Rosie the Chatbot: Leveraging Automated and Personalized Health Information Communication to Reduce Disparities in Maternal and Child Health

聊天机器人 Rosie：利用自动化和个性化的健康信息通信来减少母婴健康差异

• 批准号: 10908148
• 负责人: Elizabeth Marie Aparicio
• 金额: $ 22.19万
• 依托单位: UNIV OF MARYLAND, COLLEGE PARK
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-24 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10908148
• 关键词: Address; Algorithms; Anxiety; Appointment; Artificial Intelligence; Back to Sleep; Behavioral Sciences; Biometry; Breast Feeding; Child; Childbirth; Communication; Communities; Complex; Computer software; Development; Discrimination; Emergency department visit; Ensure; Epidemiology; Experimental Designs; Family; Focus Groups; Friends; Geography; Goals; Grant; Health; Health Professional; Health behavior; Home visitation; Hour; Immunization; Individual; Infant Mortality; Informatics; Internet; Intervention; Knowledge; Left; Libraries; Maternal Mortality; Maternal and Child Health; Medical; Medicine; Methodology; Methods; Minority Women; Misinformation; Mothers; Natural Language Processing; Participant; Population; Postpartum Depression; Pregnancy; Preventive; Procedures; Public Health; Quality of life; Randomized; Randomized, Controlled Trials; Reduce health disparities; Resources; Risk; Role; Sampling; Technology; Testing; Text Messaging; Underserved Population; Visit; Vulnerable Populations; Well Child Visits; Woman; care outcomes; chatbot; checkup examination; community clinic; computer science; coping; cost; cost effective; design; disparity reduction; ethnic disparity; ethnic minority; family support; flexibility; health care service organization; health organization; improved; infant nutrition; infant outcome; maternal outcome; new technology; open source; outcome disparities; patient oriented; personalized approach; phrases; population based; programs; prototype; racial disparity; racial health disparity; racial minority; recruit; response; scale up; screening guidelines; stressor; tool; virtual; web page; women of color

PROJECT SUMMARY/ABSTRACT This proposal has the potential to alter the way health information is presented to vulnerable populations. Our proposal promotes a more flexible and tailored approach to reach underserved groups. Racial/ethnic minority women are at increased risk for postpartum depression, and their children as less likely to have had well-child checkups in the past year. Moreover, racial/ethnic disparities are still prevalent for maternal and infant mortality as well as various health behaviors such as safe sleep practices, breastfeeding, and infant nutrition. Currently, some popular programs involve resource-intensive home visits (limited in scale due to staff and cost constraints) or non-personalized text messages (may not directly address an individual’s questions). We propose the development of a chatbot that addresses both of these possible limitations by representing a scalable tool that can have widespread reach across geographies and is personalized and responsive to an individual’s specific informational needs. We have built a prototype of the chatbot, Rosie, capable of engaging in live question-and-answer sessions. Rosie is able to respond to 334 popular questions that new mothers may have. Pretests with mother groups and Mary’s Center patients have showed a positive reception to the chatbot. Over the course of the grant, we will leverage recent advances in natural language processing and the emergence of efforts to aggregate massive amounts of health information, to assemble a comprehensive health information library. We will further refine Rosie’s dialogue analyzer and response inference engine to robustly recognize and respond to user’s questions in the various and complex ways they can phrase a question. We will test the hypothesis that Rosie may lower risk of postpartum depression, decrease emergency room visits, and increase attendance of well-baby visits. We will employ primarily a virtual recruitment strategy to conduct a randomized controlled trial to evaluate the impact of this intervention on maternal and infant outcomes. Our investigative team—comprised of experts in the field of epidemiology, computer science, biostatistics, and maternal and child health experts—is uniquely suited to implement the study aims. Our Specific Aims are: 1) Develop technology for a chatbot, Rosie, that will provide health informational support to vulnerable mothers the moment they need it; 2) Evaluate the use of Rosie on maternal and infant outcomes; and 3) Release an open-source packet for the construction of a chatbot. Rosie provides informational support to vulnerable moms the moment they need it and safeguards new moms from misinformation that is common on the web with the ultimate goal of closing the gap in maternal and infant outcomes. Results and tools developed from this proposal can be utilized to inform population-based strategies to reduce health disparities and improve health.

