A facial expression-based personalization engine (FPE) for monitoring and modulating real-time effective engagement in cognitive training in older adults at risk for AD/ADRD

摘要 如何确保在无人监督的情况下(例如，在家中、在自我指导的情况下)坚持进行计算机化认知训练 在有阿尔茨海默病(AD)或AD相关痴呆(AD/ADRD)风险的老年人中 未得到充分研究。R61/R33的目标是改进和测试一种基于面部表情的新型个性化 用于监控和调节实时有效交战的引擎(FPE)，最终目标是增强 有AD/ADRD风险的老年人长期坚持无人监督的认知训练。在这里，有效 敬业度被定义为某人在多大程度上积极参与并以显著的 在训练的同时注意和享受，在坚持和认知收获/可塑性之间寻求平衡 从训练中脱身。基于以前的工作，包括我们的工作，我们假设(1)精神疲劳揭示在 面部表情将反映受训者有效参与的程度，这可以通过调节来改变 任务新颖性；(2)我们建议的FPE将通过监控确保有效参与认知训练 学员面部表情和调节反应训练，促进学员长期坚守 训练与认知可塑性。在R61(Y1-Y2)中，我们将生成FPE，用于监测和调制实时- 通过改进我们已建立的应用程序，在有AD/ADRD风险的老年人中投入时间进行认知训练 编程界面采用的是我的一个阶段设计。在R33(Y3-Y5)，我们将进行第二阶段干预效果 无监督认知训练中有效投入度和依从性的比较研究 在有AD/ADRD风险的老年人中，有FPE和没有FPE的计划。我们将讨论在 这两个阶段都是：(A)确保拟议的FPE为R33(R61里程碑)做好准备；(B)评估和 为将来的实施测试进一步修订FPE(R33里程碑)。影响：拟议的FPE可能有助于 监测和改善无监督认知障碍老年人的有效参与和依从性 训练。在当前的应用中，我们将在一个名为处理速度的认知训练程序中测试FPE 训练。然而，在未来的研究中，这种FPE可能会嵌入到任何计算机化的认知训练中，以帮助 解决与遵守相关的问题。

ABSTRACT How to ensure adherence to computerized cognitive training in unsupervised circumstances (e.g., at-home, self- administered) in older adults at risk for Alzheimer’s disease (AD) or AD related dementia (AD/ADRD) is understudied. The objective of the R61/R33 is to refine and test a novel facial expression-based personalization engine (FPE) for monitoring and modulating real-time effective engagement, with an ultimate goal of enhancing long-term adherence in unsupervised cognitive training in older adults at risk for AD/ADRD. Here, Effective engagement is defined as the extent to which someone is actively engaged and performing with significant attention and enjoyment while training, addressing a balance between adherence and cognitive gains/plasticity from the training. Based on previous work, including ours, we hypothesize that (1) mental fatigue revealed in facial expressions will reflect a trainee’s degree of effective engagement, which can be modified by modulating task novelty; (2) our proposed FPE will ensure the effective engagement in cognitive training by monitoring trainee facial expressions and modulating training in response, promoting the trainee’s long-term adherence to the training and cognitive plasticity. In R61 (Y1-Y2), we will generate the FPE for monitoring and modulating real- time engagement in cognitive trainings in older adults at risk for AD/ADRD by refining our established application programming interface using a Stage I design. In R33 (Y3-Y5), we will conduct a Stage II intervention efficacy study comparing effective engagement and adherence in unsupervised cognitive training between training programs with vs. without FPE in older adults at risk for AD/ADRD. We will address milestones proposed in both stages to (a) ensure the readiness of the proposed FPE for R33 (R61 milestone) and (b) evaluate and further revision of FPE for future implementation test (R33 milestone). Impact: the proposed FPE may assist in monitoring and improving effective engagement and adherence in older adults with unsupervised cognitive training. In the current application, we will test FPE in a cognitive training program called speed of processing training. However, such FPE may be embedded to any computerized cognitive training in future studies to help address adherence related issues.