IntroductionGenomic medical research has generated a large number of candidate biomarkers that have potential use in the early‐phase detection and prognosis of many diseases. Compared to the conventional approach based on single biomarker, simultaneously using multiple biomarkers can substantially improve the sensitivity and accuracy of early detection of diseases (Sidransky, ; Etzioni et al., ). Multiple biomarker‐based scoring systems, such as the International Prognostic Scoring System (IPSS) (Greenberg et al., ), WHO Prognostic Scoring System (WPSS), and Revised International Prognostic Scoring System (IPSS‐R) (Greenberg et al., ), have played fundamental roles in the treatment decision‐making process. For example, multiple biomarkers have been used to guide treatment decisions for Myelodysplastic syndromes (MDS), a heterogeneous group of myeloid disorders. IPSS or IPSS‐R can play a crucial role in differentiating between patients at high risk of disease progression, for whom a more aggressive treatment may be justified, and patients with a minor risk of disease progression, for whom a more conservative treatment may be preferable.Although developing scoring systems for risk prediction has been an active research area, the vast majority of them have focused on binary outcomes (e.g., developing disease or not). Su and Liu () considered linear discriminant analysis by maximizing the area under
Biometrics – Wiley
Published: Jan 1, 2018
Keywords: ; ; ; ; ;
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 12 million articles from more than
10,000 peer-reviewed journals.
All for just $49/month
It’s easy to organize your research with our built-in tools.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud