A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS).
A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS).
复制标题
用于反应自适应放射治疗（ARCliDS）中AI辅助决策的临床决策支持系统。
DOI：
10.1038/s41598-023-32032-6
复制
发表时间：
2023-03-31
影响因子：
4.6
通讯作者：
El Naqa, Issam
中科院分区：
文献类型：
--
作者：
Niraula, Dipesh;Sun, Wenbo;Jin, Jionghua;Dinov, Ivo D.;Cuneo, Kyle;Jamaluddin, Jamalina;Matuszak, Martha M.;Luo, Yi;Lawrence, Theodore S.;Jolly, Shruti;Ten Haken, Randall K.;El Naqa, Issam
肿瘤动态治疗方案（DTR）中涉及的变量多、治疗反应的不确定性和患者间异质性对客观决策提出了挑战。先进的机器学习分析与信息丰富的密集多组学数据相结合，有能力克服这些挑战。我们已经开发了一个全面的基于人工智能（AI）的最佳决策框架，用于协助肿瘤学家进行DTR。在这项工作中，我们展示了建议的框架知识为基础的响应自适应放射治疗（KBR-ART）的应用程序，通过开发一个交互式的软件工具，自适应放射治疗临床决策支持（ARCliDS）。ARCliDS由两个主要部分组成：实时决策环境（ARTE）和最优决策器（ODM）。ARTE被设计为马尔可夫决策过程，并通过监督学习进行建模。给定患者的治疗前和治疗期间的信息，ARTE可以估计选定的每日剂量值（辐射分数大小）的治疗结果。ODM是使用强化学习制定的，并在ARTE上进行训练。ODM可以推荐最佳的每日剂量调整，以最大限度地提高肿瘤局部控制概率，并最大限度地减少副作用。图神经网络（GNN）被应用于利用特征间的关系，以提高建模性能，并设计了一种新的双GNN架构，以避免非物理治疗反应。大小为117和292的数据集分别来自非小细胞肺癌（NSCLC）患者的自适应RT和肝细胞癌（HCC）患者的自适应立体定向体RT（SBRT）的两项临床试验。对于训练和验证，67名NSCLC患者的297个特征和71名HCC患者的110个特征的密集数据可用。为了增加ODM训练的样本量，我们应用生成对抗网络来生成10，000名合成患者。ODM在合成患者上进行训练，并在原始数据集上进行验证。我们发现，双GNN架构能够纠正非物理剂量反应趋势，并改善ARCliDS推荐。ARCliDS建议和使用双GNN报告的临床决策之间的平均均方根差（RMSD）为0.61 [0.03]戈伊/frac。（平均值[sem]），适应性SBRT HCC为2.96 [0.42]戈伊/frac，而单一GNN的RSD为0.97 [0.12]戈伊/frac和4.75 [0.16]戈伊/frac，分别总体而言，对于NSCLC和HCC，具有双GNN的ARCliDS能够分别重现36%和50%的良好临床决策（局部控制和无副作用），并改善74%和30%的不良临床决策。总之，ARCliDS是第一个基于网络的软件，致力于帮助KBR-ART与多组学数据。ARCliDS可以从报告的临床决策中学习，并促进AI辅助的临床决策，以改善DTR的结局。
Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient’s pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN’s RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.
登录
查看更多内容
DOI：
10.1146/annurev-statistics-022513-115553
发表时间：
2014
影响因子：
7.9
作者：
Chakraborty B;Murphy SA
通讯作者：
Murphy SA
DOI：
10.1259/bjr.20220239
发表时间：
2022-10-01
期刊：
The British journal of radiology
影响因子：
--
作者：
通讯作者：
--
影响因子：
3.8
作者：
Tseng HH;Luo Y;Cui S;Chien JT;Ten Haken RK;Naqa IE
通讯作者：
Naqa IE
影响因子：
4.7
作者：
Tseng HH;Luo Y;Ten Haken RK;El Naqa I
通讯作者：
El Naqa I
影响因子：
3.8
作者：
Luo Y;McShan DL;Matuszak MM;Ray D;Lawrence TS;Jolly S;Kong FM;Ten Haken RK;El Naqa I
通讯作者：
El Naqa I