项目概要/摘要 该提案有可能改变向弱势群体提供健康信息的方式。我们的 该提案提倡采取更灵活、更有针对性的方法来覆盖服务不足的群体。种族/少数族裔 女性患产后抑郁症的风险增加，她们的孩子也不太可能生出健康的孩子 过去一年的检查。此外，孕产妇和婴儿死亡率的种族/民族差异仍然普遍存在 以及各种健康行为，如安全睡眠习惯、母乳喂养和婴儿营养。现在， 一些受欢迎的项目涉及资源密集型家访（由于人员和成本的原因，规模有限） 限制）或非个性化短信（可能不会直接解决个人的问题）。我们 建议开发一个聊天机器人，通过代表一个解决这两个可能的限制 可扩展的工具，可以广泛覆盖各个地区，并且是个性化的并且能够响应 个人的特定信息需求。我们已经构建了聊天机器人 Rosie 的原型，能够与 在现场问答环节中。 Rosie 能够回答新妈妈们可能会遇到的 334 个常见问题 有。母亲团体和玛丽中心患者的预测试表明，聊天机器人受到了积极的欢迎。 在资助过程中，我们将利用自然语言处理和 努力汇总大量健康信息，形成全面的健康信息 健康信息图书馆。我们将进一步完善 Rosie 的对话分析器和响应推理引擎 能够以各种复杂的方式强有力地识别和回答用户的问题 问题。我们将检验罗西可能降低产后抑郁症风险、减少紧急情况的假设 房间探访，并增加健康婴儿探访的人数。我们将主要采用虚拟招聘策略 进行随机对照试验，评估该干预措施对母婴的影响 结果。我们的调查团队由流行病学、计算机科学、 生物统计学和妇幼健康专家——非常适合实现研究目标。我们的 具体目标是： 1) 开发聊天机器人 Rosie 的技术，该机器人将为以下人群提供健康信息支持： 脆弱的母亲在需要的时候； 2) 评估Rosie的使用对孕产妇和婴儿结局的影响； 3) 发布用于构建聊天机器人的开源包。罗西提供信息支持 在弱势妈妈需要的时候向她们提供帮助，并保护新妈妈免受常见错误信息的影响 在网络上，其最终目标是缩小孕产妇和婴儿结局的差距。结果和工具 根据该提案制定的成果可用于为减少健康差距的基于人口的战略提供信息 并改善健康。

项目成果

A Multistate Study on Housing Factors Influential to Heat-Related Illness in the United States.

• DOI: 10.3390/ijerph192315762
• 发表时间: 2022-11-26
• 期刊: INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
• 作者: Hu, Ming;Zhang, Kai;Nguyen, Quynh Camthi;Tasdizen, Tolga;Krusche, Krupali Uplekar
• 通讯作者: Krusche, Krupali Uplekar

Association of Neighborhood Racial and Ethnic Composition and Historical Redlining With Built Environment Indicators Derived From Street View Images in the US.

邻里种族和种族组成以及历史上的红线与美国街景图像得出的建筑环境指标的关联。

• DOI: 10.1001/jamanetworkopen.2022.51201
• 发表时间: 2023-01-03
• 期刊: JAMA NETWORK OPEN
• 影响因子: 13.8
• 作者: Yang, Yukun;Cho, Ahyoung;Nguyen, Quynh;Nsoesie, Elaine O.
• 通讯作者: Nsoesie, Elaine O.

Rosie, a Health Education Question-and-Answer Chatbot for New Mothers: Randomized Pilot Study.

• DOI: 10.2196/51361
• 发表时间: 2024-01-12
• 期刊: JMIR FORMATIVE RESEARCH
• 影响因子: 2.2
• 作者: Nguyen, Quynh C;Aparicio, Elizabeth M;Jasczynski, Michelle;Channell Doig, Amara;Yue, Xiaohe;Mane, Heran;Srikanth, Neha;Gutierrez, Francia Ximena Marin;Delcid, Nataly;He, Xin;Boyd-Graber, Jordan
• 通讯作者: Boyd-Graber, Jordan

Vigilance and Protection: How Asian and Pacific Islander, Black, Latina, and Middle Eastern Women Cope with Racism.

• DOI: 10.1007/s40615-023-01560-2
• 发表时间: 2024-04
• 期刊: JOURNAL OF RACIAL AND ETHNIC HEALTH DISPARITIES
• 影响因子: 3.9
• 作者: Criss, Shaniece;Kim, Melanie;De La Cruz, Monica M;Thai, Nhung;Nguyen, Quynh C;Hswen, Yulin;Gee, Gilbert C;Nguyen, Thu T
• 通讯作者: Nguyen, Thu T

Examination of the Public's Reaction on Twitter to the Over-Turning of Roe v Wade and Abortion Bans.

• DOI: 10.3390/healthcare10122390
• 发表时间: 2022-11-29
• 期刊: HEALTHCARE
• 影响因子: 2.8
• 作者: Mane, Heran;Yue, Xiaohe;Yu, Weijun;Doig, Amara Channell;Wei, Hanxue;Delcid, Nataly;Harris, Afia-Grace;Nguyen, Thu T. T.;Nguyen, Quynh C. C.
• 通讯作者: Nguyen, Quynh C. C.