Development and Validation of a Prediction Model for Thyroid Dysfunction in Patients During Immunotherapy
Authors' conclusion
The proposed nomogram serves as an effective and intuitive tool for predicting the risk of thyroid immune-related adverse events, facilitating clinicians making individualized decisions based on patient-specific information.
Study context
- Population
- Patients with malignant tumors receiving PD-1/PD-L1 inhibitors
- Participants
- 586 patients
- Exposure
- Training vs Validation
- Outcome
- Thyroid dysfunction (thyroid immune-related adverse events) after ICI treatment
Methodological detailsprediction model development and validation, random 7:3 split into training and validation cohorts, nomogram, K-fold cross-validation, decision curve analysis
- Prediction model development and validation
- Random 7:3 split into training and validation cohorts
- Nomogram
- K-fold cross-validation
- Decision curve analysis
Main finding
As reported in the abstract
Nomogram discrimination for thyroid immune-related adverse events
| Group | AUC |
|---|---|
| Training | 0.863 (95%CI: 0.817-0.909) |
| Validation | 0.885 (95%CI: 0.827-0.944) |
AUC
Training0.863 (95%CI: 0.817-0.909)
Validation0.885 (95%CI: 0.827-0.944)
Observational data: associations, not effects.
Further findings
Independent predictors of thyroid immune-related adverse events (logistic regression, training set) · baseline
- Baseline TSH, OR
- 1.427 (1.163-1.876) (95% CI)
- Baseline thyroglobulin antibody (TgAb), OR
- 1.105 (1.035-1.180) (95% CI)
- Baseline thyroid peroxidase antibody (TPOAb), OR
- 1.172 (1.110-1.237) (95% CI)
- Baseline platelet count, OR
- 1.004 (1.000-1.007) (95% CI)
Original publication
Development and Validation of a Prediction Model for Thyroid Dysfunction in Patients During Immunotherapy. Endocr Pract. Published 14 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →