Explainable Machine Learning Models for Predicting Recurrence in Differentiated Thyroid Cancer

Year 2024, , 468 - 473, 24.09.2024

Ahmet Kadir Arslan , Cemil Çolak

https://doi.org/10.37990/medr.1525801

Abstract

Aim: Differentiated thyroid cancer (DTC) is a common type of cancer that originates in the thyroid gland. This study aimed to predict the recurrence of differentiated thyroid carcinoma, in patient with well-DTC, using explainable machine learning (XAI) models.
Material and Method: The study utilized a dataset from the UCI Machine Learning Repository, which included 383 patients and 13 candidate predictors. After a variable selection process using distance correlation, only four predictors (Response, Risk, T, and N) were retained for model building. Two XAI models, Fast Interpretable Greedy-Tree Sums (FIGS) and Explainable Boosting Machines (EBM), were employed.
Results: The EBM model slightly outperformed the FIGS model in terms of accuracy. The study found that the most influential predictors of Well-DTC recurrence were the response to DTC treatment, risk status according to the American Thyroid Association classification, tumor size (T), and lymph node metastasis (N).
Conclusion: In conclusion, this study successfully identified key risk factors for DTC recurrence using XAI models, providing interpretable insights for clinical decision-making and potential for personalized treatment strategies.

Keywords

Differentiated thyroid cancer, explainable machine learning, risk factors, explainable boosting machine, fast interpretable greedy-tree sums

References

• Cabanillas ME, McFadden DG, Durante C. Thyroid cancer. The Lancet. 2016;388:2783-95.
• Nguyen QT, Lee EJ, Huang MG, et al. Diagnosis and treatment of patients with thyroid cancer. Am Health Drug Benefits. 2015;8:30-40.
• Chen DW, Lang BH, McLeod DS, et al. Thyroid cancer. Lancet. 2023;401:1531-44.
• Burns WR, Zeiger MA. Differentiated thyroid cancer. Semin Oncol. 2010:557-66.
• Schmidbauer B, Menhart K, Hellwig D, Grosse J. Differentiated thyroid cancer—treatment: state of the art. Int J Mol Sci. 2017;18:1292.
• Panagiotakopoulos T, Chorti A, Pliakos I, et al. Thyroid cancer and pregnancy: a systematic ten-year-review. Gland surgery. 2024;13:1097-107.
• Caron N, Clark O. Well differentiated thyroid cancer. Scand J Surg. 2004;93:261-71.
• Belle V, Papantonis I. Principles and practice of explainable machine learning. Frontiers in big Data. 2021;4:688969.
• Roscher R, Bohn B, Duarte MF, Garcke J. Explainable machine learning for scientific insights and discoveries. Ieee Access. 2020;8:42200-16.
• Akter S, Mustafa HA. Analysis and interpretability of machine learning models to classify thyroid disease. Plos One. 2024;19:e0300670.
• Sankar S, Sathyalakshmi S. A study on the explainability of thyroid cancer prediction: SHAP values and association-rule based feature integration framework. Computers, Materials & Continua. 2024;79:3111-38.
• Borzooei S, Tarokhian A. Differentiated Thyroid Cancer Recurrence (Dataset). UCI Machine Learning Repository. 2023. doi: 10.24432/C5632J
• Borzooei S, Briganti G, Golparian M, et al. Machine learning for risk stratification of thyroid cancer patients: a 15-year cohort study. Eur Arch Otorhinolaryngol. 2024;281:2095-104.
• Székely GJ, Rizzo ML, Bakirov NK. Measuring and testing dependence by correlation of distances. 2007;35:2769-94.
• Tan YS, Singh C, Nasseri K, et al. Fast interpretable greedy-tree sums (figs). arXiv. 2023;arXiv:2201.11931.
• Lou Y, Caruana R, Gehrke J, Hooker G. Accurate intelligible models with pairwise interactions. 2013:623-31.
• Nori H, Jenkins S, Koch P, Caruana R. Interpretml: a unified framework for machine learning interpretability. arXiv. 2019;arXiv:190909223.
• Sudjianto A, Zhang A, Yang Z, et al. PiML toolbox for interpretable machine learning model development and diagnostics. arXiv. 2023;arXiv:230504214.
• Smallridge RC, Ain KB, Asa SL, et al. American Thyroid Association guidelines for management of patients with anaplastic thyroid cancer. Thyroid. 2012;22:1104-39.
• Steinschneider M, Pitaro J, Koren S, et al. Differentiated thyroid cancer with biochemical incomplete response: clinico-pathological characteristics and long term disease outcomes. Cancers. 2021;13:5422.
• Campopiano MC, Ghirri A, Prete A, et al. Active surveillance in differentiated thyroid cancer: a strategy applicable to all treatment categories response. Frontiers in Endocrinol. 2023;14:1133958.
• Onitilo AA, Engel JM, Lundgren CI, et al. Simplifying the TNM system for clinical use in differentiated thyroid cancer. J Clin Oncol. 2009;27:1872-8.
• Grønlund MP, Jensen JS, Hahn CH, et al. Risk factors for recurrence of follicular thyroid cancer: a systematic review. Thyroid. 2021;31:1523-30.
• Taboni S, Paderno A, Giordano D, et al. Differentiated thyroid cancer: the role of ATA nodal risk factors in N1b patients. Laryngoscope. 2021;131:E1029-34.
• Sibarani IJB, Suharjito S. Enhancing predictive accuracy for differentiated thyroid cancer (DTC) recurrence through advanced data mining techniques. TIN: Terapan Informatika Nusantara. 2024;5:11-22.