Department of Pediatrics, Division of Gastroenterology, Hepatology and Nutrition, Boston Children's Hospital, Boston, Mass; Department of Medicine, Harvard Medical School, Boston, Mass.
Department of Pediatrics, Division of Gastroenterology, Hepatology and Nutrition, Boston Children's Hospital, Boston, Mass.
J Allergy Clin Immunol. 2018 Apr;141(4):1354-1364.e9. doi: 10.1016/j.jaci.2017.11.027. Epub 2017 Dec 19.
Diagnostic evaluation of eosinophilic esophagitis (EoE) remains difficult, particularly the assessment of the patient's allergic status.
This study sought to establish an automated medical algorithm to assist in the evaluation of EoE.
Machine learning techniques were used to establish a diagnostic probability score for EoE, p(EoE), based on esophageal mRNA transcript patterns from biopsies of patients with EoE, gastroesophageal reflux disease and controls. Dimensionality reduction in the training set established weighted factors, which were confirmed by immunohistochemistry. Following weighted factor analysis, p(EoE) was determined by random forest classification. Accuracy was tested in an external test set, and predictive power was assessed with equivocal patients. Esophageal IgE production was quantified with epsilon germ line (IGHE) transcripts and correlated with serum IgE and the T2-type mRNA profile to establish an IGHE score for tissue allergy.
In the primary analysis, a 3-class statistical model generated a p(EoE) score based on common characteristics of the inflammatory EoE profile. A p(EoE) ≥ 25 successfully identified EoE with high accuracy (sensitivity: 90.9%, specificity: 93.2%, area under the curve: 0.985) and improved diagnosis of equivocal cases by 84.6%. The p(EoE) changed in response to therapy. A secondary analysis loop in EoE patients defined an IGHE score of ≥37.5 for a patient subpopulation with increased esophageal allergic inflammation.
The development of intelligent data analysis from a machine learning perspective provides exciting opportunities to improve diagnostic precision and improve patient care in EoE. The p(EoE) and the IGHE score are steps toward the development of decision trees to define EoE subpopulations and, consequently, will facilitate individualized therapy.
嗜酸性粒细胞性食管炎（EoE）的诊断评估仍然具有挑战性，尤其是评估患者的过敏状态。
本研究旨在建立一种自动化的医学算法，以协助评估 EoE。
使用机器学习技术，基于 EoE、胃食管反流病和对照患者的食管 mRNA 转录模式，建立 EoE 的诊断概率评分（p[EoE]）。在训练集中进行降维处理，确定加权因素，并用免疫组织化学进行验证。在随机森林分类中，根据加权因素分析确定 p[EoE]。在外部测试集中测试准确性，并对可疑患者进行预测能力评估。通过 ε 胚系（IGHE）转录本定量测量食管 IgE 产生，并与血清 IgE 和 T2 型 mRNA 谱相关联，建立组织过敏的 IGHE 评分。
在主要分析中，基于炎症性 EoE 谱的共同特征，3 类统计模型生成了 p[EoE]评分。p[EoE]≥25 可成功识别 EoE，具有较高的准确性（敏感性：90.9%，特异性：93.2%，曲线下面积：0.985），并将疑似病例的诊断提高了 84.6%。p[EoE]随治疗而变化。EoE 患者的二次分析循环定义了 p[EoE]≥37.5 的患者亚群，其食管过敏炎症增加。
从机器学习的角度开发智能数据分析为提高 EoE 的诊断精度和改善患者护理提供了令人兴奋的机会。p[EoE]和 IGHE 评分是开发决策树的步骤，可以定义 EoE 亚群，从而有助于个体化治疗。
