Design of a geospatial model applied to Health management / La producción de un modelo geoespacial aplicado a la gestión de la salud / Concepção de um modelo geoespacial aplicado na gestão à saúde

ABSTRACT Objective: To identify geographically the beneficiaries categorized as prone to Type 2 Diabetes Mellitus, using the recognition of patterns in a database of a health plan operator, through data mining. Method: The following steps were developed: the initial step, the information survey. Development, construction of the process of extraction, transformation, and loading of the database. Deployment, presentation of the geographical information through a georeferencing tool. Results: As a result, the mapping of Paraná according to its health care network and the concentration of Type 2 Diabetes Mellitus is presented, enabling the identification of cause-and-effect relationships. Conclusion: It is concluded that the analysis of georeferenced information, linked to health information obtained through the data mining technique, can be an excellent tool for the health management of a health plan operator, contributing to the decision-making process in Health.

RESUMEN Objetivo: Identificar geográficamente a los beneficiarios categorizados como propensos a la enfermedad Diabetes mellitus tipo 2, utilizándose el reconocimiento de patrones en una base de datos de cierta compañía de seguro médico por medio de la minería de datos. Método: Se desarrollaron las siguientes etapas: fase inicial, levantamiento de información. Desarrollo, construcción del proceso de extracción, transformación y carga en la base de datos. Implantación, presentación de la información geográfica mediante la herramienta de georreferenciación. Resultados: Se presenta el mapeo de Paraná (Brasil) con relación a su red asistencial y la concentración de Diabetes mellitus tipo 2, proporcionando la identificación de las relaciones de causa-efecto. Conclusión: Se concluyó que el análisis de las informaciones georreferenciadas, vinculadas a las informaciones de salud obtenidas por la técnica de minería de datos, puede ser una excelente herramienta en la gestión de salud de cierta compañía de seguro médico, lo que contribuye al apoyo a la toma de decisiones en salud.

RESUMO Objetivo: Identificar geograficamente os beneficiários categorizados como propensos à doença Diabetes Mellitus Tipo 2, utilizando o reconhecimento de padrões em uma base de dados de uma operadora de plano de saúde, por meio da mineração de dados. Método: Desenvolveram-se as seguintes etapas: fase inicial, levantamento de informações. Desenvolvimento, construção do processo de extração, transformação e carga do banco de dados. Implantação, apresentação das informações geográficas por meio da ferramenta de georreferenciamento. Resultados: Como resultados, apresenta-se o mapeamento do Paraná em relação a sua rede assistencial e a concentração de Diabetes Mellitus Tipo 2, oportunizando a identificação de relações de causa-efeito. Conclusão: Conclui-se que a análise de informações georreferenciadas, vinculadas às informações de saúde obtidas por meio da técnica de mineração de dados, pode ser um excelente instrumento para a gestão da saúde de uma operadora de plano de saúde, contribuindo para o apoio à tomada de decisões em saúde.

Método de mineração de dados para identificação de câncer de mama baseado na seleção de variáveis / A data mining method for breast cancer identification based on a selection of variables

Na maioria dos países, o câncer de mama entre as mulheres é predominante. Se diagnosticado precocemente, apresenta alta probabilidade de cura. Diversas abordagens baseadas em Estatística foram desenvolvidas para auxiliar na sua detecção precoce. Este artigo apresenta um método para a seleção de variáveis para classificação dos casos em duas classes de resultado, benigno ou maligno, baseado na análise citopatológica de amostras de célula da mama de pacientes. As variáveis são ordenadas de acordo com um novo índice de importância de variáveis que combina os pesos de importância da Análise de Componentes Principais e a variância explicada a partir de cada componente retido. Observações da amostra de treino são categorizadas em duas classes através das ferramentas k-vizinhos mais próximos e Análise Discriminante, seguida pela eliminação da variável com o menor índice de importância. Usa-se o subconjunto com a máxima acurácia para classificar as observações na amostra de teste. Aplicando ao Wisconsin Breast Cancer Database, o método proposto apresentou uma média de 97,77% de acurácia de classificação, retendo uma média de 5,8 variáveis.

In the majority of countries, breast cancer among women is highly prevalent. If diagnosed in the early stages, there is a high probability of a cure. Several statistical-based approaches have been developed to assist in early breast cancer detection. This paper presents a method for selection of variables for the classification of cases into two classes, benign or malignant, based on cytopathological analysis of breast cell samples of patients. The variables are ranked according to a new index of importance of variables that combines the weighting importance of Principal Component Analysis and the explained variance based on each retained component. Observations from the test sample are categorized into two classes using the k-Nearest Neighbor algorithm and Discriminant Analysis, followed by elimination of the variable with the index of lowest importance. The subset with the highest accuracy is used to classify observations in the test sample. When applied to the Wisconsin Breast Cancer Database, the proposed method led to average of 97.77% in classification accuracy while retaining an average of 5.8 variables.

Phenotypic spectrum in uniparental disomy: Low incidence or lack of study.

CONTEXT: Alterations in the human chromosomal complement are expressed phenotypically ranging from (i) normal, via (ii) frequent fetal loss in otherwise normal person, to (iii) sub‑clinical to severe mental retardation and dysmorphism in live births. A subtle and microscopically undetectable chromosomal alteration is uniparental disomy (UPD), which is known to be associated with distinct birth defects as per the chromosome involved and parental origin. UPD can be evident due to imprinted genes and/or activation of recessive mutations. AIMS: The present study comprises of data mining of published UPD cases with a focus on associated phenotypes. The goal was to identify non‑random and recurrent associations between UPD and various genetic conditions, which can possibly indicate the presence of new imprinted genes. SETTINGS AND DESIGN: Data mining was carried out using the homepage “http://www.fish.uniklinikum‑jena.de/ UPD.html,” an online catalog of published cases with UPD. MATERIALS AND METHODS: The UPD cases having normal karyotype and with or without clinical findings were selected to analyze the associated phenotypes for each chromosome, maternal or paternal involved in UPD. RESULTS: Our results revealed many genetic conditions (other than the known UPD syndromes) to be associated with UPD. Even in cases of bad obstetric history as well as normal individuals chance detection of UPD has been reported. CONCLUSIONS: The role of UPD in human genetic disorders needs to be studied by involving larger cohorts of individuals with birth defects as well as normal population. The genetic conditions were scrutinized in terms of inheritance patterns; majority of these were autosomal recessive indicating the role of UPD as an underlying mechanism.

Comorbidity Study on Type 2 Diabetes Mellitus Using Data Mining

BACKGROUND/AIMS: The aim of this study was to analyze comorbidity in patients with type 2 diabetes mellitus (T2DM) by using association rule mining (ARM). METHODS: We used data from patients who visited Keimyung University Dongsan Medical Center from 1996 to 2007. Of 411,414 total patients, T2DM was present in 20,314. The Dx Analyze Tool was developed for data cleansing and data mart construction, and to reveal associations of comorbidity. RESULTS: Eighteen associations reached threshold (support, > or = 3%; confidence, > or = 5%). The highest association was found between T2DM and essential hypertension (support, 17.43%; confidence, 34.86%). Six association rules were found among three comorbid diseases. Among them, essential hypertension was an important node between T2DM and stroke (support, 4.06%; confidence, 8.12%) as well as between T2DM and dyslipidemia (support, 3.44%; confidence, 6.88%). CONCLUSIONS: Essential hypertension plays an important role in the association between T2DM and its comorbid diseases. The Dx Analyze Tool is practical for comorbidity studies that have an enormous clinical database.