SBIR Phase II: HealthText: Providing digital healthcare navigation for underserved communities in the US

这项小企业创新研究（SBIR）第二阶段项目的更广泛影响/商业潜力旨在进一步开发HealthText，这是一个人工智能（AI）驱动的数字健康信息和导航平台，专为医疗补助人群提供支持。该项目更广泛的影响在于，它有可能通过用户友好的短消息/短信服务（SMS）提供可信和相关的健康素养内容，从而解决资源不足社区的健康差距问题。由于缺乏健康和科学素养以及不信任，资源不足和少数群体社区的健康状况往往不佳，并脱离护理。基于技术的参与战略尚未充分覆盖这些服务不足的人群，因此HealthText成为弥补这一差距的宝贵解决方案。该项目的核心重点是直接向医疗补助受益人提供有针对性和文化上适当的健康信息宣传活动。通过相关内容和直观的短信，该平台旨在促进信任，提高医疗保健参与度，减少可避免的急诊室就诊、住院以及可预防的与健康相关的死亡。鉴于美国医疗补助计划每年的市场规模超过7200亿美元，改善服务不足和少数族裔社区的医疗保健参与相关的商业机会是巨大的。通过解决卫生知识普及和导航支持问题，该技术可以帮助实现每年可能超过1亿美元的大量成本节约，同时改善健康结果。该项目在医疗补助人群中展示了成功的参与成果，表明医疗补助保险公司有广泛商业化的潜力。该项目涉及使用聊天机器人和生成式人工智能等基于人工智能的通信工具，改进量身定制的卫生信息的交付。现有的人工智能资源没有考虑到在教育水平较低、服务不足的人群中普遍存在的沟通细微差别。为了解决这一问题，人工智能组件将专门为服务不足和少数群体社区设计，从而最大限度地减少对现有与健康相关的人工智能解决方案存在偏见的担忧。解决方案包括：1)采用高优先级质量度量的差距分析；2)利用定制内容和交付平台，通过文本、视频和按需AI聊天向患者发送有针对性的信息；3)评价改善后的临床效果。该奖项反映了美国国家科学基金会的法定使命，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。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project aims to further develop HealthText, an artificial intelligence (AI) driven digital health information and navigation platform tailored to support the Medicaid population. The project's broader impact lies in its potential to address health disparities in under-resourced communities by providing trusted and relatable health literacy content through a user-friendly Short Message/Messaging Service (SMS). Under-resourced and minority communities often experience poor health outcomes and disengagement from care due to low health and science literacy and distrust. Technology-based engagement strategies have not adequately reached these underserved populations, making HealthText a valuable solution to bridge this gap. The core focus of this project is to deliver targeted and culturally appropriate health information campaigns directly to Medicaid beneficiaries. Through relatable content and intuitive SMS messaging, the platform aims to foster trust, increase healthcare engagement, and reduce avoidable emergency room visits, hospital admissions, and preventable, health-related deaths. The commercial opportunity associated with improving healthcare engagement in underserved and minority communities is significant, given the annual US Medicaid market size of over $720 billion. By addressing health literacy and navigation support issues, this technology can help achieve substantial cost savings that could exceed $100 million annually, while improving health outcomes. This project has demonstrated successful engagement outcomes among Medicaid populations, suggesting the potential for widespread commercialization to Medicaid insurance companies. The project involves refining the delivery of tailored health information using AI-based communications tools like chatbots and generative AI. Existing AI resources lack consideration for communication nuances prevalent in underserved populations with lower educational achievements. To address this, the AI components will be specifically designed for underserved and minority communities, thereby minimizing concerns about bias in existing health-related AI solutions. The solution include: 1) gap analysis with high priority quality measures; 2) utilization of custom content and delivery platform to send targeted messaging via text, video, and on-demand AI chat to patients; and 3)evaluation of improved clinical outcomes.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.