Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 7 (2022)  /  Artículo
ARTÍCULO
TITULO

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

Andressa C. M. da Silveira    
Álvaro Sobrinho    
Leandro Dias da Silva    
Evandro de Barros Costa    
Maria Eliete Pinheiro and Angelo Perkusich    

Resumen

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.

 Artículos similares

       
 
Hualing Lin and Qiubi Sun    
Accurately predicting the volatility of financial asset prices and exploring its laws of movement have profound theoretical and practical guiding significance for financial market risk early warning, asset pricing, and investment portfolio design. The tr... ver más
Revista: Information

 
Kamel Mohamed Rahla, Ricardo Mateus and Luís Bragança    
A growing concern is given to the environmental impacts caused by the construction industry. Waste generation, resource consumption, and greenhouse gas emissions are the main drawbacks of the rapid urbanization that the world is witnessing. As a response... ver más
Revista: Infrastructures

 
Sugiarto Sugiarto,Lulusi Lulusi,Cut Mutiawati,Sofyan M. Saleh,Qurrata A'yuni,Irham Iskandar     Pág. 12 - 21
Urban bus reform so-called Trans Koetaradja (TK) is regarded as a potential urban transport policy aiming at alleviating autos traffic congestion and mitigating highly private mode dependency in Banda Aceh, Indonesia. The new bus system proposed by the G... ver más

 
Rick Kool, Judy Lawrence, Martin Drews and Robert Bell    
Sea-level rise increasingly affects low-lying and exposed coastal communities due to climate change. These communities rely upon the delivery of stormwater and wastewater services which are often co-located underground in coastal areas. Due to sea-level ... ver más
Revista: Infrastructures

 
Torgrim Log, Vigdis Vandvik, Liv Guri Velle and Maria-Monika Metallinou    
In recent years, severe and deadly wildland-urban interface (WUI) fires have resulted in an increased focus on this particular risk to humans and property, especially in Canada, USA, Australia, and countries in the Mediterranean area. Also, in areas not ... ver más