Algorithmic Spaced Retrieval Enhances Long-Term Memory in Alzheimer Disease: Case-Control Pilot Study
Bibliographic record
Abstract
BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".