eCite Digital Repository

A novel approach for prediction of vitamin D status using support vector regression

Citation

Guo, S and Lucas, RM and Ponsonby, A-L and Chapman, C and Coulthard, A and Dear, K and Dwyer, T and Kilpatrick, T and McMichael, T and Pender, MP and Taylor, B and Valery, P and van der Mei, I and Williams, D, A novel approach for prediction of vitamin D status using support vector regression, PLoS One, 8, (11) Article e79970. ISSN 1932-6203 (2013) [Refereed Article]


Preview
PDF
948Kb
  

Copyright Statement

Copyright 2013 Guo et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

DOI: doi:10.1371/journal.pone.0079970

Abstract

Background: Epidemiological evidence suggests that vitamin D deficiency is linked to various chronic diseases. However direct measurement of serum 25-hydroxyvitamin D (25(OH)D) 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 25(OH)D concentration. Predicted scores were compared with those from a MLR model.

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

Results: Better correlation was observed between predicted scores and measured 25(OH)D 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 25(OH)D levels (<75 nmol/L).

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

Item Details

Item Type:Refereed Article
Research Division:Medical and Health Sciences
Research Group:Neurosciences
Research Field:Central Nervous System
Objective Division:Health
Objective Group:Clinical Health (Organs, Diseases and Abnormal Conditions)
Objective Field:Nervous System and Disorders
Author:Taylor, B (Professor Bruce Taylor)
Author:van der Mei, I (Associate Professor Ingrid van der Mei)
ID Code:88174
Year Published:2013
Web of Science® Times Cited:2
Deposited By:Menzies Institute for Medical Research
Deposited On:2014-01-15
Last Modified:2017-11-06
Downloads:175 View Download Statistics

Repository Staff Only: item control page