Multisite Electronic Health Record-based Surveillance of the Burden of Diabetes by Type in Children and Adolescents

糖尿病是18岁以下儿童和青少年常见的慢性病。在最近两年 几十年来，1型糖尿病(T1D)和2型糖尿病(T2D)的患病率和发病率都是 在美国儿童和青少年中，这一比例大幅上升。T2D现在约占糖尿病病例的15% 在童年和青春期被诊断出来。寻找青年糖尿病是唯一正在进行的研究 美国儿童青少年T1D和T2D多点监测研究搜索研究是一项 基于人口的登记，这是一种成本更高、劳动密集度更高、速度更慢的监测方法 与使用电子健康记录(EHR)的监测系统相比。EHR算法已经表明 在识别糖尿病病例方面具有巨大的潜力。本研究将分析结构化的EHR数据(例如，诊断 代码、药物和实验室结果)和非结构化临床记录。我们将运用专业知识， 机器学习和自然语言处理，以开发识别流行和 事件T1D和T2D病例。这项研究的主要目标是建立以电子健康记录为基础的监测 美国儿童和青少年T1D和T2D负担监测系统。我们将与3家公司合作 EHR研究网络来自国家以患者为中心的临床研究网络(PCORnet)，涵盖 来自4个州(伊利诺伊州、洛杉矶、 纽约州和德克萨斯州)在3个人口普查地区。这项研究中的患者群体大致代表了病源 在集水区的人口。这项研究的具体目的是1)估计T1D的患病率 2019年按年龄、性别、种族/民族和地理区域划分的美国儿童和青少年的T2D；2) 估计美国儿童和青少年中T1D和T2D的发病率，按年龄、性别、种族/民族和 2019年地理区域；3)估计#年T1D和T2D患病率和发病率的10年趋势 2014-2023年按年龄、性别、种族/民族和地理区域划分的美国儿童和青少年；以及4)比较 按类型划分的美国儿童和青少年糖尿病患病率和发病率，以及时间趋势 与其他国家和地区的儿童和青少年的情况相同。这项研究具有创新性，因为它将 利用EHR进行监测(比登记和调查更有效率和成本效益)，使用高级 统计方法(例如，机器学习和自然语言处理)使用 患者邮政编码，根据当地可获得的临床记录，在监测方法中加入灵活性， 并采用两阶段抽样方法，提高审图效率。这项研究中的所有4个州都没有 儿童和青少年的主动糖尿病监测系统，不在搜索范围内 学习。这项研究将促进我们对中国的地理、年龄、性别和种族/民族差异的理解 美国儿童和青少年的T1D和T2D负担。获得的监视数据将有助于识别 并优先考虑预防糖尿病和相关合并症的亚群，以减少健康差距。

Diabetes is a common chronic disease in children and adolescents under age of 18 years. In the recent two decades, both the prevalence and incidence of type 1 diabetes (T1D) and type 2 diabetes (T2D) have been increasing considerably among US children and adolescents. T2D now accounts for ~15% of diabetes cases diagnosed in childhood and adolescence. The SEARCH for Diabetes in Youth study is the only ongoing multisite surveillance study of T1D and T2D in US children and adolescents. The SEARCH study is a population-based registry, which is a more expensive, more labor-intensive, and slower surveillance method compared with a surveillance system using electronic health records (EHRs). EHR algorithms have shown great potential in identifying diabetes cases. This study will analyze both structured EHR data (e.g., diagnosis codes, medications, and laboratory results) and unstructured clinical notes. We will apply expert knowledge, machine learning, and natural language processing to develop the best algorithms for identifying prevalent and incident T1D and T2D cases. The primary objective of this study is to establish an EHR-based surveillance system for monitoring the burden of T1D and T2D in US children and adolescents. We will collaborate with 3 EHR research networks from the National Patient-Centered Clinical Research Network (PCORnet), covering ~3 million racially, ethnically, and socioeconomically diverse children and adolescents from 4 states (IL, LA, NY, and TX) in 3 Census regions. The patient populations in this study are roughly representative of the source populations in the catchment areas. The specific aims of this study are 1) to estimate the prevalence of T1D and T2D in US children and adolescents by age, sex, race/ethnicity, and geographic region in 2019; 2) to estimate the incidence of T1D and T2D in US children and adolescents by age, sex, race/ethnicity, and geographic region in 2019; 3) to estimate 10-year trends in the prevalence and incidence of T1D and T2D in US children and adolescents by age, sex, race/ethnicity, and geographic region, 2014-2023; and 4) to compare the prevalence and incidence of diabetes by type, as well as temporal trends, in US children and adolescents with those in children and adolescents from other countries and regions. This study is innovative because it will leverage EHRs for surveillance (more efficient and cost-effective than registries and surveys), use advanced statistical approaches (e.g., machine learning and natural language processing), estimate a denominator using patient zip codes, build flexibility into the surveillance methods according to local availability of clinical notes, and use a 2-staged sampling approach to improve chart review efficiency. All 4 states in this study do not have an active diabetes surveillance system for children and adolescents and are not covered by the SEARCH study. This study will advance our understanding of the geographic, age, sex, and racial/ethnic differences in the burden of T1D and T2D in US children and adolescents. The obtained surveillance data will help identify and prioritize subpopulations for prevention of diabetes and related comorbidities to reduce health disparities.