Smith Amy M, Marin Anna, DeCaro Renee E, Feinn Richard, Wack Audrey, Hughes Gregory I, Rivard Nathaniel, Umashankar Akshay, Turk Katherine W, Budson Andrew E
Blank Slate Technologies, LLC, Arlington, VA, United States.
Center for Translational Cognitive Neuroscience, VA Boston Healthcare System, Boston, MA, United States.
JMIR Form Res. 2024 Jul 19;8:e51943. doi: 10.2196/51943.
Spaced retrieval is a learning technique that involves engaging in repeated memory testing after increasingly lengthy intervals of time. Spaced retrieval has been shown to improve long-term memory in Alzheimer disease (AD), but it has historically been difficult to implement in the everyday lives of individuals with AD.
This research aims to determine, in people with mild cognitive impairment (MCI) due to AD, the efficacy and feasibility of a mobile app that combines spaced retrieval with a machine learning algorithm to enhance memory retention. Specifically, the app prompts users to answer questions during brief daily sessions, and a machine learning algorithm tracks each user's rate of forgetting to determine the optimal spacing schedule to prevent anticipated forgetting.
In this pilot study, 61 participants (young adults: n=21, 34%; healthy older adults: n=20, 33%; people with MCI due to AD: n=20, 33%) used the app for 4 weeks to learn new facts and relearn forgotten name-face associations. Participation during the 4-week period was characterized by using the app once per day to answer 15 questions about the facts and names. After the 4-week learning phase, participants completed 2 recognition memory tests approximately 1 week apart, which tested memory for information they had studied using the app as well as information they had not studied.
After using the mobile app for 1 month, every person with MCI due to AD demonstrated improvements in memory for new facts that they had studied via the app compared to baseline (P<.001). All but one person with MCI due to AD (19/20, 95%) showed improvements of more than 10 percentage points, comparable to the improvements shown by young adults and healthy older adults. Memory for name-face associations was similarly improved for all participant groups after using the app but to a lesser degree. Furthermore, for both new facts and name-face associations, we found no memory decay for any participant group after they took a break of approximately 1 week from using the app at the end of the study. Regarding usability, of the 20 people with MCI due to AD, 16 (80%) self-adhered to the app's automated practice schedule, and half of them (n=10, 50%) expressed an interest in continuing to use it.
These results demonstrate early evidence that spaced retrieval mobile apps are both feasible for people with early-stage AD to use in their everyday lives and effective for supporting memory retention of recently learned facts and name-face associations.
间隔检索是一种学习技巧，包括在间隔时间越来越长之后进行重复的记忆测试。间隔检索已被证明可改善阿尔茨海默病（AD）患者的长期记忆，但在AD患者的日常生活中，它历来难以实施。
本研究旨在确定对于因AD导致轻度认知障碍（MCI）的人群，一款将间隔检索与机器学习算法相结合以增强记忆保持的移动应用程序的有效性和可行性。具体而言，该应用程序在每日简短时段内提示用户回答问题，并且一种机器学习算法会跟踪每个用户的遗忘率，以确定防止预期遗忘的最佳间隔时间表。
在这项试点研究中，61名参与者（年轻成年人：n = 21，34%；健康老年人：n = 20，33%；因AD导致MCI的人群：n = 20，33%）使用该应用程序4周，以学习新事实并重新学习遗忘的姓名 - 面孔关联。在这4周期间的参与方式为每天使用该应用程序一次，回答15个关于事实和姓名的问题。在为期4周的学习阶段结束后，参与者在大约相隔1周的时间里完成了2次识别记忆测试，这些测试针对他们使用该应用程序学习过的信息以及未学习过的信息进行记忆测试。
在使用该移动应用程序1个月后，与基线相比，每一位因AD导致MCI的人在通过该应用程序学习的新事实的记忆方面都有改善（P <.001）。除一名因AD导致MCI的人外（19/20，95%），所有人的改善幅度都超过了10个百分点，这与年轻成年人和健康老年人所显示的改善幅度相当。在使用该应用程序后，所有参与者组在姓名 - 面孔关联的记忆方面同样有所改善，但程度较小。此外，对于新事实和姓名 - 面孔关联，在研究结束时，当所有参与者组从使用该应用程序中休息大约1周后，我们发现他们的记忆没有衰退。关于可用性，在20名因AD导致MCI的人中，16人（80%）自行遵守了该应用程序的自动练习时间表，其中一半人（n = 10，50%）表示有继续使用它的兴趣。
这些结果初步证明，间隔检索移动应用程序对于早期AD患者在日常生活中使用既可行，又能有效支持对最近学习的事实和姓名 - 面孔关联的记忆保持。
