RESUMO
CONTEXT AND OBJECTIVE:: Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. DESIGN AND SETTING:: Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. METHODS:: After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. RESULTS:: The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. CONCLUSION:: Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.
Assuntos
Algoritmos , Diabetes Mellitus Tipo 2/diagnóstico , Aprendizado de Máquina Supervisionado/normas , Adulto , Idoso , Teorema de Bayes , Brasil , Simulação por Computador/normas , Estudos de Viabilidade , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Redes Neurais de Computação , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
ABSTRACT CONTEXT AND OBJECTIVE: Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. DESIGN AND SETTING: Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. METHODS: After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. RESULTS: The best models were created using artificial neural networks and logistic regression. These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. CONCLUSION: Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.
RESUMO CONTEXTO E OBJETIVO: Diabetes tipo 2 é uma doença crônica associada a graves complicações de saúde, causando grande impacto na saúde global. O objetivo foi desenvolver e validar modelos preditivos para detectar diabetes não diagnosticada utilizando dados do Estudo Longitudinal de Saúde do Adulto (ELSA-Brasil) e comparar o desempenho de diferentes algoritmos de aprendizagem de máquina. TIPO DE ESTUDO E LOCAL: Comparação de algoritmos de aprendizagem de máquina para o desenvolvimento de modelos preditivos utilizando dados do ELSA-Brasil. MÉTODOS: Após selecionar 27 variáveis candidatas a partir da literatura, modelos foram construídos e validados em 4 etapas sequenciais: (i) afinação de parâmetros com validação cruzada (10-fold cross-validation); (ii) seleção automática de variáveis utilizando seleção progressiva, estratégia "wrapper" com quatro algoritmos de aprendizagem de máquina distintos e validação cruzada para avaliar cada subconjunto de variáveis; (iii) estimação de erros dos parâmetros dos modelos com validação cruzada; e (iv) teste de generalização em um conjunto de dados independente. Os modelos foram criados com os seguintes algoritmos de aprendizagem de máquina: regressão logística, redes neurais artificiais, naïve Bayes, K vizinhos mais próximos e floresta aleatória. RESULTADOS: Os melhores modelos foram criados utilizando redes neurais artificiais e regressão logística alcançando, respectivamente, 75,24% e 74,98% de média de área sob a curva na etapa de estimação de erros e 74,17% e 74,41% na etapa de teste de generalização. CONCLUSÃO: A maioria dos modelos preditivos produziu resultados semelhantes e demonstrou a viabilidade de identificar aqueles com maior probabilidade de ter diabetes não diagnosticada com dados clínicos facilmente obtidos.
Assuntos
Humanos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Idoso , Algoritmos , Diabetes Mellitus Tipo 2/diagnóstico , Aprendizado de Máquina Supervisionado/normas , Simulação por Computador/normas , Brasil , Modelos Logísticos , Estudos de Viabilidade , Reprodutibilidade dos Testes , Teorema de Bayes , Sensibilidade e Especificidade , Redes Neurais de ComputaçãoRESUMO
Chronic diseases are an important field to tackle due to increasing healthcare risk factors, including population nutritional habits, lack of physical exercise, and population aging. Diabetes mellitus, hypertension, and obesity currently affect millions of people, and this statistic grows every year and is responsible for numerous deaths everyday. Many of those deaths could be delayed by following a steady monitoring strategy over such a population, which would prevent vital signs from reaching critical stages and providing knowledge for these patients about their health. This paper introduces Mobilicare, a mobile health promotion system designed to: (i) monitor remotely a patient's vital signs in real time; (ii) support a health service in a Healthcare Center; and (iii) allow self-awareness of the disease and improve motivation. Our approach was applied to two distinct chronic patient management programs. The results showed the commitment of elder patients and the contribution of Mobilicare to the maintenance of a patient's health stability.
