A machine learning model utilizing delphian lymph node characteristics to predict contralateral central lymph node metastasis in papillary thyroid carcinoma: A prospective multicenter study

Background: This study aimed to use artificial intelligence (AI) to integrate various radiological and clinical pathological data to identify effective predictors of contralateral cervical lymph node metastasis (CCLNM) in patients with papillary thyroid carcinoma (PTC) and to establish a clinically applicable model to guide the extent of surgery. Methods: This prospective cohort study included 603 patients with PTC from three centers. Clinical, pathological, and ultrasonographic data were collected and utilized to develop a machine learning (ML) model for predicting CCLNM. Model development at the internal center utilized logistic regression along with other ML algorithms. Diagnostic efficacy was compared among these methods, leading to the adoption of the final model (random forest). This model was subject to AI interpretation and externally validated at other centers. Results: CCLNM was associated with multiple pathological factors. The Delphian lymph node metastasis ratio, ipsilateral cervical lymph node metastasis number, and presence of ipsilateral cervical lymph node metastasis were independent risk factors for CCLNM. Following feature selection, a Delphian lymph node-CCLNM (D-CCLNM) model was established using the Random forest algorithm based on five attributes. The D-CCLNM model demonstrated the highest area under the curve (AUC; 0.9273) in the training cohort and exhibited high predictive accuracy, with AUCs of 0.8907 and 0.9247 in the external and validation cohorts, respectively. Conclusions: We developed a new, effective method that uses ML to predict CCLNM in patients with PTC. This approach integrates data from Delphian lymph nodes and clinical characteristics, offering a foundation for guiding surgical decisions, and is conveniently applicable in clinical settings.