Cao Yufeng, Kunaprayoon Dan, Xu Junliang, Ren Lei
Department of Radiation Oncology, University of Maryland, Baltimore, MD, USA.
Clin Transl Radiat Oncol. 2022 Dec 20;39:100565. doi: 10.1016/j.ctro.2022.100565. eCollection 2023 Mar.
AI modeling physicians' clinical decision-making (CDM) can improve the efficiency and accuracy of clinical practice or serve as a surrogate to provide initial consultations to patients seeking secondary opinions. In this study, we developed an AI network to model radiotherapy CDM and used dose prescription as an example to demonstrate its feasibility.
MATERIALS/METHODS: 152 patients with brain metastases treated by radiosurgery from 2017 to 2021 were included. CT images and tumor and organ-at-risk (OAR) contours were exported. Eight relevant clinical parameters were extracted and digitized, including age, numbers of lesions, performance status (ECOG), presence of symptoms, arrangement with surgery (pre- or post-surgery radiation therapy), re-treatment, primary cancer type, and metastasis to other sites. A 3D convolutional neural network (CNN) architecture was built using three encoding paths with the same kernel and filters to capture the different image and contour features. Specifically, one path was built to capture the tumor feature, including the size and location of the tumor, another path was built to capture the relative spatial relationship between the tumor and OARs, and the third path was built to capture the clinical parameters. The model combines information from three paths to predict dose prescription. The actual prescription in the patient record was used as ground truth for model training. The model performance was assessed by 19-fold-cross-validation, with each fold consisting of randomly selected 128 training, 16 validation, and 8 testing subjects.
The dose prescriptions of 152 patient cases included 48 cases with 1 × 24 Gy, 48 cases with 1 × 20-22 Gy, 32 cases with 3 × 9 Gy, and 24 cases with 5 × 6 Gy prescribed by 8 physicians. The AI model prescribed correctly for 124 (82 %) cases, including 44 (92 %) cases with 1 × 24 Gy, 36 (75 %) cases with 1 × 20-22 Gy, 25 (78 %) cases with 3 × 9 Gy, and 19 (79 %) cases with 5 × 6 Gy. Analysis of the failed cases showed the potential cause of practice variations across individual physicians, which were not accounted for in the model trained by the group data. Including clinical parameters improved the overall prediction accuracy by 20 %.
To our best knowledge, this is the first study to demonstrate the feasibility of AI in predicting dose prescription in CDM in radiation therapy. Such CDM models can serve as vital tools to address healthcare disparities by providing preliminary consultations to patients in underdeveloped areas or as a valuable quality assurance (QA) tool for physicians to cross-check intra- and inter-institution practices.
人工智能对医生临床决策（CDM）进行建模，可提高临床实践的效率和准确性，或作为一种替代方式，为寻求二次诊断意见的患者提供初步会诊。在本研究中，我们开发了一个人工智能网络来对放射治疗临床决策进行建模，并以剂量处方为例证明其可行性。
材料/方法：纳入2017年至2021年接受放射外科治疗的152例脑转移患者。导出CT图像以及肿瘤和危及器官（OAR）轮廓。提取并数字化八个相关临床参数，包括年龄、病灶数量、体能状态（ECOG）、症状表现、手术安排（术前或术后放射治疗）、再次治疗、原发癌类型以及是否转移至其他部位。使用具有相同内核和滤波器的三条编码路径构建三维卷积神经网络（CNN）架构，以捕捉不同的图像和轮廓特征。具体而言，构建一条路径来捕捉肿瘤特征，包括肿瘤的大小和位置；另一条路径用于捕捉肿瘤与危及器官之间的相对空间关系；第三条路径用于捕捉临床参数。该模型结合三条路径的信息来预测剂量处方。患者记录中的实际处方用作模型训练的真实数据。通过19折交叉验证评估模型性能，每一折由随机选择的128例训练对象、16例验证对象和8例测试对象组成。
152例患者的剂量处方包括8位医生开出的48例1×24 Gy、48例1×20 - 22 Gy、32例3×9 Gy和24例5×6 Gy。人工智能模型对124例（82%）病例开出了正确处方，其中包括44例（92%）1×24 Gy、36例（75%）1×20 - 22 Gy、25例（78%）3×9 Gy和19例（79%）5×6 Gy。对失败病例的分析显示了个体医生之间存在实践差异的潜在原因，而在基于群体数据训练的模型中并未考虑这些因素。纳入临床参数使总体预测准确率提高了20%。
据我们所知，这是第一项证明人工智能在预测放射治疗临床决策中的剂量处方方面具有可行性的研究。此类临床决策模型可作为重要工具，通过为欠发达地区的患者提供初步会诊来解决医疗保健差异问题，或者作为医生用于交叉核对机构内部和机构之间实践的有价值的质量保证（QA）工具。
