Learning Longitudinal Patterns and Subtypes of Pediatric Crohn Disease Treated With Infliximab via Trajectory Cluster Analysis.
Learning Longitudinal Patterns and Subtypes of Pediatric Crohn Disease Treated With Infliximab via Trajectory Cluster Analysis.
复制标题
DOI：
10.1097/mpg.0000000000003370
复制
发表时间：
2022-03-01
影响因子：
2.9
通讯作者：
Huang J
中科院分区：
文献类型：
--
作者：
Chen A;Stein R;Baldassano RN;Huang J
本研究的目的是通过使用电子健康记录中的数据对疾病活动进行轨迹聚类分析，确定对英夫利昔单抗治疗有不同反应的儿科 CD 亚组。我们对 2010 年 1 月至 2017 年 12 月期间在费城儿童医院炎症性肠病中心接受英夫利昔单抗治疗至少一年的 295 名儿科克罗恩病患者进行了回顾性研究。描述了疾病的演变，并使用 C 反应蛋白 (CRP) 纵向数据的轨迹分析确定了患者亚组。我们比较了不同亚组的患者特征、疾病活动性生物标志物以及长期手术结果。 Cox 回归模型用于评估亚组分类对基线表型和位置在预测长期手术结果方面的附加值。我们确定了三个具有不同复发和缓解情况的患者亚组（亚组 1 至 3 中 n = 33、65 和 197 名），这代表英夫利昔单抗无反应风险较高的患者、对英夫利昔单抗有反应但偶尔出现疾病发作的患者以及有长期反应的患者。治疗反应最佳的患者出现复杂疾病表型的频率显着较低 (p = 0.01)，包括肛周受累 (p = 0.05)、较低的基线 CRP (p < 0.01) 和钙卫蛋白 (p = 0.01)，以及开始治疗后 10 年内 IBD 相关胃肠道手术的风险最低 (p < 0.01)。可以利用电子健康记录中现成的纵向数据来更深入地描述儿科克罗恩病的治疗反应。本研究采用轨迹分析，结合纵向疾病模式建模和亚组识别，以提供儿科克罗恩病的更深入特征。确定的亚组与基线表型和治疗信息相关，但不能完全由基线表型和治疗信息解释。我们的研究利用电子健康记录中的纵向测量，根据治疗后疾病演变模式对接受过英夫利昔单抗治疗的儿科克罗恩病患者进行不同的治疗反应概况进行分层。我们发现，良好控制的疾病轨迹与基线时较低的炎症负荷和较少复杂的疾病表型相关，包括基线时肛周受累较少和较低的疾病活动性。与仅使用基线疾病表型和位置的模型相比，所确定的分类改进了长期手术的风险预测。
The objective of this study is to identify subgroups of pediatric CD who had differential responses to the infliximab treatment through trajectory cluster analysis of disease activity using data from electronic health records. We conducted a retrospective study of 295 pediatric CD patients who had been treated with infliximab for a minimum of one year at the Center for Inflammatory Bowel Disease at The Children’s Hospital of Philadelphia between January 2010 and December 2017. The evolution of disease was described, and subgroups of patients were identified using trajectory analysis of longitudinal data of C-Reactive Protein (CRP). We compared patient characteristics, biomarker for disease activity, and long-term surgical outcomes across subgroups. Cox regression models were used to evaluate the added value of the subgroup classification to baseline phenotype and location in prediction of long-term surgical outcomes. We identified three subgroups of patients with differential relapse-and-remission profiles (n = 33, 65 and 197 from subgroup 1 to 3), which represented patients with a higher risk of infliximab non-response, with infliximab response but with occasional disease flares, and patients with long-term response. Patients with the best treatment response had a significantly lower frequency of complicated disease phenotypes (p = 0.01), including perianal involvement (p=0.05), lower baseline CRP (p < 0.01) and calprotectin (p = 0.01), and lowest risk of IBD-related gastrointestinal surgery within 10 years of starting treatment (p<0.01). Readily available longitudinal data from electronic health records can be leveraged to provide deeper characterization of treatment response in pediatric CD. This study uses a trajectory analysis that incorporates modelling of longitudinal disease patterns and identification of subgroups to provide deeper characterization of pediatric Crohn disease. Subgroups identified are associated with, yet not fully explained by, baseline phenotype and treatment information. Our study utilized longitudinal measures from the electronic health records to stratify pediatric Crohn disease patients who had been treated with infliximab by differential treatment response profiles based on patterns of disease evolution after the treatment. We found trajectories of well-controlled disease were associated with lower inflammatory burden as baseline and less complicating disease phenotypes, including less perianal involvement and lower disease activity at baseline. The identified classification improved risk prediction of long-term surgery comparing to models that only used baseline disease phenotype and location.