研究复发或原发难治型经典霍奇金淋巴瘤（R/R cHL）患者的预后因素对于优化风险适应性治疗策略至关重要。我们利用基线定量18F-FDG PET放射组学特征和临床特征构建了一个预后模型，用于预测经化疗搭配自体干细胞移植治疗的R/R cHL患者的无进展生存期（PFS）。从基线PET中提取了代谢性肿瘤体积（MTV）和几个新型组学特征，代表了病灶间距离、体积和标准摄取值（SUV）的差异。我们使用向后逐步选择和逻辑回归的机器学习方法，对来自两个临床试验（NCT02280993和NCT00255723）的总计113名患者进行开发和训练模型。该模型在独立的外部队列中的69名患者（NCT01508312）上进行了验证。此外，我们还验证了四种不同的PET分割方法来计算组学特征。我们确定了一组高危患者，其3年PFS结果明显低于低危组的患者，分别为38.1％对88.4％，在训练队列中（p<0.001），以及38.5％对75.0％，在验证队列中（p=0.015）。低危组的总生存期也显著优于高危组（p=0.022和p<0.001）。我们提供了一个基于该模型计算个体患者风险评分的公式。总之，我们在大规模R/R cHL患者队列中开发了一个组学和临床特征相结合的PFS预后模型。该模型计算基于PET的风险概况，可应用于发展针对R/R cHL患者的风险分层治疗策略。©2023美国血液学会版权所有。

Investigating prognostic factors in relapsed or primary refractory classical Hodgkin lymphoma (R/R cHL) patients is essential to optimize risk-adapted treatment strategies. We built a prognostic model using baseline quantitative 18F-FDG PET radiomics features and clinical characteristics to predict progression free survival (PFS) in R/R cHL patients treated with salvage chemotherapy followed by autologous stem-cell transplant (ASCT). Metabolic tumor volume (MTV) and several novel radiomics dissemination features representing inter-lesional differences in distance, volume and standard uptake value (SUV) were extracted from the baseline PET. Machine learning using backward selection and logistic regression were applied to develop and train the model on a total of 113 patients from two clinical trials (NCT02280993 and NCT00255723). The model was validated on an independent external cohort of 69 patients (NCT01508312). In addition, we validated four different PET segmentation methods to calculate radiomics features. We identified a subset of high-risk patients with significant inferior 3-year PFS outcomes of 38.1% versus 88.4% for patients in the low-risk group in the training cohort (p<0.001), and 38.5% versus 75.0% in the validation cohort (p=0.015), respectively. The overall survival was also significantly better in the low-risk group (p=0.022 and p<0.001). We provide a formula to calculate a risk score for individual patients based on the model. In conclusion, we developed a prognostic model for PFS combining radiomics and clinical features in a large cohort of R/R cHL patients. This model calculates a PET-based risk profile and can be applied to develop risk-stratified treatment strategies for R/R cHL patients.Copyright © 2023 American Society of Hematology.