An Ecologically Valid, Longitudinal, and Unbiased Assessment of Treatment Efficacy in Alzheimer Disease (the EVALUATE-AD Trial): Proof-of-Concept Study (Preprint)
Bibliographic record
Abstract
BACKGROUND The current clinical trial assessment methodology relies on a combination of self-report measures, cognitive and physical function tests, and biomarkers. This methodology is limited by recall bias and recency effects in self-reporting and by assessments that are brief, episodic, and clinic based. Continuous monitoring of ecologically valid measures of cognition and daily functioning in the community may provide a more sensitive method to detect subtle, progressive changes in patients with cognitive impairment and dementia. OBJECTIVE This study aimed to present an alternative trial approach using a home-based sensing and computing system to detect changes related to common treatments employed in Alzheimer disease (AD). This paper introduces an ongoing study that aims to determine the feasibility of capturing sensor-based data at home and to compare the sensor-based outcomes with conventional outcomes. We describe the methodology used in the assessment protocol and present preliminary results of feasibility measures and examples of data related to medication-taking behavior, activity levels, and sleep. METHODS The EVALUATE-AD (Ecologically Valid, Ambient, Longitudinal and Unbiased Assessment of Treatment Efficacy in Alzheimer’s Disease) trial is a longitudinal naturalistic observational cohort study recruiting 30 patients and 30 spouse coresident care partners. Participants are monitored continuously using a home-based sensing and computing system for up to 24 months. Outcome measures of the automated system are compared with conventional clinical outcome measures in AD. Acceptance of the home system and protocol are assessed by rates of dropout and protocol adherence. After completion of the study monitoring period, a composite model using multiple functional outcome measures will be created that represents a behavioral-activity signature of initiating or discontinuing AD-related medications, such as cholinesterase inhibitors, memantine, or antidepressants. RESULTS The home-based sensing and computing system has been well accepted by individuals with cognitive impairment and their care partners. Participants showed good adherence to the completion of a weekly web-based health survey. Daily activity, medication adherence, and total time in bed could be derived from algorithms using data from the sensing and computing system. The mean monitoring time for current participants was 14.6 months. Medication adherence, as measured with an electronic pillbox, was 77% for participants taking AD-related medications. CONCLUSIONS Continuous, home-based assessment provides a novel approach to test the impact of new or existing dementia treatments generating objective, clinically meaningful measures related to cognition and everyday functioning. Combining this approach with the current clinical trial methodology may ultimately reduce trial durations, sample size needs, and reliance on a clinic-based assessment. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/17603
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 | 0.022 | 0.016 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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".