of rules to interpret effective gene expression in cancer patients. Another result of this approach is successfully addressing the problem of disproportion between the number of samples and genes in microarrays with the proposed Filter-Wrapper Feature Selection method [FWFS]

Systematic Review of Data Mining Applications in Patient-Centered Mobile-Based Information Systems / 대한의료정보학회지

OBJECTIVES: Smartphones represent a promising technology for patient-centered healthcare. It is claimed that data mining techniques have improved mobile apps to address patients’ needs at subgroup and individual levels. This study reviewed the current literature regarding data mining applications in patient-centered mobile-based information systems. METHODS: We systematically searched PubMed, Scopus, and Web of Science for original studies reported from 2014 to 2016. After screening 226 records at the title/abstract level, the full texts of 92 relevant papers were retrieved and checked against inclusion criteria. Finally, 30 papers were included in this study and reviewed. RESULTS: Data mining techniques have been reported in development of mobile health apps for three main purposes: data analysis for follow-up and monitoring, early diagnosis and detection for screening purpose, classification/prediction of outcomes, and risk calculation (n = 27); data collection (n = 3); and provision of recommendations (n = 2). The most accurate and frequently applied data mining method was support vector machine; however, decision tree has shown superior performance to enhance mobile apps applied for patients’ self-management. CONCLUSIONS: Embedded data-mining-based feature in mobile apps, such as case detection, prediction/classification, risk estimation, or collection of patient data, particularly during self-management, would save, apply, and analyze patient data during and after care. More intelligent methods, such as artificial neural networks, fuzzy logic, and genetic algorithms, and even the hybrid methods may result in more patients-centered recommendations, providing education, guidance, alerts, and awareness of personalized output.

A computer-aided diagnostic system for kidney disease

BACKGROUND: Disease diagnosis is complicated since patients may demonstrate similar symptoms but physician may diagnose different diseases. There are a few number of investigations aimed to create a fuzzy expert system, as a computer aided system for disease diagnosis. METHODS: In this research, a cross-sectional descriptive study conducted in a kidney clinic in Tehran, Iran in 2012. Medical diagnosis fuzzy rules applied, and a set of symptoms related to the set of considered diseases defined. The input case to be diagnosed defined by assigning a fuzzy value to each symptom and then three physicians asked about each suspected diseases. Then comments of those three physicians summarized for each disease. The fuzzy inference applied to obtain a decision fuzzy set for each disease, and crisp decision values attained to determine the certainty of existence for each disease. RESULTS: Results indicated that, in the diagnosis of seven cases of kidney disease by examining 21 indicators using fuzzy expert system, kidney stone disease with 63% certainty was the most probable, renal tubular was at the lowest level with 15%, and other kidney diseases were at the other levels. The most remarkable finding of this study was that results of kidney disease diagnosis (e.g., kidney stone) via fuzzy expert system were fully compatible with those of kidney physicians. CONCLUSION: The proposed fuzzy expert system is a valid, reliable, and flexible instrument to diagnose several typical input cases. The developed system decreases the effort of initial physical checking and manual feeding of input symptoms.