Type

Journal Article

Authors

R William Watson
Denis C Shields
Orla Sheils
Radka Saldova
Pauline M Rudd
Antoinette S Perry
Stephen R Pennington
John O'Leary
Richard J O'Kennedy
Stephen Finn
and 9 others

Subjects

Medicine & Nursing

Topics
dna methylation prostate cancer performance assessment performance analysis logistic regression cross validation cancer patients data integration

Integrating biomarkers across omic platforms: an approach to improve stratification of patients with indolent and aggressive prostate cancer. (2018)

Abstract Classifying indolent prostate cancer represents a significant clinical challenge. We investigated whether integrating data from different omic platforms could identify a biomarker panel with improved performance compared to individual platforms alone. DNA methylation, transcripts, protein and glycosylation biomarkers were assessed in a single cohort of patients treated by radical prostatectomy. Novel multiblock statistical data integration approaches were used to deal with missing data and modelled via stepwise multinomial logistic regression, or LASSO. After applying leave-one-out cross-validation to each model, the probabilistic predictions of disease type for each individual panel were aggregated to improve prediction accuracy using all available information for a given patient. Through assessment of three performance parameters of area under the curve (AUC) values, calibration and decision curve analysis, the study identified an integrated biomarker panel which predicts disease type with a high level of accuracy, with Multi AUC value of 0.91 (0.89, 0.94) and Ordinal C-Index (ORC) value of 0.94 (0.91, 0.96), which was significantly improved compared to the values for the clinical panel alone of 0.67 (0.62, 0.72) Multi AUC and 0.72 (0.67, 0.78) ORC. Biomarker integration across different omic platforms significantly improves prediction accuracy. We provide a novel multiplatform approach for the analysis, determination and performance assessment of novel panels which can be applied to other diseases. With further refinement and validation, this panel could form a tool to help inform appropriate treatment strategies impacting on patient outcome in early stage prostate cancer.
Collections Ireland -> Dublin City University -> PubMed

Full list of authors on original publication

R William Watson, Denis C Shields, Orla Sheils, Radka Saldova, Pauline M Rudd, Antoinette S Perry, Stephen R Pennington, John O'Leary, Richard J O'Kennedy, Stephen Finn and 9 others

Experts in our system

1
R William G Watson
University College Dublin
Total Publications: 135
 
2
Denis C. Shields
University College Dublin
Total Publications: 123
 
3
Orla Sheils
Trinity College Dublin
Total Publications: 55
 
4
Radka Saldova
Dublin City University
 
5
Pauline M Rudd
University College Dublin
Total Publications: 45
 
6
Antoinette S Perry
Trinity College Dublin
Total Publications: 24
 
7
Stephen R Pennington
University College Dublin
 
8
John O'Leary
Trinity College Dublin
Total Publications: 93
 
9
R O'Kennedy
Dublin City University
Total Publications: 211
 
10
Stephen P Finn
Trinity College Dublin
Total Publications: 60