Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM)

TL;DR

This paper introduces EMM, an ensemble-based monitoring framework that assesses the confidence of AI predictions in real-time for intracranial hemorrhage detection, enhancing reliability without needing internal AI details.

Contribution

The study presents EMM, a novel, black-box compatible monitoring model that improves AI confidence assessment in medical imaging, specifically for intracranial hemorrhage detection.

Findings

EMM effectively categorizes AI prediction confidence levels.

Using EMM reduces cognitive burden for clinicians.

EMM improves AI tool reliability in clinical settings.

Abstract

Artificial intelligence (AI) tools for radiology are commonly unmonitored once deployed. The lack of real-time case-by-case assessments of AI prediction confidence requires users to independently distinguish between trustworthy and unreliable AI predictions, which increases cognitive burden, reduces productivity, and potentially leads to misdiagnoses. To address these challenges, we introduce Ensembled Monitoring Model (EMM), a framework inspired by clinical consensus practices using multiple expert reviews. Designed specifically for black-box commercial AI products, EMM operates independently without requiring access to internal AI components or intermediate outputs, while still providing robust confidence measurements. Using intracranial hemorrhage detection as our test case on a large, diverse dataset of 2919 studies, we demonstrate that EMM successfully categorizes confidence in the AI-generated prediction, suggesting different actions and helping improve the overall performance of AI tools to ultimately reduce cognitive burden. Importantly, we provide key technical considerations and best practices for successfully translating EMM into clinical settings.