Abstract
Numerous novel biomarkers are being considered as tools to enhance cardiovascular risk estimation. Statistical models can indicate how a biomarker influences movements between health states, and clinicians are interested in the impact they may have compared to traditional risk factors alone. Net reclassification indices (NRIs) have recently become popular statistics for measuring the prediction increment of new biomarkers. The msm package within R can fit multi-state models to longitudinal data, giving output for all permitted state-to-state transitions within the one calculation. However its usefulness could be further enhanced through its extension to include NRIs. This paper focuses on extending the msm package to enable NRIs to be calculated. The results are demonstrated for cardiovascular data, with the inclusion of a panel of novel biomarkers (CRP, NT-pro BNP, and troponin I) giving rise to a NRI of 0.2089 for males and 0.1678 for females.
Original language | English |
---|---|
Title of host publication | IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS) 20-24 June 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 203-204 |
Publication status | Published - 18 Aug 2016 |
Publication series
Name | 29th International Symposium on Computer-Based Medical Systems |
---|---|
Publisher | IEEE |
ISSN (Electronic) | 2372-9198 |
Fingerprint
Dive into the research topics of 'Can More High-Risk Cardiovascular Patients be Identified Using Novel Biomarkers? Extending the msm Package to Measure Reclassification.'. Together they form a unique fingerprint.Profiles
-
Felicity Lamrock
- School of Mathematics and Physics - Senior Lecturer
- Mathematical Sciences Research Centre
Person: Academic