Tailored Bayes: a risk modeling framework under unequal misclassification costs.


Type
Article
Change log
Authors
Karapanagiotis, Solon  ORCID logo  https://orcid.org/0000-0003-4460-2073
Benedetto, Umberto 
Mukherjee, Sach 
Kirk, Paul DW 
Newcombe, Paul J 
Abstract

Risk prediction models are a crucial tool in healthcare. Risk prediction models with a binary outcome (i.e., binary classification models) are often constructed using methodology which assumes the costs of different classification errors are equal. In many healthcare applications, this assumption is not valid, and the differences between misclassification costs can be quite large. For instance, in a diagnostic setting, the cost of misdiagnosing a person with a life-threatening disease as healthy may be larger than the cost of misdiagnosing a healthy person as a patient. In this article, we present Tailored Bayes (TB), a novel Bayesian inference framework which "tailors" model fitting to optimize predictive performance with respect to unbalanced misclassification costs. We use simulation studies to showcase when TB is expected to outperform standard Bayesian methods in the context of logistic regression. We then apply TB to three real-world applications, a cardiac surgery, a breast cancer prognostication task, and a breast cancer tumor classification task and demonstrate the improvement in predictive performance over standard methods.

Description
Keywords
Bayesian inference, Binary classification, Misclassification costs, Tailored Bayesian methods, Humans, Female, Bayes Theorem, Models, Statistical, Logistic Models, Computer Simulation, Breast Neoplasms
Journal Title
Biostatistics
Conference Name
Journal ISSN
1465-4644
1468-4357
Volume Title
Publisher
Oxford University Press (OUP)
Sponsorship
European Commission Horizon 2020 (H2020) Societal Challenges (847912)