Censo Brasileiro de Diálise, 2009

Exploring Early Prediction of Chronic Kidney Disease Using Machine Learning Algorithms for Small and Imbalanced Datasets

Chronic kidney disease (CKD) is a worldwide public health problem, usually diagnosed in the late stages of the disease. To alleviate such issue, investment in early prediction is necessary. The purpose of this study is to assist the early prediction of CKD, addressing problems related to imbalanced and limited-size datasets. We used data from medical records of Brazilians with or without a diagnosis of CKD, containing the following attributes: hypertension, diabetes mellitus, creatinine, urea, albuminuria, age, gender, and glomerular filtration rate. We present an oversampling approach based on manual and automated augmentation. We experimented with the synthetic minority oversampling technique (SMOTE), Borderline-SMOTE, and Borderline-SMOTE SVM. We implemented models based on the algorithms: decision tree (DT), random forest, and multi-class AdaBoosted DTs. We also applied the overall local accuracy and local class accuracy methods for dynamic classifier selection; and the k-nearest oracles-union, k-nearest oracles-eliminate, and META-DES for dynamic ensemble selection. We analyzed the models’ performances using the hold-out validation, multiple stratified cross-validation (CV), and nested CV. The DT model presented the highest accuracy score (98.99%) using the manual augmentation and SMOTE. Our approach can assist in designing systems for the early prediction of CKD using imbalanced and limited-size datasets.

Ser paciente renal crónico desde la perspectiva de la enfermera: una mirada existencialista en el desvelar de la evidencia cualitativa

Objetivo: Este estudio pretende desvelar la evidencia cualitativa del paciente con enfermedad renal crónica a través de la percepción del equipo de enfermería nefrológica bajo una mirada existencialista. Material y Método: Se trata de un estudio cualitativo, exploratorio-descriptivo, con análisis basado en la teoría humanista de Paterson y Zderard y de la filosofía existencialista. Los trabajos de campo se hicieron en el servicio de nefrología en el sur de Brasil y un centro de hemodiálisis en Lorca en España. La muestra fue 12 profesionales del equipo enfermería. El estudio de los datos se realizó mediante análisis de contenido, con la identificación de categorías centrales. Resultados/Discusión: se identificaron tres categorías centrales: ser paciente; aceptar la enfermedad y establecer vínculos. El ser paciente se desvela como un ser cuidado que requiere atención de enfermería especializada, para el tratamiento de los síntomas físicos, pero también desde una mirada atenta y acogedora de sus necesidades emocionales. La aceptación de la enfermedad enfermedad por parte de éste resulta clave para ser consciente de su existencia. Para ello el profesional de Enfermería debe establecer vínculos con el ser cuidado. Consideraciones finales: Al desvelar esta nueva realidad y la necesidad de realizar una terapia renal sustitutiva, el ser cuidado presenta sentimientos de miedo, tristeza, desesperanza, sufrimiento por la pérdida de autonomía. Sin embargo, también se perciben sentimientos positivos como: confianza, al establecer un vínculo con el equipo de enfermería, y de esperanza y alegría ante la posibilidad de un trasplante y recuperación de su autonomía.

Qualidade de vida de pacientes renais crônicos em tratamento hemodialítico

Objetivo: avaliar a qualidade de vida (QdV) de pacientes com DRC em tratamento com hemodiálise. Métodos: a amostra foi composta por 88 pacientes em tratamento hemodialítico na região metropolitana de Porto Alegre, Rio Grande do Sul, Brasil. Os dados foram coletados por meio de entrevista individual, utilizando-se um questionário de dados sociodemográficos e questionário Short Form-36 (SF-36) que avalia QdV em portadores de doenças crônicas. Resultados: evidenciou-se, com o escore do SF-36, baixa QdV dos pacientes devido às limitações ocasionadas pelos aspectos físicos e emocionais. Em relação ao gênero, pacientes do sexo feminino apresentaram menor escore em todos os domínios do SF-36. Conclusão: a baixa QdV dos participantes do estudo teve influência significativa devido aos problemas adaptativos e sociais sofridos ao longo do processo de adoecimento. Houve destaque para as limitações causadas por aspectos físicos, que apresentaram escores significantemente baixos.

Self-reported diabetes in older people: comparison of prevalences and control measures

OBJECTIVE

The objective of this study was to analyze the prevalence of diabetes in older people and the adopted control measures.

METHODS

Data regarding older diabetic individuals who participated in the Health Surveys conducted in the Municipality of Sao Paulo, SP, ISA-Capital, in 2003 and 2008, which were cross-sectional studies, were analyzed. Prevalences and confidence intervals were compared between 2003 and 2008, according to sociodemographic variables. The combination of the databases was performed when the confidence intervals overlapped. The Chi-square (level of significance of 5%) and the Pearson's Chi-square (Rao-Scott) tests were performed. The variables without overlap between the confidence intervals were not tested.

RESULTS

The age of the older adults was 60-69 years. The majority were women, Caucasian, with an income of between > 0.5 and 2.5 times the minimum salary and low levels of schooling. The prevalence of diabetes was 17.6% (95%CI 14.9;20.6) in 2003 and 20.1% (95%CI 17.3;23.1) in 2008, which indicates a growth over this period (p at the limit of significance). The most prevalent measure adopted by the older adults to control diabetes was hypoglycemic agents, followed by diet. Physical activity was not frequent, despite the significant differences observed between 2003 and 2008 results. The use of public health services to control diabetes was significantly higher in older individuals with lower income and lower levels of education.

