Developing a Clinical Decision Support Tool that Assesses Risk of Opioid Use Disorder Using Natural Language Processing, Machine Learning, and Social Determinants of Health from Clinical Notes

开发一种临床决策支持工具，利用自然语言处理、机器学习和临床记录中的健康社会决定因素来评估阿片类药物使用障碍的风险

• 批准号: 10352097
• 负责人: William Brown
• 金额: $ 18.64万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-15 至 2026-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10352097
• 关键词: Address; Affect; American; Caring; Clinical; Code; County; Data; Data Scientist; Diabetes Mellitus; Diagnosis; Documentation; Drug Prescriptions; Education; Evaluation; Foundations; Goals; HIV; Health; Health Insurance Portability and Accountability Act; Hospitals; ICD-10-CM; Institution; Institutional Review Boards; International; Intervention; Interview; Knowledge; Logical Observation Identifiers Names and Codes; Machine Learning; Manuals; Maps; Measurement; Measures; Medical; Mentors; Mentorship; Metadata; Modeling; Natural Language Processing; Opioid; Output; Participant; Patient-Focused Outcomes; Patients; Performance; Physicians; Play; Procedures; Questionnaires; Recommendation; Research; Research Design; Research Methodology; Research Personnel; Resources; Risk; Risk Assessment; Risk Factors; Role; Running; SNOMED Clinical Terms; Sampling; Social Identification; Specialist; Surveys; System; Technology; Terminology; Testing; Text; Time; Training; Vocabulary; Work; addiction; base; biomedical informatics; care outcomes; career; career development; clinical decision support; disorder risk; experience; food insecurity; heuristics; housing instability; improved; innovation; knowledgebase; machine learning algorithm; medication-assisted treatment; novel; opioid epidemic; opioid mortality; opioid overdose; opioid use; opioid use disorder; patient oriented; prescription opioid; recruit; safety net; skills; social; social health determinants; statistics; success; supervised learning; support tools; therapy design; therapy development; tool; usability

PROJECT SUMMARY/ABSTRACT In 2017, 1.7 million Americans suffered from opioid use disorders (OUD), which led to 47,000 American deaths from opioid overdose. Social determinates of health (SDoH) affect patients' OUD risk level and physicians' opioid prescribing. Physicians lack the tools to quickly and accurately assess SDoH associated with OUD, and lack knowledge of relevant resource for intervention. Clinical decision support (CDS) could quickly assess a patients' SDoH factors associated with OUD risk and provide actionable recommendations, which would reduce OUD risk assessment time and address knowledge gaps. In 2018, UCSF researchers created the Compendium of Medical Terminology Codes for Social Risk Factors that maps SDoH risks to medical vocabularies. However, most SDoH are documented in clinical notes. My long-term career goal is research independence with expertise in: 1) OUD risk assessment, 2) SDoH research, and 3) intervention development, implementation, and evaluation. Related to these goals, this study will use natural language processing (NLP) to identify SDoH in clinical notes, examine associations between SDoH and OUD, and develop a CDS tool to assess OUD risk. We will then assess usability, acceptability, and feasibility of using the CDS tool in clinical settings. This research will help physicians quickly and accurately assess OUD risk, intervene earlier, and improve care. Our research aims include: Aim 1. Use NLP to identify SDoH in clinical notes and examine associations between SDoH and OUD. We will use the Compendium and NLP to extract new SDoH in clinical notes. Two raters will manually validate the new SDoH, and use descriptive statistics to characterize associations between SDoH and OUD. (training goals 1 and 2). Aim 2: Develop a CDS tool to assess OUD risk. We will use SDoH and OUD associations from aim 1 to develop a supervised machine learning algorithm for our CDS tool. We will validate the CDS tool by measuring its ability to correctly assess OUD risk in patients' EHR data (training goals 1 and 2). Aim 3: Test the usability, acceptability, and feasibility of physicians' use of the CDS tool. 40 physicians will be asked to assess sample patient cases, then given CDS results on those same cases. Physicians will indicate whether they would follow the CDS's recommendations. Additionally, participants will be asked to complete an interview and questionnaire to evaluate usability and acceptability. We will assess feasibility by examining recruitment, implementation, and metadata. (training goal 3). These aims are achievable because I have experience in NLP and machine learning and my mentors are experts in OUD research, SDoH research, and intervention design; and have an outstanding record in career development. This K01 will help me achieve researcher independence by providing a) skills to develop an OUD risk assessment intervention; b) expertise in a novel growing SDoH field; c) an innovative trial-ready scalable intervention; and d) preliminary data for an R01.

项目概要/摘要 2017年，170万美国人患有阿片类药物使用障碍（OUD），导致47,000人死亡 来自阿片类药物过量。健康的社会决定因素 (SDoH) 影响患者的 OUD 风险水平 医生的阿片类药物处方。医生缺乏快速准确评估 SDoH 相关的工具 与 OUD，并且缺乏干预相关资源的知识。临床决策支持（CDS）可以 快速评估患者与 OUD 风险相关的 SDoH 因素并提供可行的建议， 这将减少 OUD 风险评估时间并解决知识差距。 2018年，加州大学旧金山分校研究人员 创建了社会风险因素医学术语代码纲要，将 SDoH 风险映射到 医学词汇。然而，大多数 SDoH 都记录在临床记录中。我的长期职业目标是 研究独立性，具有以下专业知识：1) OUD 风险评估，2) SDoH 研究，以及 3) 干预 开发、实施和评估。与这些目标相关，本研究将使用自然语言 处理 (NLP) 以识别临床记录中的 SDoH，检查 SDoH 和 OUD 之间的关联， 并开发 CDS 工具来评估 OUD 风险。然后我们将评估可用性、可接受性和可行性 在临床环境中使用 CDS 工具。这项研究将帮助医生快速准确地评估 OUD 风险、早期干预并改善护理。我们的研究目标包括： 目标 1. 使用 NLP 识别 SDoH 临床记录并检查 SDoH 和 OUD 之间的关联。我们将使用纲要和 NLP 来 在临床记录中提取新的 SDoH。两名评估者将手动验证新的 SDoH，并使用描述性的 统计数据来表征 SDoH 和 OUD 之间的关联。 （培训目标 1 和 2）。目标 2：开发 用于评估 OUD 风险的 CDS 工具。我们将利用目标 1 中的 SDoH 和 OUD 协会来开发一个受监督的系统 我们的 CDS 工具的机器学习算法。我们将通过测量 CDS 工具正确的能力来验证它 评估患者 EHR 数据中的 OUD 风险（培训目标 1 和 2）。目标 3：测试可用性、可接受性和 医生使用CDS工具的可行性。将要求 40 名医生评估样本患者病例，然后 给出了这些相同案例的 CDS 结果。医生将表明他们是否会遵循 CDS 建议。此外，参与者将被要求完成访谈和调查问卷，以 评估可用性和可接受性。我们将通过审查招聘、实施和实施来评估可行性 元数据。 （训练目标3）。这些目标是可以实现的，因为我有 NLP 和机器方面的经验 我的学习和导师都是 OUD 研究、SDoH 研究和干预设计方面的专家；并有一个 职业发展方面的杰出记录。这个 K01 将帮助我实现研究人员的独立性 提供 a) 制定 OUD 风险评估干预措施的技能； b) 新兴的 SDoH 领域的专业知识； c) 创新的、可进行试验的、可扩展的干预措施； d) R01 的初步数据。