Uncertainty Wrapper in the medical domain: Establishing transparent uncertainty quantification for opaque machine learning models in practice

TL;DR

This paper introduces the Uncertainty Wrapper, a method for transparent uncertainty quantification in machine learning models applied to medical data, enhancing decision-making safety and reliability.

Contribution

It presents a practical approach to make opaque ML models in medicine more transparent by quantifying uncertainty reliably and interpretably.

Findings

Demonstrates applicability in flow cytometry data

Shows improved decision support in medical diagnostics

Validates the utility of the Uncertainty Wrapper in practice

Abstract

When systems use data-based models that are based on machine learning (ML), errors in their results cannot be ruled out. This is particularly critical if it remains unclear to the user how these models arrived at their decisions and if errors can have safety-relevant consequences, as is often the case in the medical field. In such cases, the use of dependable methods to quantify the uncertainty remaining in a result allows the user to make an informed decision about further usage and draw possible conclusions based on a given result. This paper demonstrates the applicability and practical utility of the Uncertainty Wrapper using flow cytometry as an application from the medical field that can benefit from the use of ML models in conjunction with dependable and transparent uncertainty quantification.