Efficacy of machine learning model and EU-TIRADS-PL reporting system in predicting thyroid malignancy risk: a comparison
Authors' conclusion
The proposed ML model showed good accuracy and may improve thyroid malignancy risk assessment compared with systems based only on sonographic features.
Study context
- Population
- Patients who underwent thyroidectomy based on preoperative ultrasound and fine-needle aspiration biopsies (FNAB) resultspatients who underwent thyroidectomy
- Participants
- 561 patients
- Index test or model
- Machine learning model vs EU-TIRADS-PL reporting system, verified by histopathology
- Target condition
- thyroid malignancy
Methodological detailsdevelopment of a machine learning model, training and test sets (3:1)
- Development of a machine learning model
- Training and test sets (3:1)
Performance
As reported in the abstract
| Test or model | Test set ROC AUC |
|---|---|
| Machine learning (ML) MODEL (logistic regression (LR)) | 74% |
Machine learning (ML) MODEL (logistic regression (LR))
Test set ROC AUC74%
Further findings
Anteroposterior-to-longitudinal dimension index for malignancy
- ROC AUC
- 68% (95% CI 62.0-71.0)
Malignant nodules
- Malignant nodules
- 261 (46.5%)
Predictors of malignancy
- Microcalcifications
- P = 0.002
- Younger age
- P < 0.001
- Male sex
- P = 0.001
- Larger anteroposterior dimension
- P = 0.026
- Larger longitudinal dimension associated with lower malignancy risk
- P < 0.001
Original publication
Efficacy of machine learning model and EU-TIRADS-PL reporting system in predicting thyroid malignancy risk: a comparison. Endocr Pract. Published 13 November 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →