Journal article

Predicting deseasonalised serum 25 hydroxy vitamin D concentrations in the D-Health Trial: an analysis using boosted regression trees

Mary Waterhouse, Catherine Baxter, Briony Duarte Romero, Donald SA McLeod, Dallas R English, Bruce K Armstrong, Michael W Clarke, Peter R Ebeling, Gunter Hartel, Michael G Kimlin, Rachel L O’Connell, Hai Pham, Rachael M Rodney Harris, Jolieke C van der Pols, Alison J Venn, Penelope M Webb, David C Whiteman, Rachel E Neale

Cold Spring Harbor Laboratory | Published : 2020


ABSTRACTBackgroundThe D-Health Trial aims to determine whether monthly high-dose vitamin D supplementation can reduce the mortality rate and prevent cancer. We did not have adequate statistical power for subgroup analyses, so could not justify the high cost of collecting blood samples at baseline. To enable future exploratory analyses stratified by baseline vitamin D status, we developed a model to predict baseline serum 25 hydroxy vitamin D [25(OH)D] concentration.MethodsWe used data and serum 25(OH)D concentrations from participants who gave a blood sample during the trial for compliance monitoring and were randomised to placebo. Data were partitioned into training (80%) and validation (20..

View full abstract