Using gamification, predictive analytics, artificial intelligence, and Alexa Voice to optimize user experience for individuals living with AD/ADRD and their caregivers

使用游戏化、预测分析、人工智能和 Alexa Voice 来优化 AD/ADRD 患者及其护理人员的用户体验

• 批准号: 10468936
• 负责人: Matthew Golden
• 金额: $ 125.64万
• 依托单位: MAPHABIT, INC.
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-15 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10468936
• 关键词: Activities of Daily Living; Address; Alzheimer' s Disease; Alzheimer' s disease diagnosis; Alzheimer' s disease related dementia; American; Area; Artificial Intelligence; Award; Behavior; Behavior Therapy; Behavioral; Biometry; Brain; Caregivers; Caring; Clinical; Clinical Trials; Cognitive; Cohort Studies; Communities; Computer software; Cues; Data; Dementia; Development; Disease; Early Intervention; Early treatment; Effectiveness; Family; Family member; Friends; Goals; Habits; Health Status; Health system; Healthcare; Home Care Services; Hospitals; Impaired cognition; Independent Living; Individual; Journals; Learning; Legal patent; Link; Maps; Marketing; Memory; Memory impairment; Motivation; Neostriatum; Neuropsychology; Neurosciences; Outpatients; Paper; Patients; Pattern; Peer Review; Persons; Pharmacotherapy; Phase; Play; Predictive Analytics; Procedures; Provider; Public Health; Quality of life; Randomized Clinical Trials; Reporting; Rewards; Science; Self Care; Self-Help Devices; Services; Short-Term Memory; Signal Transduction; Small Business Innovation Research Grant; Social Interaction; Social Network; Social isolation; Societies; Standardization; Symptoms; System; Technology; Telephone; Testing; Therapeutic; Time; Translating; United States National Institutes of Health; Visual; Visual system structure; Voice; Work; base; behavioral outcome; clinically relevant; commercialization; cost; daily functioning; dashboard; data streams; decision-making capacity; dementia caregiving; design; diagnostic tool; evidence base; experience; health goals; human old age (65+); improved; innovation; intrinsic motivation; multiple data sources; novel; patient home care; predictive modeling; pressure; promoter; response; skills; social; social anxiety; tool; user-friendly; virtual reality; vision science; visual map

More than 5.8 million Americans live with dementia and one in 10 Americans over the age of 65 suffer from a diagnosis of Alzheimer’s disease and Alzheimer’s related dementias (AD/ADRD). There are no cures for AD and drug treatments have little overall impact on the course and symptoms of disease. There are no diagnostic tools that can reliably identify people in the early stages of the disease. Individuals living with AD/ADRD have the same quality of life needs as individuals without dementia, including the ability to successful complete routine activities of daily living and maintain satisfying levels of independence and autonomy. However, in the setting of progressively diminishing memory and worsening abilities for self-care, individuals living with AD/ADRD experience progressive losses in independent decision- making capacity and quality of life. Social isolation and anxiety are disabling consequences of this condition. The MapHabitTM system (MHS), is an award-winning (NIH/NIA 1st place Eureka Award) patented, neuroscience-based assistive technology app that helps the memory-impaired accomplish activities of daily living, maintain their independence, and improves overall quality of life for users. The MHS product leverages the science of visual mapping to cue appropriate behavior in the AD setting. In this SBIR Phase II application, MapHabit will further develop the utility and effectiveness of the MHS visual mapping technology to enhance its commercialization and marketing potential by increasing its “stickiness” (i.e., motivation to engage with the app) and to establish a more substantive evidence base for its effects on improved quality of life and daily functioning. We propose two specific aims: Aim 1 – MapHabit will optimize the user experience for individuals with AD/ADRD by supplementing its visual mapping software with gamification technology via a partnership with a virtual reality and in-app games company that serves healthcare needs. Social networking (via gaming with friends and other residents) will be developed to build social connectivity and increase competition, both of which are known to increase “stickiness” and keep users engaged and motivated to adhere to behavioral interventions such as ADLs. We will conduct a 6-month clinical trial to assess behavioral outcomes. Aim 2 – MapHabit will develop a predictive analytics framework using the biometric and behavioral data streams from individuals as they use visual maps to carry out their ADLs. Partnering with a healthcare artificial intelligence company, we will conduct an observational cohort study to collect and integrate 16 months of data streams from 15 dyads from multiple data sources, including gamification and social networking using the MHS, standardized neuropsychological assessments of the patients, and assessments from caregivers. These novel data will be used to explore new predictive models that will potentially indicate early warnings of oncoming cognitive decline.

超过 580 万美国人患有痴呆症，65 岁以上的美国人中有十分之一患有痴呆症 阿尔茨海默病和阿尔茨海默病相关痴呆（AD/ADRD）。 AD 无法治愈，药物治疗也无法治愈 对疾病的病程和症状总体影响不大。没有可以可靠识别的诊断工具 处于疾病早期阶段的人。 AD/ADRD 患者的生活质量需求与 没有痴呆症的人，包括成功完成日常生活活动和维持正常生活的能力 满足独立性和自主性的水平。然而，在记忆力逐渐衰退的情况下 AD/ADRD 患者的自我护理能力不断恶化，他们的独立决策能力逐渐丧失。 创造能力和生活质量。社会孤立和焦虑是这种情况的致残后果。这 MapHabitTM 系统 (MHS) 是一项屡获殊荣（NIH/NIA 第一名尤里卡奖）的专利系统，基于神经科学 辅助技术应用程序，帮助记忆受损的人完成日常生活活动，保持他们的 独立性，并提高用户的整体生活质量。 MHS 产品利用视觉映射科学 在 AD 设置中提示适当的行为。在此 SBIR 二期应用中，MapHabit 将进一步开发实用程序和 MHS 视觉映射技术的有效性，通过以下方式增强其商业化和营销潜力 增加其“粘性”（即使用应用程序的动机）并为以下方面建立更实质性的证据基础： 它对改善生活质量和日常功能的影响。我们提出两个具体目标： 目标 1 – MapHabit 将 通过补充其视觉映射软件，优化 AD/ADRD 患者的用户体验 通过与满足医疗保健需求的虚拟现实和应用内游戏公司合作，开发游戏化技术。 将开发社交网络（通过与朋友和其他居民进行游戏）以建立社交联系和 增加竞争，众所周知，这两者都可以增加“粘性”并保持用户的参与度和积极性 坚持行为干预，例如 ADL。我们将进行为期 6 个月的临床试验来评估行为结果。 目标 2 – MapHabit 将使用生物识别和行为数据流开发预测分析框架 个人使用视觉地图来执行他们的 ADL。与一家医疗人工智能公司合作， 我们将进行一项观察性队列研究，收集并整合来自 15 个群体的 16 个月的数据流 多个数据源，包括使用 MHS 的游戏化和社交网络、标准化神经心理学 患者的评估以及护理人员的评估。这些新颖的数据将用于探索新的预测 模型可能会预示即将到来的认知能力下降的早期预警。