Shrestha Keshika, Rifat H M Jabed Omur, Biswas Uzzal, Tiang Jun-Jiat, Nahid Abdullah-Al
Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh.
Centre for Wireless Technology, CoE for Intelligent Network, Faculty of Artificial Intelligence & Engineering, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malaysia.
Diagnostics (Basel). 2025 Jul 2;15(13):1684. doi: 10.3390/diagnostics15131684.
Differentiated Thyroid Cancer (DTC), comprising papillary and follicular carcinomas, is the most common type of thyroid cancer. This is highly infectious and increasing at a higher rate. Some patients experience recurrence even after undergoing successful treatment. Early signs of recurrence can be hard to identify, and the existing health care system cannot always identify it on time. Therefore, predicting its recurrence accurately and in its early stage is a significant clinical challenge. Numerous advanced technologies, such as machine learning, are being used to overcome this clinical challenge. Thus, this study presents a novel approach for predicting the recurrence of DTC. The key objective is to improve the prediction accuracy through hyperparameter optimization. In order to achieve this, we have used a metaheuristic algorithm, the whale optimization algorithm (WOA) and its modified version. The modifications that we introduced in the original WOA algorithm are a piecewise linear chaotic map for population initialization and inertia weight. Both of our algorithms optimize the hyperparameters of the Extreme Gradient Boosting (XGBoost) model to increase the overall performance. The proposed algorithms were applied to the dataset collected from the University of California, Irvine (UCI), Machine Learning Repository to predict the chances of recurrence for DTC. This dataset consists of 383 samples with a total of 16 features. Each feature captures the critical medical and demographic information. The model has shown an accuracy of 99% when optimized with WOA and 97% accuracy when optimized with the modified WOA. Furthermore, we have compared our work with other innovative works and validated the performance of our model for the prediction of DTC recurrence.
分化型甲状腺癌（DTC）包括乳头状癌和滤泡状癌，是最常见的甲状腺癌类型。这种癌症具有高度传染性，且发病率正以较高速度上升。一些患者即使在接受成功治疗后仍会复发。复发的早期迹象可能难以识别，现有的医疗保健系统也并非总能及时发现。因此，准确且早期预测其复发是一项重大的临床挑战。众多先进技术，如机器学习，正被用于克服这一临床挑战。因此，本研究提出了一种预测DTC复发的新方法。关键目标是通过超参数优化提高预测准确性。为实现这一目标，我们使用了一种元启发式算法——鲸鱼优化算法（WOA）及其改进版本。我们在原始WOA算法中引入的修改是用于种群初始化和惯性权重的分段线性混沌映射。我们的两种算法都对极端梯度提升（XGBoost）模型的超参数进行优化，以提高整体性能。所提出的算法应用于从加州大学欧文分校（UCI）机器学习库收集的数据集，以预测DTC的复发几率。该数据集由383个样本组成，共有16个特征。每个特征都捕获了关键的医学和人口统计学信息。当用WOA优化时，该模型的准确率为99%，用改进的WOA优化时准确率为97%。此外，我们还将我们的工作与其他创新工作进行了比较，并验证了我们模型在预测DTC复发方面的性能。
