Publication

Artificial intelligence tools trained on human-labeled data reflect human biases: a case study in a large clinical consecutive knee osteoarthritis cohort

Authors:

Anders Lenskjold, Mathias W Brejnebøl, Martin H Rose, Henrik Gudbergsen, Akshay Chaudhari, Anders Troelsen, Anne Moller, Janus U Nybing & Mikael Boesen

Share this publication

Objective

This study aimed to assess the consistency of RBknee’s osteoarthritis (OA) grading and its ability to detect side-to-side differences, using a large six-year retrospective clinical dataset and a validated OA reference standard.

Open access

This research is open access

This original research can be read in Nature scientific reports, published November 2024.

Funding and conflicts of interests

This research is funded by the Danish Agency for Digital Government. MB and AT are medical advisors for Radiobotics and have warrants in the company. AL, MWB, MHR, HG, AC, AM, and JUN have no conflict of interest. Radiobotics ApS contributed to customer support for their AI tool, RBknee. The hospital department purchased the AI tool for clinical and research purposes.

The latest research about Radiobotics

Entering your information does not subscribe you to marketing emails from Radiobotics; it just makes it easier for us to get in touch with you. You can always read our privacy policy.

Contact Radiobotics

Interested in a research collaboration?

Complete the form, and someone will get back to you shortly. Or find department emails at our contact us page.

Entering your information does not subscribe you to marketing emails from Radiobotics; it just makes it easier for us to get in touch with you. You can always read our privacy policy.