News Research Thyroid Disease Management Predictive Risk Models

Model predicts thyroid cancer in hard-to-reach lymph nodes

March 24, 2026 By Margery Weinstein 4 min read
Share Share via Email Share on Facebook Share on LinkedIn Share on Twitter
Objective:

To develop a machine learning model that predicts metastasis to lymph nodes around the entrance point of the recurrent laryngeal nerve in patients with clinically lymph node-negative papillary thyroid carcinoma.

Key Findings:
  • Metastasis to LN-epRLN occurred in 29 out of 149 patients (19%).
  • Larger tumors and younger age (≤45 years) were associated with LNM-epRLN.
  • The Random Forest model achieved an area under the curve of 0.92 in predicting LNM-epRLN.
Interpretation:

The Random Forest model can assist surgeons in predicting lymph node metastasis, aiding in intraoperative decision-making while considering oncologic outcomes and nerve preservation.

Limitations:
  • Conducted at a single center, limiting generalizability.
  • Retrospective data may introduce biases.
  • Small number of patients with LNM-epRLN (n = 29).
  • Model sensitivity in the test set was 0.50.
Conclusion:

The interpretable Random Forest-based ML model may enhance surgical decision-making regarding LN-epRLN dissection.

AACE Endocrine AI is published by Conexiant under a license arrangement with the American Association of Clinical Endocrinology, Inc. (AACE®). The ideas and opinions expressed in AACE Endocrine AI do not necessarily reflect those of Conexiant or AACE. For more information, see Policies.

Related Content