目前的屏幕检测肺结节管理指南为立即诊断检查或每隔 3、6 或 12 个月的随访提供了基于规则的建议。缺乏定制的就诊计划。利用强化学习 (RL) 制定个性化筛查时间表并评估基于 RL 的政策模型的有效性。利用嵌套病例对照设计，我们回顾性地识别了 308 名癌症患者，这些患者在国家肺部筛查试验中至少进行两轮筛查。我们建立了一个对照组，其中包括有结节的无癌患者，根据癌症诊断年份进行匹配（1:1）。通过生成 10,164 个序列决策集，我们训练了基于 RL 的策略模型，仅结合结节直径，结合结节外观（衰减和边缘）和/或患者信息（年龄、性别、吸烟状况、包龄和家族史） 。我们计算了误诊率、漏诊率和延误诊断率，并将基于强化学习的政策模型与基于规则的随访方案的性能进行了比较（国家综合癌症网络指南；中国肺癌筛查和早期发现指南）我们发现某些变量（例如，结节形状和患者吸烟包年数，超出指南方案中考虑的变量）与后续测试间隔的选择之间存在显着的相互作用，从而影响决策序列的质量。在验证中，一种基于强化学习的策略模型的误诊率为 12.3%，漏诊率为 9.7%，延迟诊断率为 11.7%。与两种基于规则的协议相比，三种性能最佳的基于强化学习的策略模型始终表现出针对基于疾病特征（良性或恶性）、结节表型（大小、形状和衰减）和个​​体的特定患者亚组的最佳性能。这项研究强调了使用基于强化学习的方法开发个性化肺癌筛查计划的潜力，这种方法既具有临床可解释性，又具有稳健的性能。我们的研究结果为增强当前癌症筛查系统提供了机会。© 2024 作者。约翰·威利出版的癌症医学

The current guidelines for managing screen-detected pulmonary nodules offer rule-based recommendations for immediate diagnostic work-up or follow-up at intervals of 3, 6, or 12 months. Customized visit plans are lacking.To develop individualized screening schedules using reinforcement learning (RL) and evaluate the effectiveness of RL-based policy models.Using a nested case-control design, we retrospectively identified 308 patients with cancer who had positive screening results in at least two screening rounds in the National Lung Screening Trial. We established a control group that included cancer-free patients with nodules, matched (1:1) according to the year of cancer diagnosis. By generating 10,164 sequence decision episodes, we trained RL-based policy models, incorporating nodule diameter alone, combined with nodule appearance (attenuation and margin) and/or patient information (age, sex, smoking status, pack-years, and family history). We calculated rates of misdiagnosis, missed diagnosis, and delayed diagnosis, and compared the performance of RL-based policy models with rule-based follow-up protocols (National Comprehensive Cancer Network guideline; China Guideline for the Screening and Early Detection of Lung Cancer).We identified significant interactions between certain variables (e.g., nodule shape and patient smoking pack-years, beyond those considered in guideline protocols) and the selection of follow-up testing intervals, thereby impacting the quality of the decision sequence. In validation, one RL-based policy model achieved rates of 12.3% for misdiagnosis, 9.7% for missed diagnosis, and 11.7% for delayed diagnosis. Compared with the two rule-based protocols, the three best-performing RL-based policy models consistently demonstrated optimal performance for specific patient subgroups based on disease characteristics (benign or malignant), nodule phenotypes (size, shape, and attenuation), and individual attributes.This study highlights the potential of using an RL-based approach that is both clinically interpretable and performance-robust to develop personalized lung cancer screening schedules. Our findings present opportunities for enhancing the current cancer screening system.© 2024 The Author(s). Cancer Medicine published by John Wiley & Sons Ltd.