Using System Dynamics Modeling to Foster Real-time Connections to Care

使用系统动力学建模促进实时护理联系

• 批准号: 10851137
• 负责人: Rebekah Heckmann
• 金额: $ 25.8万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2024-09-29
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10851137
• 关键词: Address; Administrative Supplement; Advocate; Algorithms; American; Artificial Intelligence; Authorization documentation; Bioethics Consultants; Caring; Cessation of life; Communities; Connecticut; Data; Data Scientist; Data Set; Data Sources; Decision Making; Detection; Development; Disparity; Doctor of Philosophy; Drug Prescriptions; Electronic Health Record; Emergency Department patient; Emergency Medicine; Ensure; Equity; Ethics; Evaluation; Exhibits; Feedback; Fostering; Funding; Future; Harm Reduction; Health Promotion; Healthcare; Helping to End Addiction Long-term; Individual; Intervention; Interview; Link; Machine Learning; Mediation; Methodology; Modeling; Opioid; Outcome; Output; Overdose; Parents; Participant; Performance; Persons; Population; Process; Provider; Public Health; Recommendation; Recovery Support; Resource Allocation; Rest; Services; Techniques; Time; Toxic effect; Translating; United States National Institutes of Health; Vulnerable Populations; Work; algorithmic bias; augmented intelligence; authority; dashboard; data ecosystem; data infrastructure; data-driven model; demographics; dynamic system; emergency preparedness; evidence base; experience; fighting; first responder; health application; improved; improved outcome; innovation; insight; machine learning algorithm; medication for opioid use disorder; novel; opioid epidemic; opioid overdose; parent project; predictive modeling; telehealth

Project Summary The two objectives of our currently funded HD2A Innovation Project are: (1) to implement a novel, scalable, evidence-based, intervention (i.e., our telehealth platform RecoveryPad) that links people who have overdosed with access to medication for opioid use disorder (MOUD), harm reduction services, and recovery supports, and (2) to collect high-quality data about the processes and outcomes associated with deployment of this platform that can be integrated with our existing system dynamics (SD) model to determine if, where, when, and what interventions should be implemented in the future. In this manner, our data (i.e., input and output from the SD model) drives our action (i.e., provision and refinement of RecoveryPad) in a continuous feedback loop. This administrative supplement will allow integration of an ethical artificial intelligence (AI) framework into the refinement and evaluation of the telehealth intervention of the parent project. Specifically, we will evaluate datasets, model assumptions, algorithmic inputs, development, and performance of the parent project for potential biases, particularly in relation to exacerbating disparity of OUD-related outcomes among vulnerable populations. Through the systematic detection and mitigation of algorithmic biases, we will enhance the fairness of AI-augmented interventions, promoting equitable treatment engagement across diverse demographics. The insights we gain will not only optimize our own RecoveryPad platform and system dynamics model but will also contribute to wider ethical AI applications in healthcare. Moreover, our work stands to improve outcomes for individuals with OUD and support national efforts to address the opioid crisis. Specifically, we propose the following supplemental aims: 1) Aim 1 - to assess bias and fairness within the SD model: This aim seeks to translate AI fairness assessment methodologies into iterative refinement of the existing system dynamics model. By leveraging our integrated team that includes a bioethicist, AI experts, data scientists, clinicians, and people with lived experience, we will examine key model inputs and their potential bias implications on model outputs for sensitive demographic attributes. Furthermore, we intend to ensure representation and mitigate any algorithmic bias. 2) Aim 2 - to assess bias and overall fairness of RecoveryPad: Aim 2a) Fairness evaluation of datasets and the brief negotiated interview (BNI) process during RecoveryPad Development: We will assess potential biases by analyzing whether our population-level machine learning algorithms exhibit differential predictions for MOUD engagement across diverse groups using historical electronic health record data, where ED patients have received a BNI from an in-person health promotion advocate. Aim 2b) Bias and Fairness Assessment of RecoveryPad: We will evaluate bias and fairness within RecoveryPad through simulated and real-time participant conversational encounters, leveraging existing frameworks for assessing conversational AI for bias and toxicity.

项目概要 我们目前资助的 HD2A 创新项目的两个目标是：(1) 实施一种新颖的、可扩展的、 循证干预（即我们的远程医疗平台 RecoveryPad）将吸毒过量的人联系起来 获得治疗阿片类药物使用障碍 (MOUD) 的药物、减少伤害服务和康复支持， (2) 收集有关与此部署相关的流程和结果的高质量数据 可以与我们现有的系统动力学 (SD) 模型集成的平台，以确定是否、何处、何时、 以及未来应采取哪些干预措施。通过这种方式，我们的数据（即输入和输出 来自 SD 模型）以持续的反馈推动我们的行动（即 RecoveryPad 的提供和完善） 环形。该行政补充将允许将道德人工智能（AI）框架整合到 父项目远程医疗干预的完善和评估。具体来说，我们将评估 父项目的数据集、模型假设、算法输入、开发和性能 潜在的偏见，特别是与加剧弱势群体中 OUD 相关结果的差异有关 人口。通过系统地检测和缓解算法偏差，我们将增强 人工智能增强干预措施的公平性，促进不同群体的公平治疗参与 人口统计。我们获得的见解不仅会优化我们自己的 RecoveryPad 平台和系统 动力学模型，但也将有助于医疗保健领域更广泛的道德人工智能应用。此外，我们的工作 致力于改善 OUD 患者的治疗结果，并支持国家解决阿片类药物危机的努力。 具体来说，我们提出以下补充目标： 1) 目标 1 - 评估 SD 内的偏见和公平性 模型：该目标旨在将人工智能公平性评估方法转化为对人工智能公平性评估方法的迭代细化。 现有的系统动力学模型。通过利用我们的综合团队，包括生物伦理学家、人工智能专家、数据 科学家、临床医生和有生活经验的人，我们将检查关键模型输入及其潜力 对敏感人口统计属性的模型输出的偏差影响。此外，我们打算确保 表示并减轻任何算法偏差。 2) 目标 2 - 评估偏见和整体公平性 RecoveryPad：目标 2a）数据集的公平性评估以及期间的简短协商访谈（BNI）过程 RecoveryPad 开发：我们将通过分析我们的人口水平是否 机器学习算法使用不同的群体对 MOUD 参与度进行差异预测 历史电子健康记录数据，其中 ED 患者已从现场健康中心获得 BNI 推广倡导者。目标 2b) RecoveryPad 的偏差和公平性评估：我们将评估偏差和公平性 通过模拟和实时参与者对话，在 RecoveryPad 中实现公平性，利用 用于评估对话式人工智能的偏见和毒性的现有框架。