A Data-Driven Approach to Refine Predictions of Differentiated Thyroid Cancer Outcomes: A Prospective Multicenter Study
Main findingResult — go to the resultNPV for low-risk patients, increase 3%Authors' conclusion
Current risk stratification systems may be complemented by the inclusion of other variables in order to improve the prediction of treatment response. A complete dataset allows for more precise patient clustering.
Study context
- Population
- Consecutive patients with differentiated thyroid cancer (DTC) and at least early follow-up data, Italian Thyroid Cancer Observatory (ITCO) database, 40 Italian centres; median follow-up 26 months (IQR 12–46)
- Participants
- 4,773 patients
- Exposure
- Data-driven decision tree model vs 2015 American Thyroid Association (ATA) risk stratification
- Outcome
- Prediction of persistent/recurrent disease
Methodological detailsmulticentre, decision tree model
- Multicentre
- Decision tree model
Main finding
As reported in the abstract
NPV for low-risk patients, increase
3%
By group
Decision tree
49%
Sensitivity of high-risk classification for structural disease
ATA
37%
Sensitivity of high-risk classification for structural disease
Observational data: associations, not effects.
Further findings
ATA risk categories
- Low risk
- 2492 (52.2%)
- Intermediate risk
- 1873 (39.2%)
- High risk
- 408
Feature importance
- Variables not in the ATA system that significantly impacted prediction of persistence/recurrence: age, BMI, tumor size, sex, family history of thyroid cancer, surgical approach, presurgical cytology, circumstances of diagnosis
Original publication
A Data-Driven Approach to Refine Predictions of Differentiated Thyroid Cancer Outcomes: A Prospective Multicenter Study. J Clin Endocrinol Metab. Published 16 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →