Computational methods using electronic health records and registry data to detect and predict clinical outcomes in rheumatic disease

项目摘要/摘要 这是芝加哥大学流行病学家Milena Gianfrancesco博士的K01奖项的新申请 加州大学旧金山分校(UCSF)医学院，他计划开展一项研究项目，重点是 了解与风湿病患者预后相关的风险因素，如不良事件。 结合侧重于计算文本挖掘方法和高级因果推理的培训计划 统计，目前研究的目标是使用大量的电子健康记录和国家登记数据， 反映现实世界的处方模式，以检查由于生物疾病修改而导致的感染风险 风湿性关节炎(RA)和系统性红斑狼疮(SLE)患者的抗风湿药物。 虽然生物药物改善了疾病控制，并与患者的显著进步有关 生活质量，几项研究已经证明，生物使用与增加患心脏病的风险有关。 严重不良事件，如感染。这种风险如何根据各种患者因素而有所不同，例如 年龄、种族和民族，目前尚不清楚，这使得临床医生没有足够的信息来预测 服用特定生物制剂的特定患者发生不良事件的概率。 这项提案将利用已建立的当地电子健康记录和国家登记数据来审查 80,000名类风湿关节炎和系统性红斑狼疮患者，以解决三个具体目标。在目标1中，Gianfrancesco博士将申请并 验证文本挖掘系统以从临床记录中识别事件、临床和机会性感染。在AIM 2，Gianfrancesco博士将使用相同的数据库来确定生物制品对 有感染的风险。在目标3中，将开发一个预测感染风险的风险评估模型，并在#年进行验证。 风湿病诊所。这项研究的发现将进一步阐明与感染风险相关的因素 个人开了生物制品，从而提高了他们在流动环境中的安全性。 Gianfrancesco博士组建了一支在计算文本挖掘方面具有专业知识的卓越指导团队 方法，高级因果推断统计，风湿学和患者安全结局，以及 使用国家登记册数据解决这些问题的经验。她将有机会获得丰富的研究成果 并通过加州大学旧金山分校的临床和职业发展计划为职业发展提供支持 翻译科学研究所K-学者计划。正式的课程作业和辅导也将是 此外，还参加了与风湿学、流行病学和信息学有关的国家会议。 完成拟议的研究和职业发展计划将使Gianfrancesco博士获得 在使用大型数据集的最先进计算方法方面的经验，以更好地理解重要的 患者结局，如严重不良事件。这个辅导式职业发展奖将提供 技能、指导和经验是推动她走向独立并使她能够领导 独立的多学科研究计划。

PROJECT SUMMARY / ABSTRACT This is a new application for a K01 award for Dr. Milena Gianfrancesco, an epidemiologist at the University of California, San Francisco (UCSF) School of Medicine, who plans a research program focusing on understanding risk factors as they relate to rheumatic disease patient outcomes, such as adverse events. Combined with a training plan focused on computational text mining methods and advanced causal inference statistics, the goal of the current study is to use large electronic health record and national registry data that reflects real-world prescribing patterns to examine the risk of infection attributed to biologic disease-modifying anti-rheumatic drugs in individuals with rheumatoid arthritis (RA) and systemic lupus erythematosus (SLE). While biologic medications have improved disease control and are associated with significant gains in patients’ quality of life, several studies have demonstrated that biologic use is associated with an increased risk of serious adverse events, such as infection. How this risk differs based on a variety of patient factors, such as age, race, and ethnicity, is currently unknown, leaving clinicians with insufficient information to predict the probability of an adverse event occurring in a given patient who is prescribed a particular biologic. This proposal will utilize established local electronic health record and national registry data to examine over 80,000 individuals with RA and SLE to address three specific aims. In Aim 1, Dr. Gianfrancesco will apply and validate a text mining system to identify incident clinical and opportunistic infections from clinical notes. In Aim 2, Dr. Gianfrancesco will use the same databases to determine the longitudinal causal effect of biologics on risk of infection. In Aim 3, a risk-assessment model to predict risk of infection will be developed and validated in a rheumatology clinic. Findings from this study will further elucidate factors associated with infectious risk for individuals prescribed biologics, thereby improving their safety in the ambulatory settings. Dr. Gianfrancesco has assembled an exceptional mentorship team with expertise in computational text mining methods, advanced causal inference statistics, rheumatology and patient safety outcomes, as well as experience using national registry data to address these questions. She will have access to a rich research environment and provided support for career development through programs such as the UCSF Clinical and Translational Science Institute K-scholars program. Formal coursework and mentoring will also be supplemented with attendance at national conferences related to rheumatology, epidemiology, and informatics. Completing the proposed research and career development plan will allow Dr. Gianfrancesco to gain experience in state-of-the-art computational methods using large datasets to better understand important patient outcomes, such as serious adverse events. This mentored career development award will provide the skills, mentorship, and experience necessary to propel her to independence and enable her to lead an independent multidisciplinary research program.