A digital twin methodology using real patient data for sample size reduction in Alzheimer's disease randomized controlled clinical trials
Andrews, D.; Golchi, S.; Collins, D. L.
Show abstract
INTRODUCTIONRecruitment for Alzheimers disease randomized controlled trials (RCTs) is difficult and expensive. To reduce RCT sample sizes, our Digital Twin Trial (DTT) methodology combines an interpretable cognitive decline prediction model with prediction-powered inference. METHODSFor DTT participants, our model identifies similar individuals ("Digital Twins") from a retrospective database and uses their cognitive scores to predict decline. Predictions adjust observed scores, reducing variance within treatment groups. We simulated 18-month DTTs and standard RCTs using mixed effects models of decline in Alzheimers Disease Neuroimaging Initiative subjects meeting lecanemabs Phase 3 inclusion criteria. RESULTSPredicted and observed change in Clinical Dementia Rating Sum-of-Boxes correlated at r = 0.4. DTTs required 1,855 subjects versus 2,170 for standard RCTs to detect a simulated 25% decline-slowing drug effect at 0.9 power. DTT Type 1 error was consistent with 0.05. DISCUSSIONDTTs could reduce recruitment and cost burdens. Model interpretability could help clinicians trust individualized prognoses.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Exploring the Feasibility of Using Real-World Data from a Large Clinical Data Research Network to Simulate Clinical Trials of Alzheimer’s Disease 95%
- Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults 94%
- Federated Target Trial Emulation using Distributed Observational Data for Treatment Effect Estimation 94%
Similar papers in this journal
- Assessing the transportability of clinical prediction models for cognitive impairment using causal models 95%
- Comparing randomized trial designs to estimate treatment effect in rare diseases with longitudinal models: a simulation study showcased by Autosomal Recessive Cerebellar Ataxias using the SARA score 93%
- Prediction-powered Inference for Clinical Trials 92%
Similar papers in this journal
Similar papers in this journal
- The New Therapeutics in Alzheimer’s Disease Longitudinal Cohort study (NTAD): study protocol 92%
- Returning Research Results That Indicate Risk of Alzheimer Disease Dementia to Healthy Participants in Longitudinal Studies (WeSHARE) 92%
- RESEARCH PROTOCOL: Large-scale evidence generation and evaluation across a network of databases for type 2 diabetes mellitus 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.