Amiri Sepideh, Abdolali Fatemeh, Neshastehriz Ali, Nikoofar Alireza, Farahani Saeid, Firoozabadi Leila Alipour, Askarabad Zahra Alaei, Cheraghi Susan
Department of Computer Sciences, University of Copenhagen, Copenhagen, Denmark.
Department of Radiology and Diagnostic Imaging, Faculty of Medicine and Dentistry, Alberta University, Edmonton, AB, Canada.
J Cancer Res Ther. 2023 Jul-Sep;19(5):1219-1225. doi: 10.4103/jcrt.jcrt_2298_21.
The present study aimed to assess machine learning (ML) models according to radiomic features to predict ototoxicity using auditory brain stem responses (ABRs) in patients with radiation therapy (RT) for head-and-neck cancers.
The ABR test was performed on 50 patients having head-and-neck RT. Radiomic features were extracted from the brain stem in computed tomography images to generate a radiomic signature. Moreover, accuracy, sensitivity, specificity, the area under the curve, and mean cross-validation were used to evaluate six different ML models.
Out of 50 patients, 21 participants experienced ototoxicity. Furthermore, 140 radiomic features were extracted from the segmented area. Among the six ML models, the Random Forest method with 77% accuracy provided the best result.
According to the ML approach, we showed the relatively high prediction power of the radiomic features in radiation-induced ototoxicity. To better predict the outcomes, future studies on a larger number of participants are recommended.
本研究旨在根据放射组学特征评估机器学习（ML）模型，以利用听觉脑干反应（ABR）预测头颈部癌放射治疗（RT）患者的耳毒性。
对50名头颈部放疗患者进行ABR测试。从计算机断层扫描图像中的脑干提取放射组学特征，以生成放射组学特征图谱。此外，使用准确性、敏感性、特异性、曲线下面积和平均交叉验证来评估六种不同的ML模型。
50名患者中，21名出现耳毒性。此外，从分割区域提取了140个放射组学特征。在六种ML模型中，准确率为77%的随机森林方法提供了最佳结果。
根据ML方法，我们展示了放射组学特征在放射性耳毒性中的较高预测能力。为了更好地预测结果，建议未来对更多参与者进行研究。
