Jinwala Zeal, Green ReJoyce, Khan Yousef, Gelernter Joel, Kember Rachel L, Hartwell Emily E
medRxiv. 2024 Nov 23:2024.11.22.24317810. doi: 10.1101/2024.11.22.24317810.
Few individuals with alcohol use disorder (AUD) receive treatment. Previous studies have shown drinking behavior, psychological problems, and substance dependence to predict treatment seeking. However, to date, no studies have incorporated polygenic scores (PGS), a measure of genetic risk for AUD.
Using the Yale-Penn sample, we identified 9,103 individuals diagnosed with DSM-IV AUD and indicated treatment-seeking status. We implemented a random forest (RF) model to predict treatment-seeking based on 91 clinically relevant phenotypes. We calculated AUD PGS for those with genetic data (African ancestry [AFR] n=3,192, European ancestry [EUR] n=3,553) and generated RF models for each ancestry group, first without and then with PGS. Lastly, we developed models stratified by age (< and ≥40 years old).
66.6% reported treatment seeking (M =40.0, 62.4% male). Across models, top predictors included years of alcohol use and related psychological problems, psychiatric diagnoses, and heart disease. In the models without PGS, we found 79.8% accuracy and 0.85 AUC for EUR and 75% and 0.78 for AFR; the addition of PGS did not substantially change these metrics. PGS was the 10 most important predictor for EUR and 23 for AFR. In the age-stratified analysis, PGS ranked 8 for <40 and 48 for ≥40 in EUR ancestry, and it ranked 14 for <40 and 24 for ≥40 in the AFR sample.
Alcohol use, psychiatric issues, and comorbid medical disorders were predictors of treatment seeking. Incorporating PGS did not substantially alter performance, but was a more important predictor in younger individuals with AUD.
While alcohol use problems are common, few individuals seek treatmentWe used machine learning in a deeply-phenotyped sample to predict treatment-seekingWe, for the first time, incorporated polygenic risk for alcohol use as a predictorAlcohol use variables, psychiatric issues, and medical problems were key predictors.
很少有酒精使用障碍（AUD）患者接受治疗。先前的研究表明，饮酒行为、心理问题和物质依赖可预测寻求治疗的情况。然而，迄今为止，尚无研究纳入多基因评分（PGS），这是一种衡量AUD遗传风险的指标。
利用耶鲁-宾夕法尼亚样本，我们确定了9103名被诊断为DSM-IV AUD并表明寻求治疗状态的个体。我们实施了一个随机森林（RF）模型，以基于91种临床相关表型预测寻求治疗的情况。我们为有基因数据的个体（非洲血统[AFR] n = 3192，欧洲血统[EUR] n = 3553）计算了AUD PGS，并为每个血统组生成了RF模型，首先不使用PGS，然后使用PGS。最后，我们开发了按年龄分层（<40岁和≥40岁）的模型。
66.6%的人报告寻求治疗（平均年龄 = 40.0岁，62.4%为男性）。在所有模型中，最重要的预测因素包括饮酒年限和相关心理问题、精神疾病诊断以及心脏病。在不使用PGS的模型中，我们发现欧洲血统组的准确率为79.8%，曲线下面积（AUC）为0.85；非洲血统组的准确率为75%，AUC为0.78；添加PGS后这些指标没有实质性变化。PGS在欧洲血统组中是第10个最重要的预测因素，在非洲血统组中是第23个。在年龄分层分析中，在欧洲血统中，PGS在<40岁人群中排名第8，在≥40岁人群中排名第48；在非洲血统样本中，PGS在<40岁人群中排名第14，在≥40岁人群中排名第24。
饮酒、精神问题和合并的躯体疾病是寻求治疗的预测因素。纳入PGS并没有实质性改变模型性能，但在年轻的AUD患者中是一个更重要的预测因素。
虽然饮酒问题很常见，但很少有人寻求治疗我们在一个深度表型样本中使用机器学习来预测寻求治疗的情况我们首次将酒精使用的多基因风险作为预测因素饮酒变量、精神问题和躯体问题是关键预测因素。
