Predicting papillary thyroid microcarcinoma in TI-RADS 3 nodules: a combined radiomics and clinical model
Recently, we were honored to read the article “The ultrasound-based radiomics-clinical machine learning model to predict papillary thyroid microcarcinoma in TI-RADS 3 nodules” (1). The study comprised 221 patients with Thyroid Imaging Reporting and Data System (TI-RADS) 3 nodules, who were randomly allocated into a training set and a test set in an 8:2 ratio. Radiomic characteristics were derived from Conventional ultrasound (CUS) images, whilst clinical parameters were acquired from electronic medical records. Papillary thyroid microcarcinoma (PTMC) and benign thyroid nodules were differentiated using radiomics models, clinical models, and combined models that were created and verified. The “radiomics-clinical” model, when combined, achieved an area under the curve (AUC) value of 0.975 in the training dataset and 0.898 in the validation dataset. This indicates that the model has a greater level of diagnostic accuracy in differentiating PTMC.
We highly value the contributions offered by the authors. Nevertheless, there are still unresolved matters in this work that necessitate additional investigation.
In this study, three clinical criteria were included: Tumor diameter, Echogenicity, and Echotexture. These factors had P values less than 0.05. These clinical variables possess specific prognostic significance in the identification of PTMC in TI-RADS 3 nodules. We recommend that the authors contemplate incorporating other clinical variables. Research has demonstrated a strong correlation between PTMC and the presence of both anti-thyroglobulin antibodies (TgAbs) and thyroid peroxidase antibodies (TPO-Abs) (2), and thyroid-stimulating hormone (TSH) is related to the progression of PTMC (3). Research has demonstrated that the levels of carcinoembryonic antigen (CEA) and thyroglobulin (Tg) in the blood of patients with thyroid cancer are markedly elevated compared to those with benign tumors (4). Moreover, the levels of serum cytokeratin18 (CK18) in individuals with papillary thyroid carcinoma (PTC) are elevated compared to those in the group of patients without any medical conditions. As the aforementioned signs are commonly utilized as standard preoperative tests, they can be easily obtained. If the statistical analysis reveals significant differences (P<0.05) in these variables, incorporating them into the nomogram could enhance the effectiveness of the model.
Furthermore, for model evaluation, we recommend using calibration curves to evaluate the concordance between model predictions and observed results. The discussion area provides an opportunity to elaborate on radiomics-related features.
Lastly, we would like to express our gratitude once more to the authors for their valuable contribution to this work. We anticipate that our viewpoints will be of value to the authors’ future research endeavors and eagerly await their feedback.
Acknowledgments
Funding: None.
Footnote
Provenance and Peer Review: This article was a standard submission to the journal. The article did not undergo external peer review.
Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://tcr.amegroups.com/article/view/10.21037/tcr-24-413/coif). The authors have no conflicts of interest to declare.
Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.
Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.
References
- Chen Z, Zhan W, Wu Z, et al. The ultrasound-based radiomics-clinical machine learning model to predict papillary thyroid microcarcinoma in TI-RADS 3 nodules. Transl Cancer Res 2024;13:278-89. [Crossref] [PubMed]
- Liu Y, Li C, Zhao W, et al. Hashimoto's Thyroiditis is an Important Risk Factor of Papillary Thyroid Microcarcinoma in Younger Adults. Horm Metab Res 2017;49:732-8. [Crossref] [PubMed]
- Mao A, An N, Wang J, et al. Association between preoperative serum TSH and tumor status in patients with papillary thyroid microcarcinoma. Endocrine 2021;73:617-24. [Crossref] [PubMed]
- Yan G, Zhou Y, Wu H, et al. Diagnostic Value of Serum Cytokeratin 18, Carcinoembryonic Antigen, and Thyroglobulin in Patients with Papillary Thyroid Carcinoma. Clin Lab 2021; [Crossref] [PubMed]
