通过识别高风险个体，在癌症筛查计划中可以改进筛查方法，从而实现根据风险进行筛查强度的调整。之前的研究引入了一个预后模型，利用性别、年龄和两个前期粪便血红蛋白浓度来预测下一轮结直肠癌（CRC）筛查的风险。利用3轮筛查数据，该模型在预测高级别新生病变（AN）时取得了接收者操作特征曲线（AUC）为0.78的成绩。我们验证了现有的逻辑回归（LR）模型，并尝试利用更灵活的机器学习方法来改进它。我们使用来自荷兰CRC筛查计划直到2018年的219,257名第三轮参与者的最新数据，对现有的LR和新开发的随机森林（RF）模型进行了训练。对于这两个模型，我们分别使用了2018年以后的1,137,599名第三轮参与者和从2020年开始的192,793名第四轮参与者进行了两个独立的样本外验证。我们评估了AUC和预测高风险组的AN和CRC的相对风险。对于2018年以后的第三轮参与者，预测AN的AUC值分别为0.77（95% CI：0.76-0.77）和0.77（95% CI：0.77-0.77），使用LR和RF模型。对于第四轮参与者，LR和RF模型的AUC值分别为0.73（95% CI：0.72-0.74）和0.73（95% CI：0.72-0.74）。对于两个模型，预测风险最高的5%相比于平均值有7倍的AN风险，而最低的80%相对于人群平均值的风险则低于人群平均值。LR是肠道筛查计划中一种有效的风险预测方法。尽管预测性能略有下降，但LR模型仍然能够有效地预测随后的筛查周期的风险。与LR相比，RF并没有改善CRC风险预测，可能是由于可用解释变量的数量有限。由于其可解释性，LR仍然是首选的预测工具。版权所有© 2023年 Elsevier B.V. 保留所有权利。

Identification of individuals at elevated risk can improve cancer screening programmes by permitting risk-adjusted screening intensities. Previous work introduced a prognostic model using sex, age and two preceding faecal haemoglobin concentrations to predict the risk of colorectal cancer (CRC) in the next screening round. Using data of 3 screening rounds, this model attained an area under the receiver-operating-characteristic curve (AUC) of 0.78 for predicting advanced neoplasia (AN). We validated this existing logistic regression (LR) model and attempted to improve it by applying a more flexible machine-learning approach.We trained an existing LR and a newly developed random forest (RF) model using updated data from 219,257 third-round participants of the Dutch CRC screening programme until 2018. For both models, we performed two separate out-of-sample validations using 1,137,599 third-round participants after 2018 and 192,793 fourth-round participants from 2020 onwards. We evaluated the AUC and relative risks of the predicted high-risk groups for the outcomes AN and CRC.For third-round participants after 2018, the AUC for predicting AN was 0.77 (95% CI: 0.76-0.77) using LR and 0.77 (95% CI: 0.77-0.77) using RF. For fourth-round participants, the AUCs were 0.73 (95% CI: 0.72-0.74) and 0.73 (95% CI: 0.72-0.74) for the LR and RF models, respectively. For both models, the 5% with the highest predicted risk had a 7-fold risk of AN compared to average, whereas the lowest 80% had a risk below the population average for third-round participants.The LR is a valid risk prediction method in stool-based screening programmes. Although predictive performance declined marginally, the LR model still effectively predicted risk in subsequent screening rounds. An RF did not improve CRC risk prediction compared to an LR, probably due to the limited number of available explanatory variables. The LR remains the preferred prediction tool because of its interpretability.Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved.