The DOI matches its Crossref record; 20 of the 21 references it cites were found in a registry or an index; 13 of the 21 sources its claims cite were checked for support.
Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care
Open accessAbstract
BACKGROUND: Acute kidney injury (AKI) in pediatric critical care patients is diagnosed using elevated serum creatinine, which occurs only after kidney impairment. There are no treatments other than supportive care for AKI once it has developed, so it is important to identify patients at risk to prevent injury. This study develops a machine learning model to learn pre-disease patterns of physiological measurements and predict pediatric AKI up to 48 h earlier than the currently established diagnostic guidelines. METHODS: EHR data from 16,863 pediatric critical care patients between 1 month to 21 years of age from three independent institutions were used to develop a single machine learning model for early prediction of creatinine-based AKI using intelligently engineered predictors, such as creatinine rate of change, to automatically assess real-time AKI risk. The primary outcome is prediction of moderate to severe AKI (Stage 2/3), and secondary outcomes are prediction of any AKI (Stage 1/2/3) and requirement of renal replacement therapy (RRT). Predictions generate alerts allowing fast assessment and reduction of AKI risk, such as: "patient has 90% risk of developing AKI in the next 48 h" along with contextual information and suggested response such as "patient on aminoglycosides, suggest check level and review dose and indication". RESULTS: The model was successful in predicting Stage 2/3 AKI prior to detection by conventional criteria with a median lead-time of 30 h at AUROC of 0.89. The model predicted 70% of subsequent RRT episodes, 58% of Stage 2/3 episodes, and 41% of any AKI episodes. The ratio of false to true alerts of any AKI episodes was approximately one-to-one (PPV 47%). Among patients predicted, 79% received potentially nephrotoxic medication after being identified by the model but before development of AKI. CONCLUSIONS: As the first multi-center validated AKI prediction model for all pediatric critical care patients, the machine learning model described in this study accurately predicts moderate to severe AKI up to 48 h in advance of AKI onset. The model may improve outcome of pediatric AKI by providing early alerting and actionable feedback, potentially preventing or reducing AKI by implementing early measures such as medication adjustment.
Overview
CoChat Summary
TL;DR
A single age-dependent ensemble machine learning model was developed on EHR data from 16,863 pediatric critical care patients across three institutions to predict creatinine-based AKI up to 48 h before conventional diagnosis. It predicted Stage 2/3 AKI with a median lead-time of 30 h and AUROC 0.89, while also forecasting any AKI and renal replacement therapy.
Key findings
- The model predicted Stage 2/3 AKI before conventional criteria with a median lead-time of 30 h; AUROC reached 0.89 within the training prediction window (48–24 h before onset) and decreased slightly to 0.85 outside it.
- It identified 70% of subsequent RRT episodes, 58% of Stage 2/3 AKI episodes, and 41% of any AKI episodes; PPV for any AKI was 47% (false-to-true alert ratio approximately 1:1), and PPV for Stage 2/3 AKI was 22% (1:4).
- Among patients predicted by the model, 79% received potentially nephrotoxic medication after being identified but before AKI development.
- The renal angina index comparator was less predictive, with AUROC around 0.57, sensitivity of 5% for any AKI and 3% for Stage 2/3 AKI, and PPV of 4% (1:21) and 1% (1:98), respectively.
Methods
- Retrospective multi-center cohort using EHR data from 16,863 pediatric critical care patients aged 1 month to 21 years from three independent institutions (PICU and CTICU); each center’s data were split into derivation (70%), validation (15%), and holdout testing (15%) sets with no patient overlap.
- A single age-dependent ensemble machine learning model used 15 final predictors plus age, selected from 250 candidate predictors; predictors were aggregated every 6 h, the model was trained on data 48–24 h before AKI onset, and tested on holdout data 48–6 h before onset. Primary outcome was Stage 2/3 AKI; secondary outcomes were any AKI and RRT requirement; the renal angina index served as baseline comparator.
- AKI was labeled using KDIGO serum creatinine criteria; urine output criteria were not used due to unreliable records. Baseline creatinine was determined by mean normal creatinine for age and gender, and the model can make predictions when some predictors are missing without data imputation.
