ABSTRACT
Abstract Diabetes mellitus (DM) is a category of metabolic disorders caused by high blood sugar. The DM affects human metabolism, and this disease causes many complications like Heart disease, Neuropathy, Diabetic retinopathy, kidney problems, skin disorder and slow healing. It is therefore essential to predict the presence of DM using an automated diabetes diagnosis system, which can be implemented using machine learning algorithms. A variety of automated diabetes prediction systems have been proposed in previous studies. Even so, the low prediction accuracy of DM prediction systems is a major issue. This proposed work developed a diabetes mellitus prediction system to improve the diabetes mellitus prediction accuracy using Optimized Gaussian Naive Bayes algorithm. This proposed model using the Pima Indians diabetes dataset as an input to build the DM predictive model. The missing values of an input dataset are imputed using regression imputation method. The sequential backward feature elimination method is used in this proposed model for selecting the relevant risk factors of diabetes disease. The proposed machine learning classifier named Optimized Gaussian Naïve Bayes (OGNB) is applied to the selected risk factors to create an enhanced Diabetes diagnostic system which predicts Diabetes in an individual. The performance analysis of this prediction architecture shows that, over other traditional machine learning classifiers, the Optimized Gaussian Naïve Bayes achieves an 81.85% classifier accuracy. This proposed DM prediction system is effective as compared to other diabetes prediction systems found in the literature. According to our experimental study, the OGNB based diabetes mellitus prediction system is more appropriate for DM disease prediction.
ABSTRACT
Introdução: Pacientes com doença coronariana, cuja principal causa é a aterosclerose, podem também desenvolver Doença Arterial Obstrutiva Periférica (DAOP). Objetivo: Analisar a incidência de DAOP em pacientes com doença arterial coronariana, relacionando com o número de artérias obstruídas. Material e métodos: Participaram deste estudo 48 pacientes com doença coronariana submetidos a cineangiocoronariografia com angioplastia e implante de stent coronariano, no período de janeiro de 2008 a junho de 2009, em um hospital de atendimento exclusivo do Sistema Único de Saúde (SUS) da cidade de Presidente Prudente, SP, Brasil. Foram avaliados dados demográficos, presença de patologias concomitantes e fatores de risco cardiovasculares, e realizada a aferição do Índice Tornozelo-Braquial (ITB). Foi realizada análise descritiva dos resultados. Resultados: A idade média foi de 59,5 ± 8,2 anos, sendo 64,6% do sexo masculino. O diabetes mellitusesteve presente em 37,5% dos pacientes, a hipertensão arterial sistêmica em 89,6%, a dislipidemia em 64,6% e o tabagismo em 52,1%. Na cineangiocoronariografia, houve predomínio de lesão na artéria descendente anterior (n=37; 77,1%), seguida pela coronária direita (n=24; 50%), primeira diagonal (n=16; 33,3%) e circunflexa (n=12; 25%). Dos avaliados, 19 pacientes (40%) tiveram o ITB alterado em, no mínimo, um membro. Conclusão: Em pacientes com doença coronariana e fatores de risco cardiovasculares, a DAOP foi altamente incidente. Porém, este estudo não observou correlação do ITB com a quantidade de artérias obstruídas. Considerando que os fatores de risco observados são mutáveis e plausíveis de serem controlados ou erradicados, como o tabagismo, é necessário que a atenção básica seja estimulada à busca ativa destes pacientes na comunidade, intensificando as estratégias de controle da hipertensão arterial sistêmica, da dislipidemia, do diabetes mellitus e do tabagismo.
Introduction: Patients with coronary disease whose primary cause is atherosclerosis may also develop Peripheral Arterial Disease (PAD). Objective: To analyze the incidence of PAD in patients with coronary artery disease, related to the number of obstructed arteries. Materials and methods: The study included 48 patients with coronary artery disease undergoing coronary angiography with angioplasty and coronary stenting, from January 2008 to June 2009, in a hospital serving exclusively the Unified Health System (SUS) in Presidente Prudente, SP, Brazil. Demographics, presence of concomitant diseases and cardiovascular risk factors were assessed and performed, and the Ankle Brachial Index (ABI) was measured. Descriptive Analysis of results was performed. Results: Mean age was 59.5 ± 8.2 years, 64.6% were males. Diabetes mellitus was present in 37.5% of patients, systemic arterial hypertension in 89.6%, dyslipidemia in 64.6% and smoking in 52.1%. In coronary angiography, there was a prevalence in lesion in the anterior descending artery (n=37; 77.1%), followed by the right coronary artery (n=24; 50%), first diagonal (n=16; 33.3%) and circumflex (n=12; 25%). Of the patients evaluated, 19 (40%) presented an altered ABI in at least one member. Conclusion: In patients with coronary disease and cardiovascular risk factors, the PAD was highly incident. However, this study found no correlation between the ABI and the quantity of obstructed arteries. Considering that the risk factors observed are changeable and plausible to be controlled or eradicated, such as smoking, it is necessary that primary care is encouraged so that there is an active search of these patients in the community, intensifying strategies for control of systemic arterial hypertension, dyslipidemia, diabetes mellitus and smoking
Subject(s)
Humans , Male , Female , Adult , Middle Aged , Coronary Artery Disease/diagnosis , Diabetes Mellitus , Peripheral Arterial DiseaseABSTRACT
Objective To study the relationship between urinary laminin(LN) and diabetic nephropathy.Methods Using the method for concentrating urinary laminin based on precipitation with PEG-4 000 and γ-globulin.The concentration of LN in the urine of 83 diabetics was measured by RIA.The concentration of micro-albumin and Ccr in the urine and the levels of plasma glucose and HbA1c were also measured.Results The choice of 150g/L of PEG-4 000 and 0.5 g/L of γ-globulin was the best method for concentrating urinary LN.The urinary LN in all groups was significantly higher than that in control group.Conclusion Urinary LN is an indicator in the diagnosis of the early diabetic nephropathy.
ABSTRACT
By applying the thrombo pre molecular markers, including plasmal GMP - 140, tPA, PAI - I TAT, PAP, ET, their correlation with blood stasis type diabetes were explored. Results showed that, the diabetic with blood -stasis type revealed the activation of platelets, injury of endothelial cells, changes of fibrinolysin. Their plasmal GMP-140, TAT, PAP, ET were all higher than that of the control group, indicating that the activation of platelets, injury of endothelial cells, and changes in the balance of blood coagulation/fibrinolysis are likely to benefit the incidence of blood stasis. The pathophysiological mechanism in blood stasis type diabetes is related to the changes in platelet, endothelial cells, blood coagulation and fibrinolysis.