hdmax2, an R package to perform high dimension mediation analysis
Bibliographic record
Abstract
Mediation analysis plays a crucial role in epidemiology, unraveling the intricate pathways through which exposures exert influence on health outcomes. Recent advances in high-throughput sequencing techniques have generated growing interest in applying mediation analysis to explore the causal relationships between patient environmental exposure, molecular features (such as omics data) and various health outcomes. Mediation analysis handling high-dimensional mediators raise a number of statistical challenges. Despite the emergence of numerous methods designed to tackle these challenges, the majority are limited to continuous outcomes. Furthermore, these advanced statistical approaches have yet to find widespread adoption among epidemiologists and health data scientists in their day-to-day practices. To address this gap, we introduce a method specifically tailored for high-dimensional mediation analysis using the max-squared method (HDMAX2). This tool aims to bridge the current divide by providing a practical solution for researchers and practitioners eager to explore intricate causal relationships in health data involving complex molecular features. Here we improve the HDMAX2 method, and expand its capabilities to accommodate multivariate exposure and non-continuous outcomes. This improvement enables its application to a diverse array of mediation analysis scenarios, mirroring the complexity often encountered in healthcare data. To enhance accessibility for users with varying expertise, we release an R package called hdmax2. This package allows users to estimate the indirect effects of mediators, calculate the overall indirect effect of mediators, and facilitates the execution of high-dimensional mediation analysis. We demonstrate its application through two high-dimensional case studies examining DNA methylation and gene expression as mediators, with binary outcomes and both continuous and binary exposures. These examples illustrate practical aspects of the method, including latent factor selection and mediator identification.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".