Skip to main content

ORIGINAL RESEARCH article

Front. Endocrinol.
Sec. Thyroid Endocrinology
Volume 15 - 2024 | doi: 10.3389/fendo.2024.1433192
This article is part of the Research Topic Advances in precision medicine in the management of thyroid nodules and thyroid cancer View all 25 articles

A prognostic model for thermal ablation of benign thyroid nodules based on interpretable machine learning

Provisionally accepted
Zuolin Li Zuolin Li 1Wei Nie Wei Nie 2Qingfa Liu Qingfa Liu 3Min Lin Min Lin 1Xiaolian Li Xiaolian Li 1Jiantang Zhang Jiantang Zhang 1Tengfu Liu Tengfu Liu 1Yongluo Deng Yongluo Deng 1Shuiping Li Shuiping Li 1*
  • 1 Department of Ultrasound, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, Fujian Province, China
  • 2 Department of Information, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, China
  • 3 School of Information Engineering, Minxi Vocational & Technical College, Longyan, China

The final, formatted version of the article will be published soon.

    The detection rate of benign thyroid nodules is increasing every year, with some affected patients experiencing symptoms. Ultrasound-guided thermal ablation can reduce the volume of nodules to alleviate symptoms. As the degree and speed of lesion absorption vary greatly between individuals, an effective model to predict curative effect after ablation is lacking. This study aims to predict the efficacy of ultrasound-guided thermal ablation for benign thyroid nodules using machine learning and explain the characteristics affecting the nodule volume reduction ratio (VRR).The clinical and ultrasonic characteristics of patients who underwent ultrasound-guided thermal ablation of benign thyroid nodules at our hospital between January 2020 and January 2023 were recorded.Measurements: Six machine learning models (logistic regression, support vector machine, decision tree, random forest, eXtreme Gradient Boosting [XGBoost], and Light Gradient Boosting Machine [LGBM]) were constructed to predict efficacy; the effectiveness of each model was evaluated and the optimal model selected. SHapley Additive exPlanations (SHAP) was used to visualize the decision process of the optimal model and analyze the characteristics affecting the VRR.In total, 518 benign thyroid nodules were included: 356 in the satisfactory group (VRR ≥70% 1 year after operation) and 162 in the unsatisfactory group. The optimal XGBoost model predicted satisfactory efficacy with 78.9% accuracy, 88.8% precision, 79.8% recall rate, an F1 value of 0.84 F1, and an area under the curve of 0.86. The top five characteristics that affected VRRs were the proportion of solid components < 20%, initial nodule volume, blood flow score, peripheral blood flow pattern, and proportion of solid components ~50-80%.The models, based on interpretable machine learning, predicted the VRR after thermal ablation for benign thyroid nodules, which provided a reference for preoperative treatment decisions.

    Keywords: artificial intelligence, Benign thyroid nodule, machine learning, thyroid nodules, Thermal ablation, Ultrasound-guided, Volume reduction rate

    Received: 15 May 2024; Accepted: 01 Aug 2024.

    Copyright: © 2024 Li, Nie, Liu, Lin, Li, Zhang, Liu, Deng and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Shuiping Li, Department of Ultrasound, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, Fujian Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.