Clinical Evaluation of an Artificial Intelligence-Based Decision Support System for the Diagnosis and American College of Radiology Thyroid Imaging Reporting and Data System Classification of Thyroid Nodules
Authors' conclusion
The use of an AI-based DSS was associated with overall improvement in the diagnostic efficacy of ultrasound imaging, based on the AUROC, as well as an increase in Sens, Spe, negative and PPVs, and diagnostic accuracy. There was also a reduction in interobserver variability and an increase in the degree of concordance with the use of AI. AI reclassified more than half of the nodules with intermediate ACR TI-RADS scores into lower risk categories.
Study context
- Population
- Patients with thyroid nodules with histological findings, thyroid nodule clinic, June 2021–December 2022; 83.1% women, mean age 52.3 ± 15.3 years
- Participants
- 172 patients
- Comparison
- ACR TI-RADS ultrasound reading before vs after use of artificial intelligence (AI)-based decision support system (DSS)
- Outcome
- Diagnostic performance vs histological diagnosis (AUROC)
Methodological detailsretrospective, single thyroid nodule clinic, six readers
- Retrospective
- Single thyroid nodule clinic
- Six readers
Performance
As reported in the abstract
- Area under the ROC curve (AUROC) increased after the use of AI
- AI-based DSS improved mean Sens and specificity (Spe), produced a high NPV, and increased PPV and diagnostic precision
- Ultrasound imaging and the AI-based DSS vs Ultrasound imaging alone: P < 0.001
Further findings
R
| Outcome | US alone | US + AI-based DSS | P value |
|---|---|---|---|
| Interobserver agreement (ACR TI-RADS score)Significant improvement after use of AI | 0.741 | 0.981 | P < 0.001 |
AI reclassification into lower risk categories
- ACR TI-RADS 3 nodules reclassified lower by AI
- 81.4%
- ACR TI-RADS 4 nodules reclassified lower by AI
- 24.5%
Original publication
Clinical Evaluation of an Artificial Intelligence-Based Decision Support System for the Diagnosis and American College of Radiology Thyroid Imaging Reporting and Data System Classification of Thyroid Nodules. Thyroid. Published 19 March 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →