High-Dimensional Biostatistics for Drug Safety and Genomics, Université Paris-Saclay, UVSQ, Inserm, CESP, Villejuif, France.
Exposome, Heredity, Cancer and Health, Université Paris-Saclay, UVSQ, Inserm, CESP, Villejuif, France.
Mov Disord. 2022 Dec;37(12):2376-2385. doi: 10.1002/mds.29205. Epub 2022 Aug 29.
Available treatments for Parkinson's disease (PD) are only partially or transiently effective. Identifying existing molecules that may present a therapeutic or preventive benefit for PD (drug repositioning) is thus of utmost interest.
We aimed at detecting potentially protective associations between marketed drugs and PD through a large-scale automated screening strategy.
We implemented a machine learning (ML) algorithm combining subsampling and lasso logistic regression in a case-control study nested in the French national health data system. Our study population comprised 40,760 incident PD patients identified by a validated algorithm during 2016 to 2018 and 176,395 controls of similar age, sex, and region of residence, all followed since 2006. Drug exposure was defined at the chemical subgroup level, then at the substance level of the Anatomical Therapeutic Chemical (ATC) classification considering the frequency of prescriptions over a 2-year period starting 10 years before the index date to limit reverse causation bias. Sensitivity analyses were conducted using a more specific definition of PD status.
Six drug subgroups were detected by our algorithm among the 374 screened. Sulfonamide diuretics (ATC-C03CA), in particular furosemide (C03CA01), showed the most robust signal. Other signals included adrenergics in combination with anticholinergics (R03AL) and insulins and analogues (A10AD).
We identified several signals that deserve to be confirmed in large studies with appropriate consideration of the potential for reverse causation. Our results illustrate the value of ML-based signal detection algorithms for identifying drugs inversely associated with PD risk in health-care databases. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
目前治疗帕金森病（PD）的方法仅部分有效或效果短暂。因此，寻找具有治疗或预防 PD 作用的现有分子（药物再利用）是非常重要的。
我们旨在通过大规模自动化筛选策略，发现与市场上的药物和 PD 之间可能存在潜在保护关联的药物。
我们在嵌套于法国国家健康数据系统的病例对照研究中实施了一种机器学习（ML）算法，该算法结合了子采样和套索逻辑回归。我们的研究人群包括 2016 年至 2018 年期间通过验证算法确定的 40760 例新发 PD 患者和 176395 名年龄、性别和居住地相似的对照者，所有患者均自 2006 年开始随访。药物暴露情况按化学亚组水平定义，然后按解剖治疗化学（ATC）分类的物质水平定义，考虑到索引日期前 10 年开始的 2 年内处方的频率，以限制反向因果关系偏倚。使用更具体的 PD 状态定义进行了敏感性分析。
我们的算法在筛选的 374 种药物中发现了 6 种药物亚组。磺酰胺类利尿剂（ATC-C03CA），特别是呋塞米（C03CA01），显示出最强的信号。其他信号包括肾上腺素能药物与抗胆碱能药物（R03AL）和胰岛素及其类似物（A10AD）。
我们确定了几个信号，这些信号值得在大型研究中进一步确认，同时适当考虑反向因果关系的可能性。我们的结果说明了基于 ML 的信号检测算法在识别与 PD 风险呈负相关的药物方面的价值，这些药物可在医疗保健数据库中发现。© 2022 作者。运动障碍协会由 Wiley 期刊出版公司代表国际帕金森病和运动障碍协会出版。
