STTR Phase I: Digital Advance Care Planning Platform

这一小型企业技术转让(STTR)第一阶段项目的广泛影响/商业潜力可能会通过高级护理规划(ACP)显著提高临终关怀的质量。患者的临终愿望并不总是可能与他们所接受的护理相一致。拟议的项目为机场核心计划开发了一个数字平台。该系统将使用机器学习指导对话，以提供适应个人和文化偏好的个性化视听内容。这一系统可能会改善许多人的临终关怀。这个小型企业技术转移(STTR)第一阶段项目解决了提供个性化平台的技术挑战，该平台执行数字激励访谈，并根据患者的个性调整视听内容和输入查询。将机器学习应用于ACP的一个主要障碍是个人和文化因素的可变性，以及对回答的完整性的验证。该项目的中心是收集和分析来自两个患者调查的心理测量数据，并结合其他健康信息。项目目标是：(A)为机器学习算法执行基准培训患者调查，以研究性别、种族和健康状况对ACP的影响；(B)利用数据指导的机器学习算法开发可靠的人物角色检测工具，避免引入无意识偏见；(C)证明与由人类卫生工作者管理的ACP和没有机器学习的静态在线平台相比，该平台提高了完成率和患者满意度；以及(D)展示数字化过程与患者意愿的一致性。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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 Technology Transfer (STTR) Phase I project may significantly improve the quality of end-of-life care through Advanced Care Planning (ACP). It is not always possible to align patients' end-of-life wishes with the care they receive. The proposed project develops a digital platform for ACP. This system will use a machine-learning guided dialogue to deliver personalized audiovisual content adapted to individual and cultural preferences. This system may improve palliative end-of-life care for many. This Small Business Technology Transfer (STTR) Phase I project addresses the technical challenge of providing a personalized platform that performs digital motivational interviewing and adapts audiovisual content and input queries to patients’ personae. A major hurdle of applying machine learning to ACP is the variability in personal and cultural factors, as well as validation of the integrity of the responses. The project centers on the collection and analysis of psychometric data from two patient surveys combined with other health information. The project objectives are: (a) Execute a benchmark training patient survey for the machine-learning algorithm for a study on the influence of gender, ethnicity, and health status on ACP; (b) Develop a reliable persona detection tool using machine learning algorithms guided by the data, avoiding the introduction of unconscious bias; (c) Demonstrate that the platform improves completion rates and patient satisfaction compared to ACP administered by human health workers and static online platforms without machine learning; and (d) Demonstrate the alignment of the digital process with patient wishes.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.