Extraction of Symptom Burden from Clinical Narratives of Cancer Patients using Natural Language Processing

使用自然语言处理从癌症患者的临床叙述中提取症状负担

• 批准号: 10591957
• 负责人: Meliha Yetisgen
• 金额: $ 27.45万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2024-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10591957
• 关键词: Active Learning; Address; Administrative Supplement; Adolescent; Adult; Affect; Age; Architecture; Attention; Cancer Patient; Categories; Cause of Death; Child; Child Health; Childhood; Clinical; Clinical Research; Collection; Communities; Computer software; Data; Data Set; Diagnosis; Disease; Economics; Electronic Health Record; Employment Status; Ensure; Environment; Ethnic Origin; Ethnic group; Event; Family; Funding; Future; Goals; Gold; Health; Housing; Hunger; Institution; Link; Literature; Living Arrangement; Malignant Childhood Neoplasm; Malignant Neoplasms; Mediating; Medical center; Mental Health; Methods; Modeling; National Cancer Institute; Natural Language Processing; Outcome; Patient Care; Patient-Focused Outcomes; Patients; Pediatric Oncology; Pediatric cohort; Performance; Physical environment; Population; Poverty; Psyche structure; Publications; Quality of life; Race; Recording of previous events; Research; Resources; Risk; Running; Sampling; Social Environment; Substance abuse problem; Symptoms; Systems Development; Technology; Training; Trauma; United States; Universities; Washington; Work; base; cancer care; cancer type; clinical practice; cohort; data standards; deep learning; design; discrete data; education access; experimental study; health care availability; health data; improved; infancy; innovation; learning strategy; novel; open source; patient population; pediatric patients; pediatrician; point of care; relating to nervous system; social; social factors; social health determinants; substance use

Project Summary/Abstract Although cancer in children and adolescents is rare, it is the leading cause of death by disease past infancy among children in the United States. The US Department of Health defines SDOH as “conditions in the environment that affect health, functioning, and quality of life outcomes and risks." There is an extensive literature base linking race, ethnicity, and SDOH to pediatric cancer outcomes. SDOH are commonly queried in pediatric clinical practice. Very few of the SDOH data points are noted as discrete data-fields such as race and ethnicity; most are documented as clinical narratives in Electronic Health Records (EHRs) which makes it difficult to collect SDOH in clinical and research settings to improve patient care and advance clinical research. We therefore propose to develop novel deep learning-based NLP technologies that can extract detailed SDOH information from EHRs of pediatric patients for secondary use. Our dataset will include clinical notes of pediatric patients from two institutions: Seattle Cancer Care Alliance (SCCA) and University of Washington Medical Center (UWMC). SCCA cohort will include only pediatric cancer patients. To ensure the generalizability of extraction approaches across different institutions and patient populations, UWMC cohort will include a random sample from general pediatric population. Our final corpus will include thousands of clinical notes of hundreds of pediatric patients over a period of ten years (1.1.2012-12.31.2021). We will design a frame-based event representation schema to capture the salient details of the following categories of SDOH: (1) health care access and quality, (2) living arrangements, (3) economic stability, (4) housing and hunger insecurity, (5) prior trauma/loss, (6) education access and quality, (7) patient and family substance use history, and (8) patient/family mental. We will use active learning to sample a diverse and representative set of notes for gold standard annotation. Given this gold standard, our goal is automated extraction of SDOH from clinical narratives of pediatric patients with deep learning-based NLP approaches. The proposed frame- based event representation, active learning framework and NLP architectures will be based on ongoing work from our ITCR - R21 project titled “Extraction of Symptom Burden from Clinical Narratives of Cancer Patients using Natural Language Processing” (1 R21 CA258242-01). All models and their implementations produced during the execution of this project will be shared with the community as open-source resources.

项目摘要/摘要 虽然癌症在儿童和青少年中很少见，但它是婴儿期以后因疾病死亡的主要原因。 在美国的儿童中。美国卫生部对SDOH的定义是： 影响健康、功能和生活质量的环境结果和风险。 将种族、民族和SDOH与儿科癌症结局联系起来的文献基础。通常在中查询SDOH 儿科临床实践。SDOH数据点很少被标记为离散数据字段，如RACE和 种族；大多数作为临床叙述被记录在电子健康记录(EHR)中，这使得 难以在临床和研究环境中收集SDOH，以改善患者护理和推进临床研究。 因此，我们建议开发新的基于深度学习的自然语言处理技术，该技术可以提取详细的SDOH 来自儿科患者电子病历的信息，供二次使用。我们的数据集将包括以下临床记录 来自两个机构的儿科患者：西雅图癌症护理联盟(SCCA)和华盛顿大学 医疗中心(UWMC)。SCCA队列将仅包括儿科癌症患者。为了确保 不同机构和患者群体的提取方法的概括性，UWMC队列将 包括从普通儿科人群中随机抽取的样本。我们的最终语料库将包括数千个临床 十年间(2012年1月1日-2021年12月31日)数百名儿科患者的笔记。我们将设计一个 基于帧的事件表示方案，以捕获以下SDOH类别的显著细节： (1)保健机会和质量；(2)生活安排；(3)经济稳定；(4)住房和饥饿 不安全感，(5)既往创伤/损失，(6)受教育机会和质量，(7)患者和家庭药物使用史， (8)病人/家庭心理。我们将使用主动学习来采样一组不同的和有代表性的笔记 用于黄金标准注释。考虑到这一黄金标准，我们的目标是自动从 采用基于深度学习的NLP方法的儿科患者的临床叙述。建议的框架如下： 基于事件表示、主动学习框架和NLP架构将基于正在进行的工作 摘自我们的ITCR-R21项目，题为《从癌症患者的临床叙述中提取症状负担》 使用自然语言处理“(1 R21 CA258242-01)。生产的所有模型及其实现 在这个项目执行期间，将作为开源资源与社区共享。