Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets
Bibliographic record
Abstract
The significance of Findable, Accessible, Interoperable, and Reusable (FAIR) data is increasing, particularly in the context of enhancing data reuse in research. The National Research Data Infrastructure for Personal Health Data (NFDI4Health) aims to enhance the findability, reusability, and interoperability of health data derived from epidemiological, clinical, and public health studies. NFDI4Health has established the German Central Health Study Hub to improve health data findability through rich metadata. The Maelstrom Catalog, provided by Maelstrom Research, offers a comprehensive dataset of labeled and harmonized study variables, thereby enhancing the findability and reusability of epidemiological data. Both platforms rely on standardized categorization to optimize data reuse. To facilitate this process, NFDI4Health developed the Metadata Annotation Workbench, which supports metadata annotation with standardized vocabulary. This paper presents an AI solution for automatic classification and annotation integrated into this service, using a BioBERT-based text classifier. The model achieved a weighted F1-score of over 92% and demonstrated improved annotation performance, particularly for non-experts. It accelerates variable categorization, thereby enhancing data findability and re-use. As a result, the categorization of study variables can be accelerated and we are confident that the further development of such AI approaches will reduce curatorial workload and promote semantically annotated interoperable data catalogs.
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 | 0.005 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".