A Novel Approach for Prediction of Vitamin D Status Using Support Vector RegressionReportar como inadecuado

A Novel Approach for Prediction of Vitamin D Status Using Support Vector Regression - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.


Epidemiological evidence suggests that vitamin D deficiency is linked to various chronic diseases. However direct measurement of serum 25-hydroxyvitamin D 25OHD concentration, the accepted biomarker of vitamin D status, may not be feasible in large epidemiological studies. An alternative approach is to estimate vitamin D status using a predictive model based on parameters derived from questionnaire data. In previous studies, models developed using Multiple Linear Regression MLR have explained a limited proportion of the variance and predicted values have correlated only modestly with measured values. Here, a new modelling approach, nonlinear radial basis function support vector regression RBF SVR, was used in prediction of serum 25OHD concentration. Predicted scores were compared with those from a MLR model.


Determinants of serum 25OHD in Caucasian adults n = 494 that had been previously identified were modelled using MLR and RBF SVR to develop a 25OHD prediction score and then validated in an independent dataset. The correlation between actual and predicted serum 25OHD concentrations was analysed with a Pearson correlation coefficient.


Better correlation was observed between predicted scores and measured 25OHD concentrations using the RBF SVR model in comparison with MLR Pearson correlation coefficient: 0.74 for RBF SVR; 0.51 for MLR. The RBF SVR model was more accurately able to identify individuals with lower 25OHD levels <75 nmol-L.


Using identical determinants, the RBF SVR model provided improved prediction of serum 25OHD concentrations and vitamin D deficiency compared with a MLR model, in this dataset.

Autor: Shuyu Guo , Robyn M. Lucas, Anne-Louise Ponsonby, the Ausimmune Investigator Group

Fuente: http://plos.srce.hr/


Documentos relacionados