Abstract
Objective
To develop and validate a prediction model of acute kidney injury (AKI) of any severity
that could be used for AKI surveillance and management to improve clinical outcomes.
Patients and Methods
This retrospective cohort study was conducted in medical, surgical, and mixed intensive
care units (ICUs) at Mayo Clinic in Rochester, Minnesota, including adult (≥18 years
of age) ICU-unique patients admitted between October 1, 2004, and April 30, 2011.
Our primary objective was prediction of AKI using extant clinical data following ICU
admission. We used random forest classification to provide continuous AKI risk score.
Results
We included 4572 and 1958 patients in the training and validation mutually exclusive
cohorts, respectively. Acute kidney injury occurred in 1355 patients (30%) in the
training cohort and 580 (30%) in the validation cohort. We incorporated known AKI
risk factors and routinely measured vital characteristics and laboratory results.
The model was run throughout ICU admission every 15 minutes and achieved an area under
the receiver operating characteristic curve of 0.88 on validation. It was 92% sensitive
and 68% specific and detected 30% of AKI cases at least 6 hours before the criterion
standard time (AKI stages 1-3). For discrimination of AKI stages 2 to 3, the model
had 91% sensitivity, 71% specificity, and 53% detection of AKI cases at least 6 hours
before AKI onset.
Conclusion
We developed and validated an AKI prediction model using random forest for continuous
monitoring of ICU patients. This model could be used to identify high-risk patients
for preventive measures or identifying patients of prospective interventional trials.
Abbreviations and Acronyms:
AKI (acute kidney injury), AKIN (Acute Kidney Injury Network), AUC (area under the curve), GFR (glomerular filtration rate), ICU (intensive care unit), ROC (receiver operating characteristic)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Mayo Clinic ProceedingsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Prevention of cardiac surgery-associated AKI by implementing the KDIGO guidelines in high risk patients identified by biomarkers: the PrevAKI randomized controlled trial.Intensive Care Med. 2017; 43 ([published correction appears in Intensive Care Med. 2017;43(11):1749]): 1551-1561
- Biomarker-guided intervention to prevent acute kidney injury after major surgery: the Prospective Randomized BigpAK Study.Ann Surg. 2018; 267: 1013-1020
- Development of a multicenter ward-based AKI prediction model.Clin J Am Soc Nephrol. 2016; 11: 1935-1943
- Acute kidney injury, mortality, length of stay, and costs in hospitalized patients.J Am Soc Nephrol. 2005; 16: 3365-3370
- Epidemiology of acute kidney injury in critically ill patients: the multinational AKI-EPI study.Intensive Care Med. 2015; 41: 1411-1423
- Epidemiology of acute kidney injury in the intensive care unit.Crit Care Res Pract. 2013; 2013: 479730
- No increase in the incidence of acute kidney injury in a population-based annual temporal trends epidemiology study.Kidney Int. 2017; 92: 721-728
- Early nephrology consultation can have an impact on outcome of acute kidney injury patients.Nephrol Dial Transplant. 2011; 26: 3202-3206
- Nephrology consultation in acute renal failure: does timing matter?.Am J Med. 2002; 113: 456-461
- Evaluation and initial management of acute kidney injury.Clin J Am Soc Nephrol. 2008; 3: 962-967
- Nephrology referral and outcomes in critically ill acute kidney injury patients.PLoS One. 2013; 8: e70482
- Sequential evaluation of prognostic models in the early diagnosis of acute kidney injury in the intensive care unit.Kidney Int. 2009; 75: 982-986
- Section 2: AKI Definition.Kidney Int Suppl (2011). 2012; 2: 19-36
- The growth of acute kidney injury: a rising tide or just closer attention to detail?.Kidney Int. 2015; 87: 46-61
- Urinary and serum biomarkers for the diagnosis of acute kidney injury: an in-depth review of the literature.Nephrol Dial Transplant. 2013; 28: 254-273
- 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: 11
- International Society of Nephrology's 0by25 initiative for acute kidney injury (zero preventable deaths by 2025): a human rights case for nephrology.Lancet. 2015; 385: 2616-2643
- Recognition and management of acute kidney injury in the International Society of Nephrology 0by25 Global Snapshot: a multinational cross-sectional study.Lancet. 2016; 387 ([published correction appears in Lancet. 2016;387(10032):1998]): 2017-2025
- A clinical score to predict acute renal failure after cardiac surgery.J Am Soc Nephrol. 2005; 16: 162-168
- Clinical risk scoring models for prediction of acute kidney injury after living donor liver transplantation: a retrospective observational study.PLoS One. 2015; 10: e0136230
- A new model to predict acute kidney injury requiring renal replacement therapy after cardiac surgery.CMAJ. 2016; 188: 1076-1083
- A simple risk score for prediction of contrast-induced nephropathy after percutaneous coronary intervention: development and initial validation.J Am Coll Cardiol. 2004; 44: 1393-1399
- A risk prediction score for acute kidney injury in the intensive care unit.Nephrol Dial Transplant. 2017; 32: 814-822
- Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury.Crit Care. 2007; 11: R31
- Development and validation of electronic surveillance tool for acute kidney injury: a retrospective analysis.J Crit Care. 2015; 30: 988-993
- Informatics infrastructure for syndrome surveillance, decision support, reporting, and modeling of critical illness.Mayo Clin Proc. 2010; 85: 247-254
- Acute kidney injury electronic alert for nephrologist: reactive versus proactive?.Blood Purif. 2016; 42: 323-328
- Variation in risk and mortality of acute kidney injury in critically ill patients: a multicenter study.Am J Nephrol. 2015; 41: 81-88
- Sniffing out acute kidney injury in the ICU: do we have the tools?.Curr Opin Crit Care. 2013; 19: 531-536
- Technological distractions (part 2): a summary of approaches to manage clinical alarms with intent to reduce alarm fatigue.Crit Care Med. 2018; 46: 130-137
- Development and validation of an acute kidney injury risk index for patients undergoing general surgery: results from a national data set.Anesthesiology. 2009; 110: 505-515
- AKIpredictor, an online prognostic calculator for acute kidney injury in adult critically ill patients: development, validation and comparison to serum neutrophil gelatinase-associated lipocalin.Intensive Care Med. 2017; 43: 764-773
- Identifying the patient at risk of acute kidney injury: a predictive scoring system for the development of acute kidney injury in acute medical patients.Nephron Clin Pract. 2013; 123: 143-150
- Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis.2nd ed. Springer International Publishing, New York, NY2015
- Generalizability of epidemiological findings and public health decisions: an illustration from the Rochester Epidemiology Project.Mayo Clin Proc. 2012; 87: 151-160
- The development of a machine learning inpatient acute kidney injury prediction model.Crit Care Med. 2018; 46: 1070-1077
Article Info
Footnotes
For editorial comment, see page 748
Potential Competing Interests: This work was performed in all intensive care units at Mayo Clinic in Rochester, Minnesota, in collaboration with Philips Research North America, Cambridge, Massachusetts. Drs Ghosh and Eshelman are employed by Philips Research North America and Drs Chiofolo and Chbat were formerly employed by Philips Research North America, and this work was done as a part of their duties. Drs Chiofolo and Chbat are currently with Quadrus Medical Technologies, New York, New York. Dr Chiofolo completed most of the work while at Philips Research North America, and Dr Chbat completed part of the work while at Philips Research North America. Dr Kashani reports no competing interests.
Identification
Copyright
© 2019 Mayo Foundation for Medical Education and Research
