Use of a Novel Artificial Intelligence Platform on Mobile Devices to Assess Dosing Compliance in a Phase 2 Clinical Trial in Subjects With Schizophrenia
Bibliographic record
Abstract
BACKGROUND: Accurately monitoring and collecting drug adherence data can allow for better understanding and interpretation of the outcomes of clinical trials. Most clinical trials use a combination of pill counts and self-reported data to measure drug adherence, despite the drawbacks of relying on these types of indirect measures. It is assumed that doses are taken, but the exact timing of these events is often incomplete and imprecise. OBJECTIVE: The objective of this pilot study was to evaluate the use of a novel artificial intelligence (AI) platform (AiCure) on mobile devices for measuring medication adherence, compared with modified directly observed therapy (mDOT) in a substudy of a Phase 2 trial of the α7 nicotinic receptor agonist (ABT-126) in subjects with schizophrenia. METHODS: AI platform generated adherence measures were compared with adherence inferred from drug concentration measurements. RESULTS: The mean cumulative pharmacokinetic adherence over 24 weeks was 89.7% (standard deviation [SD] 24.92) for subjects receiving ABT-126 who were monitored using the AI platform, compared with 71.9% (SD 39.81) for subjects receiving ABT-126 who were monitored by mDOT. The difference was 17.9% (95% CI -2 to 37.7; P=.08). CONCLUSIONS: Using drug levels, this substudy demonstrates the potential of AI platforms to increase adherence, rapidly detect nonadherence, and predict future nonadherence. Subjects monitored using the AI platform demonstrated a percentage change in adherence of 25% over the mDOT group. Subjects were able to use the technology successfully for up to 6 months in an ambulatory setting with early termination rates that are comparable to subjects outside of the substudy. TRIAL REGISTRATION: ClinicalTrials.gov NCT01655680 https://clinicaltrials.gov/ct2/show/NCT01655680?term=NCT01655680.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".