CONCLUSIONS

Diabetes is a complex and challenging disease for patients and the health systems. Measures that encourage health promotion practices are necessary because they presented a smaller proportion than the use of hypoglycemic agents. Public health policies should be implemented, and aimed mainly at older individuals with low income and schooling levels. These changes are essential to improve the health condition of older diabetic patients.

Série histórica de custos com terapia de substituição renal no município do Rio de Janeiro (1995-2009)

Objetivou-se avaliar a tendência temporal do custo total de terapia de substituição renal e a proporção entre custo e solicitações de Autorizações de Procedimentos Ambulatoriais de Alta Complexidade/Custo no município do Rio de Janeiro, entre 1995 e 2009, em totais e segundo prestador. Estudo quantitativo, descritivo, tipo série temporal. Utilizaram-se informações referentes aos valores e quantidades de autorizações de procedimentos de alta complexidade para terapia de substituição renal por ano, disponíveis no DATASUS, coletadas entre fevereiro e março de 2011. Observou-se tendência crescente para o custo total e o total de autorizações destes procedimentos (y=3,8414x + 16,904, R²=0,9665 e y=14519x + 299719, R²=0,8835, respectivamente). Há uma diferença estatisticamente significativa (p<0,001) da variação da tendência quando comparados os serviços públicos e os privados. Conclui-se que há uma tendência em programar cada vez mais serviços nos hospitais públicos, tornando crescente a demanda por profissionais qualificados para atuação na área.

Prevalence and management of anemia in hemodialysis patients in a Brazilian population of predominantly African descent

BACKGROUND/OBJECTIVE

Findings from the international DOPPS indicated a rise in hemoglobin levels for patients on maintenance hemodialysis (MHD) for more than 180 days across many countries with more than 60% with hemoglobin ≥11 g/dl. However, the situation of anemia control for a large contingent of the hemodialysis population remains unknown. Studies in the United States indicate that hemoglobin level is lower for African Americans on MHD, but studies in other populations of African descent are lacking. We investigated the prevalence of, and associated factors for, hemoglobin <11 g/dl in MHD patients from the Brazilian city with the largest proportion of African descendants outside Africa.

METHODS

Cross-sectional study of 1,263 MHD patients enrolled in the Prospective Study of the Prognosis of Chronic Hemodialysis Patients (PROHEMO) in Salvador, Brazil 2005-2009.

RESULTS

88.0% black or mixed race; age 49.0 ± 14.7 years; 96.6% receiving erythropoietin, median = 6,000 units/week. In patients on MHD for more than 180 days, 67.4% had hemoglobin <11 g/dl. Factors associated with hemoglobin<11 g/dl were MHD by catheter (odds ratio (OR) = 3.03, 95% confidence interval (CI) = 1.43-6.42), hospitalization in prior 3 months (OR = 2.14, 95% CI = 1.20-3.83), transferrin saturation <20% (OR = 1.49, 95% CI = 1.05-2.12) and higher malnutrition-inflammation score (OR = 1.58 per each log-transformed unit, 95% CI = 1.14-2.19).

CONCLUSIONS

The results suggest that iron deficiency, insufficient erythropoietin dose, catheter use, malnutrition-inflammation, and problems associated with hospitalization are explanations for the high prevalence of hemoglobin below the guideline target in MHD patients from a large African descent Brazilian population. These results have implications for understanding the lower hemoglobin concentration in MHD populations of African descent.

A Brazilian experience in assisted automated peritoneal dialysis: a reliable and effective home care approach

INTRODUCTION

Automated assisted peritoneal dialysis (AAPD) has been shown to be successful as renal replacement therapy for elderly and physically incapable end-stage renal disease (ESRD) patients. In early 2003, a pioneer AAPD program was initiated at GAMEN Renal Clinic in Rio de Janeiro, Brazil. ♢

OBJECTIVE

We evaluated the results of an AAPD program offered as an option to elderly ESRD patients with physical or cognitive debilities or as last resort to patients with vascular access failure or hemodynamic instability during hemodialysis. ♢

METHODS

A cohort of 30 consecutive patients started AAPD from January 2003 to March 2008 and was followed to July 2009. Demographics, clinical and laboratory parameters, causes of death, and patient and technique survival were analyzed. ♢

RESULTS

Median age of the patients was 72 years (range: 47 - 93 years), with 60% being older than 65. The Davies score was greater than 2 in 73% of patients, and the Karnofsky index was less than 70 in 40%. The overall peritonitis rate was 1 episode in 37 patient-months. The total duration of AAPD ranged from 3 to 72 months. Patient survival was 80% at 12 months, 60% at 24 months, and 23.3% at 48 months. The most common cause of death was cardiovascular problems (70%). ♢

CONCLUSIONS

In this clinical observational study, AAPD fulfilled its expected role, offering an opportune, reliable, and effective homecare alternative for ESRD patients with no other renal replacement therapy options.