Predicting thyroid cancer recurrence using supervised CatBoost: A SHAP-based explainable AI approach
Open Access
- 30 May 2025
- journal article
- research article
- Published by Wolters Kluwer Health in Medicine
- Vol. 104 (22) , e42667
Abstract
Recurrence prediction in well-differentiated thyroid cancer remains a clinical challenge, necessitating more accurate and interpretable predictive models. This study investigates the use of a supervised CatBoost classifier to predict recurrence in well-differentiated thyroid cancer patients, comparing its performance against other ensemble models and employing Shapley Additive Explanations (SHAP) to enhance interpretability. A dataset comprising 383 patients with diverse demographic, clinical, and pathological variables was utilized. Data preprocessing steps included handling values and encoding categorical features. The dataset was split into training and testing sets using a 70:30 ratio. Model performance was evaluated using accuracy and area under the receiver operating characteristic curve. A comparative analysis was conducted with other ensemble methods, such as Extra Trees, LightGBM, and XGBoost. SHAP analysis was employed to determine feature importance and assess model interpretability at both the global and local levels. The supervised CatBoost classifier demonstrated superior performance, achieving an accuracy of 97% and an area under the receiver operating characteristic curve of 0.99, outperforming competing models. SHAP analysis revealed that treatment response (SHAP value: 2.077), risk stratification (SHAP value: 0.859), and lymph node involvement (N) (SHAP value: 0.596) were the most influential predictors of recurrence. Local SHAP analyses provided insight into individual predictions, highlighting that misclassification often resulted from overemphasizing a single factor while overlooking other clinically relevant indicators. The supervised CatBoost classifier demonstrated high predictive performance and enhanced interpretability through SHAP analysis. These findings underscore the importance of incorporating multiple predictive factors to improve recurrence risk assessment. While the model shows promise in personalizing thyroid cancer management, further validation on larger, more diverse datasets is warranted to ensure robustness.Keywords
This publication has 17 references indexed in Scilit:
- Stacked deep learning approach for efficient SARS-CoV-2 detection in blood samplesArtificial Intelligence in Medicine, 2024
- Corrigendum: Non-invasive detection of anemia using lip mucosa images transfer learning convolutional neural networksFrontiers in Big Data, 2023
- Using machine learning algorithm to analyse the hypothyroidism complications caused by radiotherapy in patients with head and neck cancerScientific Reports, 2023
- Machine learning for risk stratification of thyroid cancer patients: a 15-year cohort studyEuropean Archives of Oto-Rhino-Laryngology, 2023
- Anemia detection through non-invasive analysis of lip mucosa imagesFrontiers in Big Data, 2023
- Thyroid Cancer Polygenic Risk Score Improves Classification of Thyroid Nodules as Benign or MalignantThe Journal of Clinical Endocrinology & Metabolism, 2023
- Predictive factors for nodal recurrence in differentiated thyroid cancersCancer Treatment and Research Communications, 2023
- The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population‐based to a more “personalized” approach to cancer stagingCA: A Cancer Journal for Clinicians, 2017
- The Treatment of Well-Differentiated Thyroid CarcinomaDeutsches Ärzteblatt international, 2015
- Well-differentiated thyroid cancerCurrent Problems in Surgery, 1994