Rhudy Christian, Perry Courtney, Wesley Michael, Fardo David, Bumgardner Cody, Hassan Syed, Barrett Terrence, Talbert Jeffery
Department of Pharmacy Services, University of Kentucky Healthcare, Lexington, KY, USA.
Division of Digestive Diseases and Nutrition, Department of Medicine, University of Kentucky College of Medicine, Lexington, KY, USA.
Crohns Colitis 360. 2024 Jul 8;6(3):otae039. doi: 10.1093/crocol/otae039. eCollection 2024 Jul.
Adherence to self-administered biologic therapies is important to induce remission and prevent adverse clinical outcomes in Inflammatory bowel disease (IBD). This study aimed to use administrative claims data and machine learning methods to predict nonadherence in an academic medical center test population.
A model-training dataset of beneficiaries with IBD and the first unique dispense of a self-administered biologic between June 30, 2016 and June 30, 2019 was extracted from the Commercial Claims and Encounters and Medicare Supplemental Administrative Claims Database. Known correlates of medication nonadherence were identified in the dataset. Nonadherence to biologic therapies was defined as a proportion of days covered ratio <80% at 1 year. A similar dataset was obtained from a tertiary academic medical center's electronic medical record data for use in model testing. A total of 48 machine learning models were trained and assessed utilizing the area under the receiver operating characteristic curve as the primary measure of predictive validity.
The training dataset included 6998 beneficiaries ( = 2680 nonadherent, 38.3%) while the testing dataset included 285 patients ( = 134 nonadherent, 47.0%). When applied to test data, the highest performing models had an area under the receiver operating characteristic curve of 0.55, indicating poor predictive performance. The majority of models trained had low sensitivity and high specificity.
Administrative claims-trained models were unable to predict biologic medication nonadherence in patients with IBD. Future research may benefit from datasets with enriched demographic and clinical data in training predictive models.
坚持自我给药的生物疗法对于诱导炎症性肠病（IBD）缓解和预防不良临床结局很重要。本研究旨在使用行政索赔数据和机器学习方法预测学术医疗中心测试人群中的不依从情况。
从商业索赔与医疗记录以及医疗保险补充行政索赔数据库中提取2016年6月30日至2019年6月30日期间患有IBD且首次独特配给自我给药生物制剂的受益人的模型训练数据集。在数据集中确定了已知的药物不依从相关因素。生物疗法的不依从定义为1年时覆盖天数比例<80%。从一家三级学术医疗中心的电子病历数据中获得了类似的数据集用于模型测试。共训练并评估了48个机器学习模型，使用受试者操作特征曲线下面积作为预测有效性的主要衡量指标。
训练数据集包括6998名受益人（=2680名不依从者，38.3%），而测试数据集包括285名患者（=134名不依从者，47.0%）。应用于测试数据时，表现最佳的模型的受试者操作特征曲线下面积为0.55，表明预测性能较差。大多数训练的模型敏感性低而特异性高。
基于行政索赔训练的模型无法预测IBD患者的生物药物不依从情况。未来的研究可能会受益于在训练预测模型时使用具有丰富人口统计学和临床数据的数据集。
