Visualising the Truth: A Composite Evaluation Framework for Score-Based Predictive Models Selection

Abstract excerpt

Model selection in machine learning applications for biomedical predictions is often constrained by reliance on conventional global performance metrics such as area under the ROC curve (AUC), sensitivity, and specificity. When these metrics are closely clustered across multiple candidate models, distinguishing the most suitable model for real-world application becomes challenging. We propose a novel composite eval...

Topics

Open a Topic to create a Post that cites this publication.

• Diagnostic Imaging
• Metabolomics
• Molecular Imaging
• Neoplasms
• Phenotype
• Sepsis Diagnosis and Treatment
• Spectrometry, Mass, Electrospray Ionization
• Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization

Identifiers and source

Literature Corpus work

e87bfa19-e822-5b82-8b61-2e2f63d00461

DOI

10.20944/preprints202506.1803.v1