AIM-AHEAD Year 4 PAIR - Project 2039 Dataset

Project Title: Evaluating Large Language Models for Diagnostic Checking and Test‑Ordering in Outpatient Clinical Decision Support Project Awardee: Haibing Lu This dataset is derived from the OCHIN Community Health Database – AIM‑AHEAD Year 4 and implemented as a set of views. It includes adults aged 18 and older with outpatient encounters between 2018 and 2024, with a focus on patients with mental and behavioral health diagnoses, supporting evaluation of diagnostic checking and test‑ordering patterns in outpatient clinical decision support. The dataset includes patient demographics (sex, age, race, ethnicity, language, payer, federal poverty level, ZIP/ZCTA, homelessness status, marital status, and interpreter‑needed indicator), visit‑level data (including office visits and telehealth), provider information, vital signs, condition diagnoses used as reference labels for diagnostic activity, laboratory testing data to characterize observed ordering patterns, medication exposures, procedure data related to outpatient behavioral health services, and selected patient screening measures (including depression and substance use screening instruments and other contextual screening domains). For additional information about this dataset and access requirements, please contact the Project Awardee and/or OCHIN at AI‑DataConsult[at]ochin.org.项目名称：评估大型语言模型（Large Language Models）在门诊临床决策支持中的诊断核查与检验开单能力 项目负责人：卢海滨 本数据集源自OCHIN社区健康数据库——AIM-AHEAD第四年项目数据集，并以数据库视图集形式实现。本数据集纳入2018年至2024年间存在门诊就诊记录的18岁及以上成年人，重点关注伴有精神及行为健康诊断的患者，旨在支持对门诊临床决策支持中的诊断核查与检验开单模式开展评估。 本数据集包含患者人口统计学信息（性别、年龄、种族、族裔、语言、支付方、联邦贫困线水平、ZIP/ZCTA编码、无家可归状态、婚姻状况及是否需要口译标识）、就诊层面数据（包括门诊面诊与远程医疗就诊）、医疗服务提供者信息、生命体征数据、用作诊断活动参考标签的疾病诊断信息、用于表征实际观测到的开单模式的实验室检验数据、药物暴露情况、与门诊行为健康服务相关的操作数据，以及选定的患者筛查指标（包括抑郁症与物质使用筛查工具及其他相关背景筛查维度）。 如需了解本数据集的更多信息及获取要求，请联系项目负责人及/或OCHIN，联系方式为AI-DataConsult[at]ochin.org。