Negative correlations between biomarkers maximize the combined AUC in multivariate normal models, with the largest gains when markers have equal predictive power, as shown by derivation, simulations, and pancreatic cancer metabolite data.
Building multi-marker algorithms for disease prediction–-the role of correlations among markers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating the role of correlation among markers in prediction models
Negative correlations between biomarkers maximize the combined AUC in multivariate normal models, with the largest gains when markers have equal predictive power, as shown by derivation, simulations, and pancreatic cancer metabolite data.