Development and validation of a machine learning model for central compartmental lymph node metastasis in solitary papillary thyroid microcarcinoma via ultrasound imaging features and clinical parameters

Abstract

Background: Papillary thyroid microcarcinoma (PTMC) is the most common malignant subtype of thyroid cancer. Preoperative assessment of the risk of central compartment lymph node metastasis (CCLNM) can provide scientific support for personalized treatment decisions prior to microwave ablation of thyroid nodules. The objective of this study was to develop a predictive model for CCLNM in patients with solitary PTMC on the basis of a combination of ultrasound radiomics and clinical parameters.

Methods: We retrospectively analyzed data from 480 patients diagnosed with PTMC via postoperative pathological examination. The patients were randomly divided into a training set (n = 336) and a validation set (n = 144) at a 7:3 ratio. The cohort was stratified into a metastasis group and a nonmetastasis group on the basis of postoperative pathological results. Ultrasound radiomic features were extracted from routine thyroid ultrasound images, and multiple feature selection methods were applied to construct radiomic models for each group. Independent risk factors, along with radiomics features identified through multivariate logistic regression analysis, were subsequently refined through additional feature selection techniques to develop combined predictive models. The performance of each model was then evaluated.

Results: The combined model, which incorporates age, the presence of Hashimoto's thyroiditis (HT), and radiomics features selected via an optimal feature selection approach (percentage-based), exhibited superior predictive efficacy, with AUC values of 0.767 (95% CI: 0.716-0.818) in the training set and 0.729 (95% CI: 0.648-0.810) in the validation set.

Conclusion: A machine learning-based model combining ultrasound radiomics and clinical variables shows promise for the preoperative risk stratification of CCLNM in patients with PTMC. However, further validation in larger, more diverse cohorts is needed before clinical application.

Clinical trial number: Not applicable.

Keywords: Lymph node metastasis; Machine learning; Papillary thyroid carcinoma; Ultrasound.

Fig. 1

Ultrasound image of a thyroid nodule with the region of interest (ROI) outlined in red. The image shows the characteristics of the nodule, which are analyzed for radiomic feature extraction in the study

Fig. 2

ROC curve analysis of clinical parameters for predicting central lymph node metastasis in patients with thyroid micropapillary carcinoma. The graph compares the diagnostic performance of three factors: age (blue curve), HT (green curve), and the combined prediction probability (red curve)

Fig. 3

Feature importance rankings from the logistic regression model for predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma. Both clinical and radiomic features were included. Radiomic features were extracted via the Darwin platform (http://www.yizhun-ai.com/)

Fig. 4

ROC curve comparison of the model developed using radiomic features from ultrasound data and independent risk factors for predicting central lymph node metastasis in patients with thyroid micropapillary carcinoma. (a) ROC curve for the model applied to the training set (orange curve), (b) ROC curve for the model applied to the test set (black curve)

Fig. 5

Calibration plots of the model for predicting central lymph node metastasis in patients with thyroid micropapillary carcinoma. The points illustrate the alignment between the model’s predicted probabilities and the actual observed outcomes in both the training and test datasets