Creating a Globally Distributed Multinational Dialysis Database - The ApolloDialDb Initiative
Bibliographic record
Abstract
Introduction Large amounts of data are captured during dialysis, yet multinational datasets are scarce due to challenges in harmonizing and integrating clinical data, as well as complying with data protection regulations across the world. A global kidney care provider, Fresenius Medical Care, approached this challenge and finalized the creation of an anonymized dialysis database, coined Apollo DialDb TM . We report the approach used for database creation and detail dialysis patient characteristics globally. Methods To create this globally distributed multinational database, data from different electronic clinical systems were extracted, covering routinely collected medical information from dialysis clinics worldwide. This data was harmonized, and then anonymized following a reidentification risk assessment conducted by the external company Privacy Analytics, Ontario, CA. The data was consolidated and is stored in a central cloud environment and will be updated periodically. Results Apollo DialDb TM captures data from January 2018 – March 2021 from 40 countries and 543,169 patients worldwide (4.6% Asia-Pacific, 13.9% Europe, Middle East, & Africa, 7.0% Latin America, 74.5% North America). It contains demographic data, 35,874,039 laboratory and 140,016,249 treatment observations as well as frequently recorded medication information, and clinical outcomes (e.g., hospitalization and mortality). Several regional differences can be observed using this data, such as age, treatment modality, and treatment time. Conclusion Creating a robust multinational dialysis database offers vast opportunities to conduct real-world research and data analytics, including the development of artificial intelligence models. These activities hold promise of advancing the understanding of kidney disease and dialysis therapies. It can serve as comparative resource for the nephrology community.
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 | 0.024 | 0.023 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".