EHRs Data Harmonization Platform, an easy-to-use shiny app based on recodeflow for harmonizing and deriving clinical features
Bibliographic record
Abstract
Electronic health records (EHRs) contain important longitudinal information on individuals who have received medical care. Traditionally, EHRs have been used to support a wide range of administrative activities such as billing and clinical workflow, but, given the depth and breadth of clinical and demographic data they contain, they are increasingly being used to provide real-world data for research. Although EHR data have enormous research potential, the full realization of that potential requires a data management strategy that extracts from large EHR databases, that are collected from a range of care settings and time periods, well-documented research-relevant data that can be used by different researchers. Having a common well-documented data management strategy for EHR will support reproducible research and sharing documentation on research variables that are derived from EHR variables is important to open science. In this short paper, we describe the EHRs Data Harmonization Platform. The platform is based on an easy to use web app a publicly available at https://poxotn-arian-aminoleslami.shinyapps.io/Arian/ and as a standalone software package at https://github.com/ArianAminoleslami/EHRs-Data Harmonization-Platform, that is linked to an existing R library for data harmonization called recodeflow. The platform can be used to extract, document, and harmonize variables from EHR and it can also be used to document and share research variables that have been derived from those EHR data.
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 | 0.019 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.007 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.055 | 0.037 |
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".