Acute Kidney Injury in the Era of Big Data: The 15 <sup>th</sup> Consensus Conference of the Acute Dialysis Quality Initiative (ADQI)
Bibliographic record
Abstract
The world is immersed in "big data". Big data has brought about radical innovations in the methods used to capture, transfer, store and analyze the vast quantities of data generated every minute of every day. At the same time; however, it has also become far easier and relatively inexpensive to do so. Rapidly transforming, integrating and applying this large volume and variety of data are what underlie the future of big data. The application of big data and predictive analytics in healthcare holds great promise to drive innovation, reduce cost and improve patient outcomes, health services operations and value. Acute kidney injury (AKI) may be an ideal syndrome from which various dimensions and applications built within the context of big data may influence the structure of services delivery, care processes and outcomes for patients. The use of innovative forms of "information technology" was originally identified by the Acute Dialysis Quality Initiative (ADQI) in 2002 as a core concept in need of attention to improve the care and outcomes for patients with AKI. For this 15(th) ADQI consensus meeting held on September 6-8, 2015 in Banff, Canada, five topics focused on AKI and acute renal replacement therapy were developed where extensive applications for use of big data were recognized and/or foreseen. In this series of articles in the Canadian Journal of Kidney Health and Disease, we describe the output from these discussions.
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 | 0.063 | 0.078 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.005 | 0.008 |
| Science and technology studies | 0.006 | 0.011 |
| Scholarly communication | 0.020 | 0.011 |
| Open science | 0.006 | 0.011 |
| Research integrity | 0.014 | 0.025 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
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".