# Decoding Uncertainty Quantification for Oncology—An Illustration Using Radiomics

## TL;DR

This paper introduces uncertainty quantification in AI models for oncology to help doctors understand how reliable predictions are.

## Contribution

The paper introduces uncertainty quantification in AI models for oncology using a radiomics risk model as an example.

## Key findings

- A radiomics risk model for thymic epithelial tumors was developed to illustrate uncertainty quantification.
- Uncertainty can be measured using distance measures within the feature space of AI models.
- Clinicians may need more information in specific cases to improve confidence in AI-driven assessments.

## Abstract

While AI models are developed in oncology for predicting different clinical outcomes, the focus is often on accuracy and many fail to adequately communicate the degree of certainty in these predictions. To improve clinical decision-making in oncology, this work introduces the idea of uncertainty quantification (UQ) for AI models using an illustrative example. Our goal is to help radiologists and oncologists better understand prediction reliability by integrating UQ. Our illustrative example is a Radiomics Risk Model (RM) for Thymic Epithelial Tumours, developed to provide a basic understanding of the mechanism to evaluate the degree to which individual patient data matches the training set. The study demonstrates the concept of measuring uncertainty in artificial intelligence (AI) models using a simple example of distance measures within the feature space and example cases where uncertainty is addressed with probable causes. The paper highlights specifically where the clinicians may need more information to improve their confidence in their AI-driven assessments for clinical diagnostics.