A method for increasing the robustness of stable feature selection for biomarker discovery in molecular medicine developed using serum small extracellular vesicle associated miRNAs and the Barrett’s oesophagus disease spectrum

The biomarker development field within molecular medicine remains limited by the methods that are available for building predictive models. We developed an efficient method for conservatively estimating confidence intervals for the cross validation derived prediction errors of biomarker models. This new method was investigated for its ability to improve the capacity of our previously developed method, StaVarSel, for selecting stable biomarkers. Compared with the standard cross validation method StaVarSel markedly improved the estimated generalisable predictive capacity of serum miRNA biomarkers for the detection of disease states that are at increased risk of progressing to oesophageal adenocarcinoma. The incorporation of our new method for conservatively estimating confidence intervals into StaVarSel resulted in the selection of less complex models with increased stability and improved or similar predictive capacities. The methods developed in this study have the potential to improve progress from biomarker discovery to biomarker driven translational research. Controls (n=14, all male). This group of patients had a visibly normal oesophageal mucosa at endoscopy. Non-dysplastic Barrett’s oesophagus (NDB; n=21, all male). This group of patients had endoscopically visible Barrett’s oesophagus which was confirmed by histology to be negative for dysplasia. Barrett’s oesophagus with high grade dysplasia (HGD; n=19, all male). This group of patients had a histological confirmation of high-grade dysplasia within the Barrett’s oesophagus segment. In one patient, the presence of T1a cancer was also noted on the histology report. >>>Submitter states: NOTE that we are unable to submit raw data files due to institutional human ethics privacy constraints. <<<