MétaCan
Menu
Back to cohort

Abstract A002: A Bayesian Machine Learning Approach for Estimating Treatment Effects in Decentralized Clinical Trials

2025· article· en· W4412163746 on OpenAlexaboutno aff
Ying Yuan

Bibliographic record

VenueClinical Cancer Research · 2025
Typearticle
Languageen
FieldMathematics
TopicStatistical Methods in Clinical Trials
Canadian institutionsnot available
Fundersnot available
KeywordsBayesian probabilityClinical trialMachine learningArtificial intelligenceMedicineComputer scienceIntensive care medicineInternal medicine

Abstract

fetched live from OpenAlex

Abstract A decentralized clinical trial (DCT) is a type of clinical trial where some or all trial-related activities occur at locations other than traditional clinical trial sites (e.g., at home). DCTs offer great flexibility and convenience for participants, potentially improving recruitment and retention rates. However, they are more susceptible to bias and measurement errors compared to conventional randomized clinical trials due to the off-site measurement of endpoints. This article introduces a Bayesian additive regression trees approach to estimate the conditional average treatment effect (cATE) in hybrid longitudinal DCTs, where endpoints are measured off-site at some time points and on-site at other time points. Extensive simulation studies demonstrate that our proposed method is not only robust but also more efficient than conventional approaches. We illustrate our approach using a dementia clinical trial. Citation Format: Ying Yuan. A Bayesian Machine Learning Approach for Estimating Treatment Effects in Decentralized Clinical Trials [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A002.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.169
metaresearch head score (Gemma)0.781
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Research integrity
Consensus categoriesMetaresearch
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.915
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.1690.781
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0040.001
Bibliometrics0.0000.001
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.883
GPT teacher head0.765
Teacher spread0.117 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designOther design
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueClinical Cancer ResearchSame topicStatistical Methods in Clinical TrialsFrench-language works237,207