English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Diagnostic testing provides a unique setting for studying and developingtools in classification theory. In such contexts, the concept of prevalence,i.e. the number of individuals with a given condition, is fundamental, both asan inherent quantity of interest and as a parameter that controlsclassification accuracy. This manuscript is the first in a two-part series thatstudies deeper connections between classification theory and prevalence,showing how the latter establishes a more complete theory of uncertaintyquantification (UQ) for certain types of machine learning (ML). We motivatethis analysis via a lemma demonstrating that general classifiers minimizing aprevalence-weighted error contain the same probabilistic information asBayes-optimal classifiers, which depend on conditional probability densities.This leads us to study relative probability level-sets $B^\star (q)$, which arereinterpreted as both classification boundaries and useful tools forquantifying uncertainty in class labels. To realize this in practice, we alsopropose a numerical, homotopy algorithm that estimates the $B^\star (q)$ byminimizing a prevalence-weighted empirical error. The successes andshortcomings of this method motivate us to revisit properties of the levelsets, and we deduce the corresponding classifiers obey a useful monotonicityproperty that stabilizes the numerics and points to important extensions to UQof ML. Throughout, we validate our methods in the context of synthetic data anda research-use-only SARS-CoV-2 enzyme-linked immunosorbent (ELISA) assay.

Analysis of Diagnostics (Part I): Prevalence, Uncertainty Quantification, and Machine Learning