Back

Assessment of AUC and fold change for precision medicine

Climer, S.; Smith, K.

2022-02-15 health informatics
10.1101/2022.02.14.22270972 medRxiv
Show abstract

Precision medicine is advancing patient care for complex human diseases. Discovery of biomarkers to diagnose specific subtypes within a heterogeneous diseased population is a key step towards realizing the benefits of precision medicine. However, popular statistical methods for evaluating candidate biomarkers - fold change (FC) and area under the receiver operating characteristic curve (AUC) - were designed for homogeneous data. Herein, we evaluate the performance of these metrics in heterogeneous populations. Using simulated biomarkers that are nearly ideal for distinguishing subgroups of various proportions of the diseased population, we observe that AUC misses all up to subset size of 50% and FC misses all biomarkers entirely. We introduce a simple new measure to address this shortfall and run a series of trials comprised of simulated and biological data to demonstrate its utility for evaluating biomarkers associated with disease subtypes.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.