Human-AI collaboration for ultrasound diagnosis of thyroid nodules: a clinical trial
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. However, the operator had a substantial impact on the AI-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.
Authors
- Kasper Wennervaldt
- Jacob Melchiors (ORCID: https://orcid.org/0000-0002-9929-9350)
- Martin Bech (ORCID: https://orcid.org/0000-0001-9109-7175)
- Fatemeh Makouei (ORCID: https://orcid.org/0000-0002-6443-7362)
- Martin G. Tolsgaard (ORCID: https://orcid.org/0000-0001-9197-5564)
- Mikkel Kaltoft (ORCID: https://orcid.org/0009-0000-1900-3445)
- Anne Fog Lomholt (ORCID: https://orcid.org/0000-0002-5332-6560)
- Tobias Todsen (ORCID: https://orcid.org/0000-0003-3267-3560)
- Gitte Bjørn Hvilsom (ORCID: https://orcid.org/0000-0001-9239-3208)
- Axel Bukhave Edström
Institutions
- University of Copenhagen (DK)
- Copenhagen University Hospital (DK)
- Rigshospitalet (DK)
- Copenhagen Academy for Medical Education and Simulation (DK)
- Zealand University Hospital Køge (DK)
Publication Details
- Journal
- European Archives of Oto-Rhino-Laryngology
- Published
- 2025-02-07
- DOI
- https://doi.org/10.1007/s00405-025-09236-9
- Citations
- 8
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 10.36