ArticleJournal of the American Medical Informatics Association : JAMIA2017
Calibration drift in regression and machine learning models for acute kidney injury.
Article in Journal of the American Medical Informatics Association : JAMIA, 2017. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 151 papers, 6 of them syntheses that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
151 citing papers in PubMed, 6 syntheses or guidelines pooled it.
- Discrimination and calibration performances of non-laboratory-based and laboratory-based cardiovascular risk predictions: a systematic review.Open heart · 2025Pooled it
- Recommendations for prediction models in clinical practice guidelines for cardiovascular diseases are over-optimistic: a global survey utilizing a systematic literature search.Frontiers in cardiovascular medicine · 2024Pooled it
- Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review.JAMA network open · 2022Pooled it
- Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine.Applied clinical informatics · 2021Pooled it
- Developing more generalizable prediction models from pooled studies and large clustered data sets.Statistics in medicine · 2021Pooled it
- Use of machine learning to analyse routinely collected intensive care unit data: a systematic review.Critical care (London, England) · 2019Pooled it
- Predicting acute kidney injury at hospital re-entry using high-dimensional electronic health record data.PloS one · 2018Trial
- Inhibitory receptor profiles for joint prediction of benefit and toxicity in immune checkpoint blockade.iScience · 2026Review
- Early prediction of anastomotic leakage within 24 h after minimally invasive colorectal cancer surgery using postoperative inflammatory markers: development and temporal validation of a machine learning model.Surgical endoscopy · 2026Article
- Beyond Regulatory Approval: Lifecycle Assurance for Clinical Artificial Intelligence.Journal of medical systems · 2026Article
- Temporal Heterogeneity of Factors Associated with Intra-ICU Mortality: A Formal Interaction Analysis of the Multi-Centre Silesian ICU Registry (2010-2020).Journal of clinical medicine · 2026Article
- Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation.IEEE transactions on bio-medical engineering · 2026Review
- Explainability in context: calibrating appropriate trust and reliance in artificial intelligence.Journal of the American Medical Informatics Association : JAMIA · 2026Article
- Predicting Outcomes of Traumatic Brain Injury Using Machine Learning Models Among Patients at Kilimanjaro Christian Medical Centre, Tanzania: A Registry-Based Cohort Study.Health science reports · 2026Article
- A robust clinical-laboratory AI model for predicting cumulative live birth per oocyte retrieval as a benchmark for evaluating emerging embryo selection technologies.JBRA assisted reproduction · 2026Article
- Toward universal representations of the living: Physiological invariance for transportable medical AI.PLOS digital health · 2026Review
- Validation is not enough: Longitudinal evidence of post-deployment fragility in clinical AI systems.PLOS digital health · 2026Article
- FIRST-ICU: forecasting interventions and risk stratification in the ICU using graph neural network autoencoders.NPJ digital medicine · 2026Article
- Co-Lifecycle Governance for Learning Medical AI: A Hybrid Convergence Framework for Adaptive Regulatory Oversight.Journal of medical Internet research · 2026Article
- Interpretable machine learning for predicting in-hospital mortality in COPD ICU patients: a rigorous validation across time and geography.Respiratory research · 2026Article
91 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
objectivePredictive analytics create opportunities to incorporate personalized risk estimates into clinical decision support. Models must be well calibrated to support decision-making, yet calibration deteriorates over time. This study explored the influence of modeling methods on performance drift and connected observed drift with data shifts in the patient population. MATERIALS AND
methodsUsing 2003 admissions to Department of Veterans Affairs hospitals nationwide, we developed 7 parallel models for hospital-acquired acute kidney injury using common regression and machine learning methods, validating each over 9 subsequent years.
resultsDiscrimination was maintained for all models. Calibration declined as all models increasingly overpredicted risk. However, the random forest and neural network models maintained calibration across ranges of probability, capturing more admissions than did the regression models. The magnitude of overprediction increased over time for the regression models while remaining stable and small for the machine learning models. Changes in the rate of acute kidney injury were strongly linked to increasing overprediction, while changes in predictor-outcome associations corresponded with diverging patterns of calibration drift across methods.
conclusionsEfficient and effective updating protocols will be essential for maintaining accuracy of, user confidence in, and safety of personalized risk predictions to support decision-making. Model updating protocols should be tailored to account for variations in calibration drift across methods and respond to periods of rapid performance drift rather than be limited to regularly scheduled annual or biannual intervals.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.