RDBU| Repositório Digital da Biblioteca da Unisinos

A machine learning model for early diagnosis of arteriovenous fistula stenosis

Show simple item record

metadataTrad.dc.contributor.author Hidalgo Junior, Orlando Vilmar Rodrigues;
metadataTrad.dc.contributor.advisor Costa, Cristiano André da;
metadataTrad.dc.contributor.advisorLattes http://lattes.cnpq.br/9637121030877187;
metadataTrad.dc.publisher Universidade do Vale do Rio dos Sinos;
metadataTrad.dc.title A machine learning model for early diagnosis of arteriovenous fistula stenosis;
metadataTrad.dc.description.resumo The quality of the vascular access of patients with Chronic Kidney Disease is extremely important and proves to be a decisive factor in the patient's longevity and well-being. Currently, arteriovenous fistula is one of the most recommended vascular access and some concerns about this access are evident, such as arteriovenous fistula stenosis. The aim of this work is to develop a machine learning model for analysis and prediction based on monitoring of the data generated by the hemodialysis equipment and hemodialysis session. This study is a partnership between Clinical Research Center located in Porto Alegre, Brazil and the Graduate Programs in Applied Computing and Nursing at UNISINOS. The project was previously approved by the Research Ethics Committee of UNISINOS and HCPA and uses 1483 samples from 27 patients. Logistic Regression, K-Nearest Neighbors, Support Vector Machine and Random Forest have been trained and tested using 10- fold cross validation. Random Forest achieved the best performance with an F1- score of 98.40%, sensitivity of 98.80% and specificity of 98.50%. We also found that patient’s age, fistula age and gender had higher importance for Random Forest in Predicting stenosis. This model used a new set of features and had higher results compared to the related works, making it a promising predictor of arteriovenous fistula stenosis;
metadataTrad.dc.subject Arteriovenous fistula; Stenosis; Hemodialysis; K-Nearest neighbors; Support vector machine; Random forest; Logistic regression;
metadataTrad.dc.type TCC;
metadataTrad.dc.date.issued 2020-12-02;
metadataTrad.dc.identifier.uri http://www.repositorio.jesuita.org.br/handle/UNISINOS/11052;
metadataTrad.dc.audience.educationLevel Graduação;
metadataTrad.dc.curso Ciência da Computação;

Files in this item

This item appears in the following Collection(s)

Show simple item record


Advanced Search


My Account