Examining Thyroid Cancer Diagnosis: Harnessing Machine Learning for Early Risk Detection

Abstract

Thyroid cancer is a common type of cancer that begins to form in thyroid gland cells, which has been seen frequently in recent years. Thyroid cancer is a malignancy that develops in the cells of the thyroid gland and is an increasing health problem worldwide. Thyroid cancer grows slowly and usually has no symptoms in the early stages. Therefore, detecting thyroid cancer in the early stages is of great importance. Thyroid cancer is a type of disease with high treatment success when the risk is detected at an early stage, and correct diagnosis and treatment is applied to prevent cancer. Therefore, this study aimed to detect the risk of thyroid cancer at an early stage with the help of computer-aided systems. Thanks to these systems, experts' workloads will be lightened, and the errors experts can make will be minimized. This study used four machine learning methods to determine the risk stage of thyroid cancer. The dataset used in the study is a public data set and consists of 16 features and 383 samples. Different performance measurement metrics were used to evaluate the performance of the models. As a result, when the results obtained in the study were examined, it was shown that machine learning methods achieved competitive results in detecting the risk of thyroid cancer.

Keywords

• Artificial Intelligence
• Cancer
• Classification
• Machine Learning
• Thyroid

References

1. [1] Cabanillas, M.E., D.G. McFadden, and C. Durante, Thyroid cancer. The Lancet, 2016. 388(10061): p. 2783-2795.
2. [2] Girotto, N., Risk Factors for Thyroid Cancer: What Do We Know So Far? Acta Clinica Croatica, 2020. 59(Suppl 1): p. 66-72.
3. [3] Kim, W.B., et al., Ultrasonographic screening for detection of thyroid cancer in patients with Graves’ disease. Clinical endocrinology, 2004. 60(6): p. 719-725.
4. [4] Hall, S.F., et al., Increasing detection and increasing incidence in thyroid cancer. World journal of surgery, 2009. 33: p. 2567-2571.
5. [5] Zhang, X., et al., Multi-channel convolutional neural network architectures for thyroid cancer detection. Plos one, 2022. 17(1): p. e0262128.
6. [6] Ahmad, W., et al., A novel hybrid decision support system for thyroid disease forecasting. Soft Computing, 2018. 22: p. 5377-5383.
7. [7] Hearst, M.A., et al., Support vector machines. IEEE Intelligent Systems and their applications, 1998. 13(4): p. 18-28.
8. [8] Haasdonk, B., Feature space interpretation of SVMs with indefinite kernels. IEEE Transactions on pattern analysis and machine intelligence, 2005. 27(4): p. 482-492.

9. [9] Rish, I. An empirical study of the naive Bayes classifier. in IJCAI 2001 workshop on empirical methods in artificial intelligence. 2001. Citeseer.
10. [10] Jadhav, S.D. and H. Channe, Comparative study of K-NN, naive Bayes and decision tree classification techniques. International Journal of Science and Research (IJSR), 2016. 5(1): p. 1842-1845.
11. [11] Quinlan, J.R., Decision trees and decision-making. IEEE Transactions on Systems, Man, and Cybernetics, 1990. 20(2): p. 339-346.
12. [12] Sagi, O. and L. Rokach, Explainable decision forest: Transforming a decision forest into an interpretable tree. Information Fusion, 2020. 61: p. 124-138.
13. [13] Choi, R.Y., et al., Introduction to machine learning, neural networks, and deep learning. Translational vision science & technology, 2020. 9(2): p. 14-14.
14. [14] Guarnieri, S., F. Piazza, and A. Uncini, Multilayer feedforward networks with adaptive spline activation function. IEEE Transactions on Neural Networks, 1999. 10(3): p. 672-683.
15. [15] Geiger, B.C., On information plane analyses of neural network classifiers—A review. IEEE Transactions on Neural Networks and Learning Systems, 2021. 33(12): p. 7039-7051.
16. [16] Url, https://archive.ics.uci.edu/dataset/915/differentiated+thyroid+cancer+recurrences.
17. [17] Borzooei, S., et al., Machine learning for risk stratification of thyroid cancer patients: a 15-year cohort study. European Archives of Oto-Rhino-Laryngology, 2024. 281(4): p. 2095-2104.
18. [18] Yildirim, M., Automatic classification and diagnosis of heart valve diseases using heart sounds with MFCC and proposed deep model. Concurrency and Computation: Practice and Experience, 2022. 34(24): p. e7232.