Causal factors in childhood and adolescence leading to anabolic-androgenic steroid use: A machine learning approach.
Causal factors in childhood and adolescence leading to anabolic-androgenic steroid use: A machine learning approach.
复制标题
DOI：
10.1016/j.dadr.2023.100215
复制
发表时间：
2024-03
期刊：
影响因子：
--
通讯作者：
Pope, Harrison G Jr
中科院分区：
文献类型：
--
作者：
Hudson, James I;Hudson, Yaakov;Kanyama, Gen;Schnabel, Jiana;Javaras, Kristin N;Kaufman, Marc J;Pope, Harrison G Jr
合成代谢雄激素类固醇（AAS）的使用是一个很大的公共卫生问题。利用现有数据集寻找AAS使用的因果因素。使用机器学习和因果推理理论来识别因果因素。有六个潜在的原因，其中对身体形象的担忧最为突出。机器学习与因果推理相结合具有广泛的应用。先前的研究已经证明了合成代谢雄激素类固醇（AAS）的使用与儿童和青少年心理社会领域的一些特征之间的联系，包括身体形象问题、反社会特征和低水平的父母照顾。然而，先前的研究方法由于关注个体特征而缺乏对相关因果结构的考虑而受到限制。我们重新分析了先前对232名年龄在18-40岁的男性举重运动员进行的横断面队列研究的数据，其中101人使用了AAS。这些男性完成了童年和青少年早期特征的回顾性测量，包括对身体形象的担忧、饮食失调、精神病理、反社会特征、物质使用和家庭关系。使用因果推理原理的方法，我们应用了四种机器学习方法——套索回归、弹性网络回归、随机森林和梯度增强——来预测AAS的使用。四种方法得出了相似的受试者工作曲线、曲线下平均面积（范围0.66至0.72）和一系列非常重要的特征。与青少年身体形象相关的特征（尤其是肌肉畸形症状）是最强的预测因子。其他重要特征是青少年的叛逆行为；青少年无效能感与内感受意识缺失以及低水平的父亲关怀。在因果关系知情的方法中应用机器学习重新分析举重运动员先前研究的数据，我们确定了六个因素（最突出的是与青少年身体形象相关的因素）作为AAS使用发展的因果因素。与先前的分析相比，这种方法在方法上更加严谨，并产生了更有力和更广泛的发现。
Anabolic-androgenic steroid (AAS) use is a large public health problem. Causal factors for AAS use were sought using an existing dataset. Machine learning and causal inference theory were used to identify causal factors. Six potential causal factors emerged, with body image concerns the most prominent. Machine learning combined with causal inference has a wide range of applications. Prior research has demonstrated associations between anabolic-androgenic steroid (AAS) use and features from several childhood and adolescent psychosocial domains including body image concerns, antisocial traits, and low levels of parental care. However, prior approaches have been limited by their focus on individual features and lack of consideration of the relevant causal structure. We re-analyzed data from a previous cross-sectional cohort study of 232 male weightlifters aged 18–40, of whom 101 had used AAS. These men completed retrospective measures of features from their childhood and early adolescence, including body image concerns, eating disorder psychopathology, antisocial traits, substance use, and family relationships. Using an approach informed by principles of causal inference, we applied four machine-learning methods – lasso regression, elastic net regression, random forests, and gradient boosting – to predict AAS use. The four methods yielded similar receiver operating curves, mean area under the curve (range 0.66 to 0.72), and sets of highly important features. Features related to adolescent body image concerns (especially muscle dysmorphia symptoms) were the strongest predictors. Other important features were adolescent rebellious behaviors; adolescent feelings of ineffectiveness and lack of interoceptive awareness; and low levels of paternal care. Applying machine learning within a causally informed approach to re-analyze data from a prior study of weightlifters, we identified six factors (most prominently those related to adolescent body image concerns) as proposed causal factors for the development of AAS use. Compared with the prior analyses, this approach achieved greater methodologic rigor and yielded stronger and broader findings.