重要性：早发性结直肠癌 (EOCRC) 的发病率在 20 世纪 90 年代中期急剧上升，并且仍在持续增加，现已在许多国家引起关注。到 2030 年，25% 被诊断患有直肠癌的美国患者年龄将小于 49 岁。绝大多数 EOCRC 在种系癌易感性突变（例如林奇综合征）或炎症性肠病（IBD）患者中未发现。因此，环境或生活方式因素被怀疑是驱动因素。肥胖、久坐的生活方式、糖尿病、吸烟、饮酒或抗生素都会影响肠道微生物组。然而，这些自 20 世纪 50 年代以来一直存在的因素尚未与 EOCRC 突然增加有最终的联系。急剧增加表明为年轻人引入了新的风险因素。我们假设，驱动因素可能是药物在遗传易感的年轻人亚群中的脱靶效应（在普通人群中使用之前需要获得监管部门的批准，或者是先前批准的药物的标签外使用）。如果药剂是 EOCRC 驱动因素，则可以采用监管风险缓解策略。评估药剂作为 EOCRC 风险因素的可能性。设计：病例对照研究。包括人口统计、合并症和完整配药历史（处方药和非处方药）在内的数据均从 Maccabi Healthcare Services (MHS) 的电子病历数据库中获得，该数据库是国家授权的医疗服务提供者，覆盖以色列人口的 26% 。参与者：确定了 2001-2019 年间诊断的 941 例 EOCRC 病例（<50 岁），并与 9410 例对照进行 1:10 的密度匹配。 IBD 患者和已知患有遗传性癌症易感综合征的患者被排除在外。方法：使用基于梯度提升决策树的先进机器学习算法，结合贝叶斯模型优化和重复数据采样，对非常高维的药物配药数据进行排序，以识别与 EOCRC 一致相关的特定药物组，同时允许协同作用或药物之间的拮抗相互作用。已确定药物类别的优势比是从条件逻辑回归模型中获得的。在 800 多种药物类别中，我们在独立训练的模型中确定了与 EOCRC 风险一致 (>50%) 相关的几个类别。药物组之间的相互作用似乎并未显着影响风险。在我们的分析中，与 EOCRC 始终呈正相关的药物组包括 β 受体阻滞剂（OR=1.94，95% CI=1.37-2.77，p<0.01）和缬草（Valeriana officinalis），OR=1.61，95% CI=1.15-2.25 ，p=0.01）；抗生素与 EOCRC 风险并不一致。我们的分析表明 EOCRC 的发生可能与之前使用特定药物有关。应采用额外的分析来验证结果。然后需要确定候选药剂诱导 EOCRC 的作用机制。

Importance: The incidence of early-onset colorectal cancer (EOCRC) rose abruptly in the mid-1990s, is continuing to increase, and has now been noted in many countries. By 2030, 25% of American patients diagnosed with rectal cancer will be < 49 years old. The large majority of EOCRC are not found in germline cancer susceptibility mutation (eg Lynch Syndrome) or inflammatory bowel disease (IBD) patients. Thus, environmental or lifestyle factors are suspected drivers. Obesity, sedentary lifestyle, diabetes mellitus, smoking, alcohol, or antibiotics affecting the gut microbiome have been proposed. However, these factors, which have been present since the 1950s, have not yet been conclusively linked to the abrupt EOCRC increase. The sharp increase suggests introduction of a new risk factor for young people. We hypothesized that the driver may be an off-target effect of a pharmaceutical agent (requiring regulatory approval before its use in the general population or an off-label use of a previously approved agent) in a genetically susceptible subgroup of young adults. If a pharmaceutical agent is an EOCRC driving factor, regulatory risk mitigation strategies could be employed.To evaluate the possibility that pharmaceutical agents serve as risk factors for EOCRC.Design: Case-Control study. Data including demographics, co-morbidities, and complete medication dispensing history (both prescription and over the counter) were obtained from the electronic medical records database of Maccabi Healthcare Services (MHS), a state-mandated health provider covering 26% of the Israeli population. Participants: 941 EOCRC cases (<50 years of age) diagnosed during 2001-2019 were identified and were density matched 1:10 with 9410 controls. IBD patients and patients with a known inherited cancer susceptibility syndrome were excluded. Methods: An advanced machine learning algorithm based on gradient boosted decision trees coupled with Bayesian model optimization and repeated data sampling was used to sort through the very high-dimensional drug dispensing data to identify specific medication groups that were consistently linked with EOCRC while allowing for synergistic or antagonistic interactions between medications. Odds ratios for the identified medication classes were obtained from a conditional logistic regression model.Of more than 800 medication classes, we identified several classes that were consistently (>50%) associated with EOCRC risk across independently trained models. Interactions between medication groups did not seem to substantially affect the risk. In our analysis drug groups that were consistently positively associated with EOCRC included beta blockers (OR=1.94, 95% CI=1.37-2.77, p<0.01) and valerian (Valeriana officinalis), OR=1.61, 95% CI=1.15-2.25, p=0.01); antibiotics were not consistently associated with EOCRC risk.Our analysis suggests that the development of EOCRC may be correlated with prior use of specific medications. Additional analyses should be employed to validate the results. The mechanism of action inducing EOCRC by candidate pharmaceutical agents will then need to be determined.