Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial.

StudyEuropean archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery· Jun 2025

Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial.

Axel Bukhave Edström, Fatemeh Makouei, Kasper Wennervaldt … Tobias Todsen

Read paper

Medical Imaging AIStudyDiagnosisQ2IF 2.5

Articifial intelligence-assisted thyroid nodule diagnostic accuracy varied widely (40-100%) by operator.

Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial.

Axel Bukhave Edström … Tobias Todsen

European archives of oto-rhino-laryngology · Jun 2025 · Q2 in General Medicine

Purpose

This clinical trial examined how the articifial intelligence (articifial intelligence)-based diagnostics system S-Detect for Thyroid influences the ultrasound diagnostic work-up of thyroid ultrasound (ultrasound) performed by different ultrasound users in clinical practice and how different ultrasound users influences the diagnostic accuracy of S-Detect.

Methods

We conducted a clinical trial with 20 participants, including medical students, ultrasound novice physicians, and ultrasound experienced physicians.

n = 20 participants

40-100%

Results

40-100%

operator skill drove accuracy from poor to perfect with the same articifial intelligence tool

n = 20 participants

More results

The accuracy of our biopsy recommendation outcome was 69.8% before and 69.2% after articifial intelligence for all participants (p = 0.75).

“

Conclusion · 1 of 2

In this trial, we did not find S-Detect to improve the thyroid diagnostic work-up in clinical practice among novice and intermediate ultrasound operators.

Conclusion · 2 of 2

However, the operator had a substantial impact on the articifial intelligence-generated ultrasound diagnosis, with a variation in diagnostic accuracy from 40 to 100%, despite the same patients and ultrasound machines being used in the trial.

Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial.

Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial.

Related papers