本研究旨在整合放射组学和剂量组学特征，开发鼻咽癌放疗后口干症（XM）的预测模型。探讨不同特征提取方法和剂量范围对性能的影响。对363例鼻咽癌患者的数据进行回顾性分析。我们首创了剂量分段策略，将总体剂量分布 (OD) 分为四个分段剂量分布 (SD)，间隔为 15 Gy。使用手动定义和深度学习提取特征，应用OD或SD并整合放射组学和剂量组学，产生相应的特征分数（手动定义放射组学，MDR；手动定义剂量组学，MDD；基于深度学习的放射组学，DLR；基于深度学习的剂量组学） ，DLD）。随后，通过结合特征和模型类型（随机森林和支持向量机）开发了 18 个模型。在 OD 下，O(DLR_DLD) 表现出了卓越的性能，最佳曲线下面积（AUC）为 0.81，平均 AUC 为 0.71 。在 SD 中，S(DLR_DLD) 超越了其他模型，实现了 0.90 的最佳 AUC 和 0.85 的平均 AUC。因此，将剂量组学整合到放射组学中可以增强预测功效。剂量分段策略可以促进提取更深刻的信息。这表明 ScoreDLR 和 ScoreMDR 与 XM 呈负相关，而源自超过 15 Gy 的 SD 的 ScoreDLD 与 XM 呈正相关。对于特征提取，深度学习优于手动定义。版权所有 © 2024 Elsevier Ltd。保留所有权利。

This study aimed to integrate radiomics and dosiomics features to develop a predictive model for xerostomia (XM) in nasopharyngeal carcinoma after radiotherapy. It explores the influence of distinct feature extraction methods and dose ranges on the performance.Data from 363 patients with nasopharyngeal carcinoma were retrospectively analyzed. We pioneered a dose-segmentation strategy, where the overall dose distribution (OD) was divided into four segmental dose distributions (SDs) at intervals of 15 Gy. Features were extracted using manual definition and deep learning, applying OD or SD and integrating radiomics and dosiomics, yielding corresponding feature scores (manually defined radiomics, MDR; manually defined dosiomics, MDD; deep learning-based radiomics, DLR; deep learning-based dosiomics, DLD). Subsequently, 18 models were developed by combining features and model types (random forest and support vector machine).Under OD, O(DLR_DLD) demonstrated exceptional performance, with an optimal area under the curve (AUC) of 0.81 and an average AUC of 0.71. Within SD, S(DLR_DLD) surpassed the other models, achieving an optimal AUC of 0.90 and an average AUC of 0.85. Therefore, the integration of dosiomics into radiomics can augment predictive efficacy. The dose-segmentation strategy can facilitate the extraction of more profound information. This indicates that ScoreDLR and ScoreMDR were negatively associated with XM, whereas ScoreDLD, derived from SD exceeding 15 Gy, displayed a positive association with XM. For feature extraction, deep learning was superior to manual definition.Copyright © 2024 Elsevier Ltd. All rights reserved.