Limitations
- Stated: the model uses creatinine alone to stage AKI due to data availability; up to 20% of AKI patients are diagnosed by urine output criteria alone, so the model may miss more urine-staged patients and reported PPV may increase if those patients were counted. Generalizability is not fully resolved, with a need for more validation on larger non-US datasets; the best way to present and integrate the model into workflow remains untested; and performance against admission reason and patient comorbidities is unknown.
- Stated: the model intentionally avoided “black-box” neural network models to preserve transparency and actionability, which may have limited performance.
- Evident from the text: validation was retrospective only, with no prospective clinical-impact study yet (the authors plan one); performance was worse on the UK hospital, likely due to its smaller data size and younger patients, and younger patients were predicted less accurately.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
9 Valid · 3 Not valid · 3 Not checked · 56 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“some studies have shown that early improvements in renal function after AKI may lead to better outcomes [1, 5, 7].”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Background
What the sources say
- Could not verifycites [1] Kaddourah A, Basu RK, Bagshaw SM, Goldstein SL. Epidemiology of acute kidney injury in critically ill children and young adults. N Engl J Med. 2017;376(1):11–20. sourceExperimental — accuracy not yet measured
The Results sections on AKI progression and risk of death report worsening AKI and an association between greater severity and mortality. They do not compare patients whose renal function improved early after AKI with those whose function did not improve. Searches for recovery, resolution, and early improvement found no passage addressing that claim; the Discussion also cautions against causal conclusions. (LLM, conf=0.76)
- Not checked — no full text of the sourcecites [5] Kellum JA, Lameire N, Aspelin P, Barsoum RS, Burdmann EA, Goldstein SL, Herzog CA, Joannidis M, Kribben A, Levey AS, MacLeod AM. Kidney disease: improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury. Kidney Int Suppl. 2012;2(1):1–138. source
- Not checked — no full text of the sourcecites [7] Levy MM, Macias WL, Vincent JL, Russell JA, Silva E, Trzaskoma B, Williams MD. Early changes in organ function predict eventual survival in severe sepsis. Crit Care Med. 2005;33(10):2194–201. source
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Up to 20% of AKI patients are diagnosed based on the urine output criteria alone [20]”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Limitations
What the sources say
- Partly supportedcites [20] Kaddourah A, Basu RK, Bagshaw SM, Goldstein SL. Epidemiology of acute kidney injury in critically ill children and young adults. N Engl J Med. 2017;376:11–20. sourceExperimental — accuracy not yet measured
The Results section (Comparison of Plasma Creatinine Level and Urine Output in Defining Acute Kidney Injury; page unavailable) supports diagnosis by urine-output criteria alone: 355 patients meeting those criteria would have been missed using plasma creatinine alone. It does not support the stated upper limit of 20%; among patients with data for both measures, those 355 represent about 32.5% of the 1,093 patients meeting either criterion. (LLM, conf=0.88)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Whilst in pediatric intensive care units (PICU) there are often no specific treatments to reverse AKI after it has developed [6]”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Background
What the sources say
- Supportedcites [6] Sutherland SM, Chawla LS, Kane-Gill SL, Hsu RK, Kramer AA, Goldstein SL, Kellum JA, Ronco C, Bagshaw SM. Utilizing electronic health records to predict acute kidney injury risk and outcomes: workgroup statements from the 15th ADQI consensus conference. Can J Kidney Health Dis. 2016;3(1):11. source
The Background states that no treatments exist to mitigate or cure AKI once it has developed, in a discussion explicitly covering both adults and children. The citing sentence’s narrower, hedged statement about pediatric intensive care units is consistent with that passage. (LLM, conf=0.92)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The baseline comparator RAI, using mainly creatinine to predict AKI [17], performed worse than the model”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Discussion > Baseline comparator
What the sources say
- Supportedcites [17] Basu RK, Zappitelli M, Brunner L, et al. Derivation and validation of the renal angina index to improve the prediction of acute kidney injury in critically ill children. Kidney Int. 2014;85(3):659–67. source
The Methods section identifies the RAI as an index for predicting AKI, and the Results ('RAI prediction of AKI—by creatinine clearance and/or fluid overload criteria') show that its creatinine-clearance component discriminated better than fluid overload alone. The statement that RAI performed worse than 'the model' is the citing authors’ comparison, not a result attributed to this source. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“This addresses the need expressed by ADQI for a predictive model to present information about patient measurements contributing to the predicted risks and provide feedback to practitioners regarding potential actionable items [6]”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Discussion > Impacting clinical workflow and improving outcomes
What the sources say
- Supportedcites [6] Sutherland SM, Chawla LS, Kane-Gill SL, Hsu RK, Kramer AA, Goldstein SL, Kellum JA, Ronco C, Bagshaw SM. Utilizing electronic health records to predict acute kidney injury risk and outcomes: workgroup statements from the 15th ADQI consensus conference. Can J Kidney Health Dis. 2016;3(1):11. source
In Results, Question 4 (page not supplied), the proposed dashboard would show which factors most significantly affect a patient's current risk score. The same section says AKI prediction tools should provide practitioners with feedback about potential actionable items. These are the two functions the citing sentence attributes to ADQI. (LLM, conf=0.92)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
39 more claims · 2 with their cited sources checked
Create a free account to see all 71 claims and every source verdict.
