Improvements in radiotherapy delivery have enabled higher therapeutic doses and improved efficacy, contributing to the growing number of long-term cancer survivors. These survivors are at risk of developing late toxicity from radiotherapy, and the inability to predict who is most susceptible results in substantial impact on quality of life and limits further curative dose escalation. A predictive assay or algorithm for normal tissue radiosensitivity would allow more personalized treatment planning, reducing the burden of late toxicity, and improving the therapeutic index. Progress over the last 10 years has shown that the etiology of late clinical radiotoxicity is multifactorial and informs development of predictive models that combine information on treatment (eg, dose, adjuvant treatment), demographic and health behaviors (eg, smoking, age), co-morbidities (eg, diabetes, collagen vascular disease), and biology (eg, genetics, ex vivo functional assays). AI has emerged as a useful tool and is facilitating extraction of signal from large datasets and development of high-level multivariable models. Some models are progressing to evaluation in clinical trials, and we anticipate adoption of these into the clinical workflow in the coming years. Information on predicted risk of toxicity could prompt modification of radiotherapy delivery (eg, use of protons, altered dose and/or fractionation, reduced volume) or, in rare instances of very high predicted risk, avoidance of radiotherapy. Risk information can also be used to assist treatment decision-making for cancers where efficacy of radiotherapy is equivalent to other treatments (eg, low-risk prostate cancer) and can be used to guide follow-up screening in instances where radiotherapy is still the best choice to maximize tumor control probability. Here, we review promising predictive assays for clinical radiotoxicity and highlight studies that are progressing to develop an evidence base for clinical utility.

放射治疗的改进提高了治疗剂量并提高了疗效，从而使长期癌症幸存者的数量不断增加。这些幸存者面临着因放射治疗而出现晚期毒性的风险，并且无法预测谁最容易受到影响，从而对生活质量产生重大影响，并限制了治疗剂量的进一步增加。正常组织放射敏感性的预测测定或算法将允许更加个性化的治疗计划，减少晚期毒性的负担，并改善治疗指数。过去 10 年的进展表明，晚期临床放射毒性的病因是多因素的，并为预测模型的开发提供了信息，该模型结合了治疗（例如剂量、辅助治疗）、人口和健康行为（例如吸烟、年龄）等信息。 -发病率（例如，糖尿病、胶原血管疾病）和生物学（例如，遗传学、离体功能测定）。人工智能已成为一种有用的工具，正在促进从大型数据集中提取信号和开发高级多变量模型。一些模型正在临床试验中进行评估，我们预计在未来几年将这些技术应用到临床工作流程中。有关预测毒性风险的信息可能会促使放射治疗实施的修改（例如，使用质子、改变剂量和/或分次、减少体积），或者在预测风险非常高的罕见情况下，避免放射治疗。风险信息还可用于协助放射治疗的疗效与其他治疗（例如低风险前列腺癌）相当的癌症的治疗决策，并且可用于在放射治疗仍然是最佳治疗的情况下指导后续筛查选择最大化肿瘤控制概率。在这里，我们回顾了有前景的临床放射毒性预测分析，并重点介绍了正在为临床实用性建立证据基础的研究。