Prediction of metabolic syndrome and its associated risk factors in patients with chronic kidney disease using machine learning techniques.
J Bras Nefrol
; 46(4): e20230135, 2024.
Article
em En, Pt
| MEDLINE
| ID: mdl-39133895
ABSTRACT
INTRODUCTION:
Chronic kidney disease (CKD) and metabolic syndrome (MS) are recognized as public health problems which are related to overweight and cardiometabolic factors. The aim of this study was to develop a model to predict MS in people with CKD.METHODS:
This was a prospective cross-sectional study of patients from a reference center in São Luís, MA, Brazil. The sample included adult volunteers classified according to the presence of mild or severe CKD. For MS tracking, the k-nearest neighbors (KNN) classifier algorithm was used with the following inputs gender, smoking, neck circumference, and waist-to-hip ratio. Results were considered significant at p < 0.05.RESULTS:
A total of 196 adult patients were evaluated with a mean age of 44.73 years, 71.9% female, 69.4% overweight, and 12.24% with CKD. Of the latter, 45.8% had MS, the majority had up to 3 altered metabolic components, and the group with CKD showed statistical significance in waist circumference, systolic blood pressure, diastolic blood pressure, and fasting blood glucose. The KNN algorithm proved to be a good predictor for MS screening with 79% accuracy and sensitivity and 80% specificity (area under the ROC curve - AUC = 0.79).CONCLUSION:
The KNN algorithm can be used as a low-cost screening method to evaluate the presence of MS in people with CKD.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Síndrome Metabólica
/
Insuficiência Renal Crônica
/
Aprendizado de Máquina
Limite:
Adult
/
Female
/
Humans
/
Male
/
Middle aged
País/Região como assunto:
America do sul
/
Brasil
Idioma:
En
/
Pt
Revista:
J Bras Nefrol
Assunto da revista:
NEFROLOGIA
Ano de publicação:
2024
Tipo de documento:
Article
País de afiliação:
Brasil
País de publicação:
Brasil