- It may state two separate claims as one. 15
- Probably not a substantial claim. 14
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Early health prediction plays a critical role in improving public health by enabling healthcare providers to identify and address potential health problems before they become more serious [11,12].”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Results > Baseline comparator
“In comparison, RAI was less predictive of AKI with AUROC around 0.57 in Fig. 2a and b and sensitivity and specificity shown in Table 3.”
§ Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care > Results > Performance
“| | Sensitivity Any Stage AKI (%) | Sensitivity AKI Stage 2 or 3 (%) | PPV (TP:FP) Any stage AKI | PPV (TP:FP) AKI Stage 2 or 3 |”
Citations
Cites
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Many research groups have tackled early prediction of AKI using electronic health records (EHR) data [8–11], but no model so far explains the rationale behind specific predictions despite a clear need for explainable and actionable predictions [6, 12].”
BackgroundKDIGO Clinical Practice Guidelines for Acute Kidney Injury
Khwaja, A. (2012) · Nephron Clinical Practice · doi:10.1159/000339789 · Cited by 8,014
Bellomo, R., Ronco, C., Kellum, J. A., Mehta, R. L., Palevsky, P., & workgroup, T. A. (2004) · Critical Care · doi:10.1186/cc2872 · Cited by 6,781 · cited 1×
“Baseline creatinine was determined by the mean normal creatinine level for age and gender group [14–16].”
Method(2012) · Kidney International Supplements · doi:10.1038/kisup.2012.1 · Cited by 4,326
A clinically applicable approach to continuous prediction of future acute kidney injury
Tomašev, N., Glorot, X., Rae, J. W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., et al. (2019) · Nature · doi:10.1038/s41586-019-1390-1 · Cited by 1,086
Epidemiology of Acute Kidney Injury in Critically Ill Children and Young Adults
Kaddourah, A., Basu, R. K., Bagshaw, S. M., & Goldstein, S. L. (2017) · New England Journal of Medicine · doi:10.1056/nejmoa1611391 · Cited by 1,075 · cited 1×
“Up to 20% of AKI patients are diagnosed based on the urine output criteria alone [20], and the lack of urine criteria may have resulted in lower AKI rates than previously described.”
BackgroundKDOQI US Commentary on the 2012 KDIGO Clinical Practice Guideline for Acute Kidney Injury
Palevsky, P. M., Liu, K. D., Brophy, P. D., Chawla, L. S., Parikh, C. R., Thakar, C. V., Tolwani, A. J., Waikar, S. S., & Weisbord, S. D. (2013) · American Journal of Kidney Diseases · doi:10.1053/j.ajkd.2013.02.349 · Cited by 935 · cited 1×
“Length of stay (days) 3 [1, 6] 4 [2, 8] 5 [3, 13]”
Mammen, C., Al Abbas, A., Skippen, P., Nadel, H., Levine, D., Collet, J. P., & Matsell, D. G. (2012) · American Journal of Kidney Diseases · doi:10.1053/j.ajkd.2011.10.048 · Cited by 573
Early changes in organ function predict eventual survival in severe sepsis*
Levy, M. M., Macias, W. L., Vincent, J.-L., Russell, J. A., Silva, E., Trzaskoma, B., & Williams, M. D. (2005) · Critical Care Medicine · doi:10.1097/01.ccm.0000182798.39709.84 · Cited by 358 · cited 1×
“Whilst in pediatric intensive care units (PICU) there are often no specific treatments to reverse AKI after it has developed [6], some studies have shown that early improvements in renal function after AKI may lead to better outcomes [1, 5, 7].”
