Mateus Pedro, Savino Mariachiara, Capocchiano Nikola Dino, Berbee Maaike, Gambacorta Maria Antonietta, Chiloiro Giuditta, Willems Yves C P, Damiani Andrea, Osong Biche, Dekker Andre, Bermejo Inigo
Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands.
Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
Med Phys. 2025 Aug;52(8):e18034. doi: 10.1002/mp.18034.
BACKGROUND: Organ preservation in patients with locally advanced rectal cancer has attracted interest due to improved quality of life and functional outcomes compared with total mesorectal excision. Hence, patients who achieve clinical complete response (cCR) after (chemo)radiotherapy are offered a watch-and-wait strategy. Those who are likely to fall short of the strict criteria of cCR and only achieve near complete response (NCR) might benefit from radiation boosting to avoid surgery. PURPOSE: To develop a prediction model that estimates the probability of NCR trained on data from different clinics. METHODS: We used data from two clinics (Maastro and Gemelli) on 1305 patients. We set up and used a federated learning infrastructure to leverage patient data from the clinics without transferring it. We used Bayesian networks for their capacity to combine expert knowledge with data and their ability to handle missing data. In this article, we propose a novel federated learning algorithm for Bayesian networks. In addition, we explore different approaches to handle missing data and train the models, combining expert elicited structures and those learnt from data. The discriminative performance of the models is reported using the area under the ROC curve (AUC). RESULTS: The model trained on data from both clinics and a structure learnt from data performed well (AUC 0.77). When using a structure elicited from an expert, the performance of the model decreased (AUC 0.68). Fine-tuning the expert structure with data led to a middle ground performance (AUC 0.72). Models trained on data from a single clinic failed to generalize when tested on data from the other clinic (AUCs 0.50 and 0.59). CONCLUSIONS: The model trained with federated learning showed good discriminative performance, which indicates that it could be useful to identify which patients with rectal cancer would benefit the most from a radiotherapy boost. This study shows that federated learning has the potential to lead to better models by allowing access to more data.
背景：与全直肠系膜切除术相比，局部晚期直肠癌患者的器官保留因生活质量和功能结局的改善而受到关注。因此，在（化疗）放疗后达到临床完全缓解（cCR）的患者可采用观察等待策略。那些可能未达到cCR的严格标准而仅实现接近完全缓解（NCR）的患者可能从加强放疗中获益以避免手术。 目的：开发一种预测模型，该模型基于来自不同诊所的数据训练来估计NCR的概率。 方法：我们使用了来自两家诊所（马斯特里赫特大学医学中心和杰梅利诊所）的1305例患者的数据。我们建立并使用了联邦学习基础设施，以利用诊所的患者数据而不进行数据传输。我们使用贝叶斯网络，因为它们能够将专家知识与数据相结合，并且能够处理缺失数据。在本文中，我们提出了一种用于贝叶斯网络的新型联邦学习算法。此外，我们探索了处理缺失数据和训练模型的不同方法，将专家得出的结构与从数据中学习到的结构相结合。使用ROC曲线下面积（AUC）报告模型的判别性能。 结果：在来自两家诊所的数据以及从数据中学习到的结构上训练的模型表现良好（AUC为0.77）。当使用从专家得出的结构时，模型的性能下降（AUC为0.68）。用数据对专家结构进行微调导致了中等性能（AUC为0.72）。在来自单个诊所的数据上训练的模型在使用来自另一个诊所的数据进行测试时无法泛化（AUC分别为0.50和0.59）。 结论：通过联邦学习训练的模型显示出良好的判别性能，这表明它可能有助于识别哪些直肠癌患者将从加强放疗中获益最大。这项研究表明，联邦学习有潜力通过允许访问更多数据而产生更好的模型。
Clin Orthop Relat Res. 2024-9-1
Health Technol Assess. 2006-9
BMJ Case Rep. 2023-7-10
Cochrane Database Syst Rev. 2022-5-20
J Healthc Inform Res. 2021
Ir J Med Sci. 2019-11
Transl Lung Cancer Res. 2018-4
Adv Drug Deliv Rev. 2016-1-14
Zotero 插件