Artificial Intelligence in AKI: Goals of an AKI!Now Workgroup
Bibliographic record
Abstract
Background: In 2019, the American Society of Nephrology established AKI!Now, a collaborative initiative to promote excellence in the prevention, diagnosis, and treatment of Acute Kidney Injury (AKI). Here, we describe the ongoing efforts of the AKI!Now workgroup focused on Artificial Intelligence (AI) to improve the quality, accessibility, affordability, and equity of AKI care. Methods: The workgroup has outlined objectives in 3 key domains: 1. Patients. Input in designing and implementing fair and equitable AI tools and identifying clinical scenarios based on personal and caregiver experience that could be improved with AI 2. Clinicians. Input in the design, value, and implementation of fair and equitable AI tools and identifying clinical uncertainties that may benefit from new AI tools 3. Researchers. Evaluation of current AI tools, with a focus on removing implicit bias; development of novel, feasible, and effective AI tools to address gaps identified by patients and clinicians; and development and implementation of AI methods along with novel sensors for more sensitive assessment of kidney function and injury to advance the science of AKI Results: This project, with involvement from a multi-disciplinary group of stakeholders, will yield efficient and effective use of AI for quality improvement in AKI care. Specific deliverables include 1) Risk-stratification and prediction tools; 2) Intelligent alert tools; 3) Decision support for bundled care compliance; 4) Decision support for implementing pragmatic clinical trials, among others. Importantly, this work will fill gaps in validating available AI tools and develop many desired AI tools that do not exist. These coordinated efforts are expected to deliver highly useful AI tools that could improve AKI care, research and reduce associated costs. Conclusions: The AKI!Now workgroup on AI is committed to improving value care in AKI and encourages engagement and collaboration with patient, provider, researcher, and industry stakeholders. We seek to improve the care provided to the growing and susceptible AKI population, along the entire lifespan.
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 | 0.109 | 0.036 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.007 | 0.008 |
| Scholarly communication | 0.018 | 0.014 |
| Open science | 0.005 | 0.029 |
| Research integrity | 0.018 | 0.024 |
| Insufficient payload (model declined to judge) | 0.006 | 0.005 |
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".