BackgroundSchneider, J., Khemani, R., Grushkin, C., & Bart, R. (2010) · Critical Care Medicine · doi:10.1097/ccm.0b013e3181cd12e1 · Cited by 323 · cited 1×
“Baseline creatinine was determined by the mean normal creatinine level for age and gender group [14–16].”
Method
Research works printed but not linked: 2
- American College of Physicians. Annals of Internal Medicine. The TRIPOD Statement: Explanation and Elaboration. https://annals.org/aim/fullarticle/2088542/transparent-reporting-multivariableprediction-model-individual-prognosisdiagnosis-tripod-explanation.
- Kaddourah A, Basu RK, Bagshaw SM, Goldstein SL. Epidemiology of acute kidney injury in critically ill children and young adults. N Engl J Med. 2017;376:11–20. · DOI · Paper page
Cited by
Hu, J., Xu, J., Li, M., Jiang, Z., Mao, J., Feng, L., Miao, K., Li, H., Chen, J., Bai, Z., et al. (2024) · eClinicalMedicine · doi:10.1016/j.eclinm.2023.102409 · Cited by 213
“Although a few retrospective studies were conducted to identify AKI prediction models in hospitalized children, 14 – 16,53 these models performed less accurately than our fi nal model 14, The ML technique has been described as a “ black-box ” with little explanation about how predictions are derived.”
MethodResultBaker, S., & Xiang, W. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3256323 · Cited by 178
“Additionally, categorization of AKI severity would further improve the work presented in [212], as would identification of when cancer recurrence is most likely to occur in [216], [217].”
BackgroundMachine learning-based models for the prediction of breast cancer recurrence risk
Zuo, D., Yang, L., Jin, Y. Q., Qi, H., Liu, Y., & Li, R. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02377-z · Cited by 183
Fan, Z., Jiang, J., Chen, X., Chen, Y., Xia, Q., Wang, J., Fang, M., Wu, Z., & Chen, F. (2023) · Journal of Translational Medicine · doi:10.1186/s12967-023-04205-4 · Cited by 172
“Dong et al. [16] developed an ML model to learn predisease patterns of physiological measurements and predict pediatric AKI up to 48 h in advance compared with presently established diagnostic guidelines.”
MethodBadidi, E. (2023) · Future Internet · doi:10.3390/fi15110370 · Cited by 113
“Early health prediction plays a critical role in improving public health by enabling healthcare providers to identify and address potential health problems before they become more serious [11,12].”
Metadata
- Authors
- Dong, J., Feng, T., Thapa-Chhetry, B., Cho, B. G., Shum, T., Inwald, D. P., Newth, C. J. L., & Vaidya, V. U.
- Affiliations
- Philips (United States) (US)
- Phoenix Children's Hospital (US)
- Addenbrooke's Hospital (GB)
- University of Southern California (US)
- Corresponding author
- Dong, Junzi
- Venue
- Critical Care
- Published
- 2021-08-10
- Volume
- 25
- Issue
- 1
- Pages
- 288-288
- ISSN
- 1364-8535 (ISSN-L)
- PMC
- PMC8353807
- OpenAlex
- W3191280566
- Cited by
- 233
- References
- 21
- Citations by year
- 2026: 40 · 2025: 75 · 2024: 65 · 2023: 33 · 2022: 20
- FWCI
- 20.17
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Critical Care (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Nephrology › Acute Kidney Injury Research
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- acute kidney injury, pediatric intensive care, early prediction, machine learning, serum creatinine, renal replacement therapy, clinical decision support alerts, nephrotoxic drugs, aminoglycosides, AKI risk stratification, electronic health records
- MeSH terms
- Machine Learning, Adolescent, Child, Child, Preschool, Computer Simulation, Critical Care, Female, Humans, Infant, Infant, Newborn, Male, Pediatrics, ROC Curve, Severity of Illness Index, Intensive Care Units, Pediatric, Cohort Studies, Area Under Curve, Young Adult, Acute Kidney Injury
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. https://app.cochat.ai/papers/10.1186/s13054-021-03724-0
- The paper
- Dong, J., Feng, T., Thapa-Chhetry, B., Cho, B. G., Shum, T., Inwald, D. P., Newth, C. J. L., & Vaidya, V. U. (2021). Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. Critical Care. https://doi.org/10.1186/s13054-021-03724-0
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.