Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.
Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.
复制标题
癫痫患者的依从性和急诊科利用率的差异：一种机器学习方法。
DOI：
10.1016/j.seizure.2023.06.021
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Koroukian,SiranM
中科院分区：
文献类型：
--
作者：
Bensken,WyattP;Vaca,GuadalupeFernandez-Baca;Williams,ScottM;Khan,OmarI;Jobst,BarbaraC;Stange,KurtC;Sajatovic,Martha;Koroukian,SiranM
目的：我们使用机器学习方法来识别导致较低依从性和较高急诊科（ED）使用率的因素组合。方法：使用医疗补助申请，我们确定抗癫痫药物的依从性和癫痫患者在2年随访期间的急诊科就诊次数。我们使用三年的基线数据来确定人口统计、疾病严重程度和管理、合并症和县级社会因素。使用分类和回归树（CART）和随机森林分析，我们确定了预测较低依从性和ED就诊的基线因素的组合。我们进一步按种族和民族对这些模型进行分层。结果：在52175例癫痫患者中，CART模型确定了发育障碍、年龄、种族和民族以及使用率是依从性的主要预测因素。当按种族和民族分层时，合并症的组合存在差异，包括发育障碍、高血压和精神合并症。我们的CART模型对ED的使用情况进行了分析，其中包括先前受伤的患者，其次是焦虑和情绪障碍、头痛、背部问题和尿路感染。当按种族和民族分层时，我们发现黑人头痛是未来ED使用的首要预测因素，尽管这在其他种族和民族群体中没有出现。结论：asm的依从性因种族和民族而异，不同的合并症组合预示着种族和民族群体的依从性较低。虽然不同种族和民族的ED使用率没有差异，但我们观察到不同的合并症组合预示着ED的高使用率。
PurposeWe used a machine learning approach to identify thecombinationsof factors that contribute to lower adherence and high emergency department (ED) utilization.MethodsUsing Medicaid claims, we identified adherence to anti-seizure medications and the number of ED visits for people with epilepsy in a 2-year follow up period. We used three years of baseline data to identify demographics, disease severity and management, comorbidities, and county-level social factors. Using Classification and Regression Tree (CART) and random forest analyses we identified combinations of baseline factors that predicted lower adherence and ED visits. We further stratified these models by race and ethnicity.ResultsFrom 52,175 people with epilepsy, the CART model identified developmental disabilities, age, race and ethnicity, and utilization as top predictors of adherence. When stratified by race and ethnicity, there was variation in the combinations of comorbidities including developmental disabilities, hypertension, and psychiatric comorbidities. Our CART model for ED utilization included a primary split among those with previous injuries, followed by anxiety and mood disorders, headache, back problems, and urinary tract infections. When stratified by race and ethnicity we saw that for Black individuals headache was a top predictor of future ED utilization although this did not appear in other racial and ethnic groups.ConclusionsASM adherence differed by race and ethnicity, with different combinations of comorbidities predicting lower adherence across racial and ethnic groups. While there were not differences in ED use across races and ethnicity, we observed different combinations of comorbidities that predicted high ED utilization.