RAISE: IHBEM: Inclusion of Challenges from Social Isolation Governed by Human Behavior through Transformative Research in Epidemiological Modeling

RAISE：IHBEM：通过流行病学模型的变革性研究纳入人类行为所带来的社会孤立的挑战

• 批准号: 2230117
• 负责人: Folashade Agusto
• 金额: $ 100万
• 依托单位: University of Kansas Center for Research Inc
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-01-01 至 2025-12-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2230117&HistoricalAwards=false
• 关键词: RAISE; IHBEM; Inclusion; Challenges; Social

Project INSIGHT is a collaborative effort to develop novel and transformative research aimed at incorporating human social, behavioral, and economic interactions in mathematical epidemiological models. Project INSIGHT addresses two sets of questions about behavioral responses to social isolation during the COVID-19 pandemic: (1) How does compliance with isolation policies drive disease mitigation outcomes? and (2) Does social isolation lead to unanticipated negative social outcomes, and if so, how? Social isolation and individual distancing are key tools in mitigating large-scale infectious disease outbreaks. Yet, social interactions are crucial for the health and prosperity of individuals and their communities. Social isolation is associated with negative outcomes such as substance use and abuse, domestic violence, and reduced mental and physical health. These negative effects are often pronounced in rural, low-income, and older communities. The primary goal of INSIGHT is to model both positive and negative effects and thereby improve our understanding of the course of the COVID-19 pandemic and its long-term effect on society. This project is funded jointly by the Division of Mathematical Sciences (DMS) in the Directorate of Mathematical and Physical Sciences (MPS) and the Division of Social and Economic Sciences (SES) and the Division of Behavioral and Cognitive Sciences (BCS) in the Directorate of Social, Behavioral, and Economic Sciences (SBE).Project INSIGHT develops realistic epidemic models incorporating behavioral responses of compliance and adherence as follows: (1) Isolation compliance. Using a classical segmentation of populations into compliant and non-compliant groups, a switching function is defined to account for changes in behavior. Games with appropriate payoff functions that inform individuals’ behavioral choices are used. (2) Opioid misuse treatment adherence. A model according to severity of substance use disorder is created, implementing treatment adherence with game-derived utility functions and incorporating drug-seeking behavior of affected individuals, Model parameters like recovery and deaths are accounted for via well-defined behavioral functions. (3) Domestic violence. Focusing on intimate partners, economic-dependent functions are used to capture partners’ choices such as abuse, forgiveness, seeking help, or leaving the domestic violence cycle. The modeling efforts use data from several national and local sources. The outcome of Project INSIGHT modeling efforts is a synthetic, in-depth view of the balance of positive (reduction of disease transmission) and negative (substance abuse, domestic violence) implications of social isolation as a response to pandemic situations.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

INSIGHT项目是一项合作努力，旨在开发新颖和变革性的研究，旨在将人类社会，行为和经济相互作用纳入数学流行病学模型。INSIGHT项目解决了两组关于COVID-19大流行期间社会隔离行为反应的问题：（1）遵守隔离政策如何推动疾病缓解结果？（2）社会隔离是否会导致不可预期的负面社会后果？如果是，如何导致的？ 社会隔离和个人隔离是缓解大规模传染病暴发的关键工具。然而，社会互动对于个人及其社区的健康和繁荣至关重要。社会孤立与负面结果有关，如药物使用和滥用，家庭暴力以及身心健康下降。这些负面影响在农村、低收入和老年社区往往很明显。INSIGHT的主要目标是模拟正面和负面影响，从而提高我们对COVID-19大流行过程及其对社会的长期影响的理解。 该项目由数学和物理科学局（MPS）的数学科学处（DMS）和社会、行为和经济科学局（SBE）的社会和经济科学处（SES）以及行为和认知科学处（BCS）共同资助。INSIGHT项目开发了现实的流行病模型，其中包括遵守和坚持的行为反应，如下所示：（1）隔离合规性。使用一个经典的人口分割成顺从和不顺从的群体，开关函数被定义为占行为的变化。游戏与适当的回报功能，告知个人的行为选择。(2)阿片类药物滥用治疗依从性。根据物质使用障碍的严重程度创建模型，利用游戏衍生的效用函数实现治疗依从性，并将受影响个体的药物寻求行为纳入其中，通过定义良好的行为函数来解释模型参数，如恢复和死亡。(3)家庭暴力以亲密伴侣为重点，使用经济依赖函数来捕捉伴侣的选择，如虐待、宽恕、寻求帮助或离开家庭暴力循环。建模工作使用来自多个国家和地方来源的数据。INSIGHT项目建模工作的结果是对社会隔离作为对流行病情况的反应的积极（减少疾病传播）和消极（药物滥用，家庭暴力）影响的平衡的综合，深入的看法。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

MACHINE LEARNING FOR PREDICTING THE DYNAMICS OF INFECTIOUS DISEASES DURING TRAVEL THROUGH PHYSICS INFORMED NEURAL NETWORKS

机器学习通过物理信息神经网络预测旅行期间传染病的动态

• DOI: 10.1615/jmachlearnmodelcomput.2023047213
• 发表时间: 2023
• 期刊: Journal of Machine Learning for Modeling and Computing
• 作者: Ogueda-Oliva, Alonso G.;Martínez-Salinas, Erika Johanna;Arunachalam, Viswanathan;Seshaiyer, Padmanabhan
• 通讯作者: Seshaiyer, Padmanabhan

Literate programming for motivating and teaching neural network-based approaches to solve differential equations

用于激励和教授基于神经网络的方法来求解微分方程的文字编程

• DOI: 10.1080/0020739x.2023.2249901
• 发表时间: 2023
• 期刊: International Journal of Mathematical Education in Science and Technology
• 影响因子: 0.9
• 作者: Ogueda-Oliva, Alonso;Seshaiyer, Padmanabhan
• 通讯作者: Seshaiyer, Padmanabhan