SCH: INT: Personalized Proactive Diabetes Self-Management and Social Networking for American Indians

糖尿病在美国印第安人社区的流行是一个严重的公共卫生挑战。由于糖尿病的日常护理主要由患者及其家属来处理，因此糖尿病控制的有效性在很大程度上受自我护理策略和行为的影响。本项目基于居住在中西部上游保留地社区的AI患者独特的社会经济、文化和地理地位，提出了一个主动糖尿病自我护理移动平台。该移动平台将人工智能糖尿病患者与其医疗设备、医疗团队和类似患者连接起来，并提供个性化的糖尿病护理预测、推荐和社交网络。它将糖尿病管理从传统的反应性和以医院为中心的护理转变为预防性、前瞻性、循证性和以人为中心的护理。该项目还将为研究生和本科生提供宝贵的研究机会，特别是来自代表性不足的人群。该项目的目标是开发一种综合的、可获得的、具有成本效益的解决方案，以改善人工智能患者的糖尿病自我管理和社交网络。考虑到大多数人工智能社区中手机的使用近乎无所不在，我们提出了一个基于手机的平台来提供智能和个性化的服务。开发了一个生物文化本体来模拟AI患者的独特特征。基于用户的本体论概况，通过基于本体论的推理和机器学习方法，将个性化的预测和推荐传递给人工智能患者。基于语义的社会匹配作为一种技术和智力框架，用于连接具有相似性的人工智能患者，形成在线同伴支持社区。开发了个性化的自我管理信任和隐私机制，以建立安全的用户关系。为了提高系统的可用性，实现了一个多模态界面，以根据用户的物理和社会环境向用户提供具有适当输入和输出模式的信息。

The epidemic of diabetes in American Indian (AI) communities is a serious public health challenge. As daily diabetes care is primarily handled by the patients and their families, the effectiveness of diabetes control is largely impacted by self-care strategies and behaviors. This project proposes a proactive diabetes self-care mobile platform based on the unique socio-economic, cultural, and geographical status of AI patients living in a reservation community in the upper Midwest. The mobile platform connects AI diabetic patients to their medical devices, healthcare team and similar patients, and offers personalized prediction, recommendation, and social networking regarding diabetes care. It transforms diabetes management from the traditional reactive and hospital-centered care to preventive, proactive, evidence-based, and person-centered care. This project will also provide valuable research opportunities for both graduate and undergraduate students, especially from underrepresented populations.The goal of the project is to develop an integrated, accessible, cost-effective solution for improved diabetes self-management and social networking for AI patients. Considering the quasi-ubiquitous use of cellphones in most AI communities, a cellphone-based platform is proposed to provide smart and personalized service. A biocultural ontology is developed to model the unique characteristics of AI patients. Based on a user's ontological profile, through ontology-based reasoning and machine learning approaches, personalized prediction and recommendation are delivered to the AI patient. Semantics-based social matching is applied as a technical and intellectual framework for connecting AI patients with similarities to form online peer support communities. Personalized self-managed trust and privacy mechanisms are developed to establish secure user relationships. To improve system usability, a multimodal interface is implemented to deliver information with appropriate input and output modalities to a user based on the user's physical and social context.