Bosco Cristina, Otenen Ege, Osorio Torres John, Nguyen Vivian, Chheda Darshil, Peng Xinran, Jessup Nenette M, Himes Anna K, Cureton Bianca, Lu Yvonne, Hill Carl V, Hendrie Hugh C, Barnes Priscilla A, Shih Patrick C
Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, United States.
School of Nursing, Indiana University, Indianapolis, IN, United States.
JMIR Aging. 2025 Jan 8;8:e60566. doi: 10.2196/60566.
Many members of Black American communities, faced with the high prevalence of Alzheimer disease and related dementias (ADRD) within their demographic, find themselves taking on the role of informal caregivers. Despite being the primary individuals responsible for the care of individuals with ADRD, these caregivers often lack sufficient knowledge about ADRD-related health literacy and feel ill-prepared for their caregiving responsibilities. Generative AI has become a new promising technological innovation in the health care domain, particularly for improving health literacy; however, some generative AI developments might lead to increased bias and potential harm toward Black American communities. Therefore, rigorous development of generative AI tools to support the Black American community is needed.
The goal of this study is to test Lola, a multimodal mobile app, which, by relying on generative AI, facilitates access to ADRD-related health information by enabling speech and text as inputs and providing auditory, textual, and visual outputs.
To test our mobile app, we used the cognitive walk-through methodology, and we recruited 15 informal ADRD caregivers who were older than 50 years and part of the Black American community living within the region. We asked them to perform 3 tasks on the mobile app (ie, searching for an article on brain health, searching for local events, and finally, searching for opportunities to participate in scientific research in their area), then we recorded their opinions and impressions. The main aspects to be evaluated were the mobile app's usability, accessibility, cultural relevance, and adoption.
Our findings highlight the users' need for a system that enables interaction with different modalities, the need for a system that can provide personalized and culturally and contextually relevant information, and the role of community and physical spaces in increasing the use of Lola.
Our study shows that, when designing for Black American older adults, a multimodal interaction with the generative AI system can allow individuals to choose their own interaction way and style based upon their interaction preferences and external constraints. This flexibility of interaction modes can guarantee an inclusive and engaging generative AI experience.
许多美国黑人社区成员，鉴于其人群中阿尔茨海默病及相关痴呆症（ADRD）的高患病率，发现自己承担起了非正式护理人员的角色。尽管是负责照顾ADRD患者的主要人员，但这些护理人员往往缺乏足够的关于ADRD相关健康素养的知识，并且对其护理责任准备不足。生成式人工智能已成为医疗保健领域一项新的有前景的技术创新，特别是在提高健康素养方面；然而，一些生成式人工智能的发展可能会导致对美国黑人社区的偏见增加和潜在危害。因此，需要严格开发支持美国黑人社区的生成式人工智能工具。
本研究的目标是测试一款多模式移动应用程序Lola，它依靠生成式人工智能，通过将语音和文本作为输入并提供听觉、文本和视觉输出，促进获取与ADRD相关的健康信息。
为了测试我们的移动应用程序，我们使用了认知走查方法，并招募了15名年龄超过50岁且居住在该地区的美国黑人社区的非正式ADRD护理人员。我们要求他们在移动应用程序上执行3项任务（即搜索一篇关于大脑健康的文章、搜索当地活动，最后搜索在其所在地区参与科学研究的机会），然后记录他们的意见和印象。要评估的主要方面是移动应用程序的可用性、可及性、文化相关性和采用情况。
我们的研究结果突出了用户对一个能够实现不同模式交互的系统的需求，对一个能够提供个性化且与文化和背景相关信息的系统的需求，以及社区和物理空间在增加Lola使用方面的作用。
我们的研究表明，在为美国黑人老年人设计时，与生成式人工智能系统的多模式交互可以让个人根据自己的交互偏好和外部限制选择自己的交互方式和风格。这种交互模式的灵活性可以保证一种包容且引人入胜的生成式人工智能体验。
