30/100

Emerging evidence

Published recordHealthGeneral

Normalized risk-based evaluation of machine learning-based classification models: A multiclass approach with applications in medical devices

Truvace record
TRV-2026-1215raw data (JSON)
Version
v2Revised
First published
Evidence type
Commentary, opinion, or narrative review
Sources
1 sourcePeer-reviewed
sha256
f387594f70e8…check it

ObjectiveMachine learning is increasingly integrated into safety-critical domains such as medical applications. In this context, regulatory frameworks require the assessment and minimization of risks associated with incorrect model predictions. However, classical evaluation methods often focus on quantifying error frequencies, which do not reflect the heterogeneous impact of different types of errors. To address this deficiency, we elaborate an approach for assessing machine learning-based multiclass classificat…

The gain

Weighted balanced accuracy (WBAn) provides a regulatory-aligned, risk-based evaluation for multiclass medical AI that weights errors by severity and links development to real-world performance, demonstrated in X-ray lung disease detection.

The problem

Standard evaluation that counts error frequencies fails to reflect differing clinical severity of error types, leaving regulatory risk requirements incompletely implemented and real-world clinical impact inadequately assessed.

What this doesn’t fix

Demonstration is limited to a single use case, which constrains generalizability of the practical applicability claim.

Sources

1 on file
  1. Peer-reviewed2026-09-28

Cite this record

v2

Truvace Impact Record TRV-2026-1215, v2: “Normalized risk-based evaluation of machine learning-based classification models: A multiclass approach with applications in medical devices.” Truvace, 2026-11-04. /record/TRV-2026-1215 (accessed on the day you copy it). sha256 f387594f70e84352…

Change history

2 versions

Every change made to this record since it was first published, and why.

  1. Revisedv2f387594f70e8…

    Editorial pass: sharper headline; filed as context: no real AI gain or problem (gain activity_only, problem unsupported).

  2. Publishedv1ada2a9ed1e1b…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-1215 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.