1
|
Low S, Vathsala A, Murali TM, Pang L, MacLaren G, Ng WY, Haroon S, Mukhopadhyay A, Lim SL, Tan BH, Lau T, Chua HR. Electronic health records accurately predict renal replacement therapy in acute kidney injury. BMC Nephrol 2019; 20:32. [PMID: 30704418 PMCID: PMC6357378 DOI: 10.1186/s12882-019-1206-4] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2018] [Accepted: 01/07/2019] [Indexed: 11/19/2022] Open
Abstract
Background Electronic health records (EHR) detect the onset of acute kidney injury (AKI) in hospitalized patients, and may identify those at highest risk of mortality and renal replacement therapy (RRT), for earlier targeted intervention. Methods Prospective observational study to derive prediction models for hospital mortality and RRT, in inpatients aged ≥18 years with AKI detected by EHR over 1 year in a tertiary institution, fulfilling modified KDIGO criterion based on serial serum creatinine (sCr) measures. Results We studied 3333 patients with AKI, of 77,873 unique patient admissions, giving an AKI incidence of 4%. KDIGO AKI stages at detection were 1(74%), 2(15%), 3(10%); corresponding peak AKI staging in hospital were 61, 20, 19%. 392 patients (12%) died, and 174 (5%) received RRT. Multivariate logistic regression identified AKI onset in ICU, haematological malignancy, higher delta sCr (sCr rise from AKI detection till peak), higher serum potassium and baseline eGFR, as independent predictors of both mortality and RRT. Additionally, older age, higher serum urea, pneumonia and intraabdominal infections, acute cardiac diseases, solid organ malignancy, cerebrovascular disease, current need for RRT and admission under a medical specialty predicted mortality. The AUROC for RRT prediction was 0.94, averaging 0.93 after 10-fold cross-validation. Corresponding AUROC for mortality prediction was 0.9 and 0.9 after validation. Decision tree analysis for RRT prediction achieved a balanced accuracy of 70.4%, and identified delta-sCr ≥ 148 μmol/L as the key factor that predicted RRT. Conclusion Case fatality was high with significant renal deterioration following hospital-wide AKI. EHR clinical model was highly accurate for both RRT prediction and for mortality; allowing excellent risk-stratification with potential for real-time deployment. Electronic supplementary material The online version of this article (10.1186/s12882-019-1206-4) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Sanmay Low
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Renal Unit, Department of Medicine, Ng Teng Fong General Hospital, Singapore, Singapore
| | - Anantharaman Vathsala
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Tanusya Murali Murali
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Long Pang
- Biostatistics, Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore
| | - Graeme MacLaren
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.,National University Heart Centre, National University Hospital, Singapore, Singapore
| | - Wan-Ying Ng
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Sabrina Haroon
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Amartya Mukhopadhyay
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.,Division of Respiratory and Critical Care Medicine, University Medicine Cluster, National University Hospital, Singapore, Singapore
| | - Shir-Lynn Lim
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.,National University Heart Centre, National University Hospital, Singapore, Singapore
| | - Bee-Hong Tan
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.,Department of Anaesthesia, National University Hospital, Singapore, Singapore
| | - Titus Lau
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Horng-Ruey Chua
- Division of Nephrology, University Medicine Cluster, National University Hospital, Level 10 Medicine Office, NUHS Tower Block, 1E Kent Ridge Road, Singapore, 119228, Singapore. .,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
| |
Collapse
|
2
|
Klein SJ, Brandtner AK, Lehner GF, Ulmer H, Bagshaw SM, Wiedermann CJ, Joannidis M. Biomarkers for prediction of renal replacement therapy in acute kidney injury: a systematic review and meta-analysis. Intensive Care Med 2018. [PMID: 29541790 PMCID: PMC5861176 DOI: 10.1007/s00134-018-5126-8] [Citation(s) in RCA: 113] [Impact Index Per Article: 18.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
Purpose Acute kidney injury (AKI) frequently occurs in critically ill patients and often precipitates use of renal replacement therapy (RRT). However, the ideal circumstances for whether and when to start RRT remain unclear. We performed evidence synthesis of the available literature to evaluate the value of biomarkers to predict receipt of RRT for AKI. Methods We conducted a PRISMA-guided systematic review and meta-analysis including all trials evaluating biomarker performance for prediction of RRT in AKI. A systematic search was applied in MEDLINE, Embase, and CENTRAL databases from inception to September 2017. All studies reporting an area under the curve (AUC) for a biomarker to predict initiation of RRT were included. Results Sixty-three studies comprising 15,928 critically ill patients (median per study 122.5 [31–1439]) met eligibility. Forty-one studies evaluating 13 different biomarkers were included. Of these biomarkers, neutrophil gelatinase-associated lipocalin (NGAL) had the largest body of evidence. The pooled AUCs for urine and blood NGAL were 0.720 (95% CI 0.638–0.803) and 0.755 (0.706–0.803), respectively. Blood creatinine and cystatin C had pooled AUCs of 0.764 (0.732–0.796) and 0.768 (0.729–0.807), respectively. For urine biomarkers, interleukin-18, cystatin C, and the product of tissue inhibitor of metalloproteinase-2 and insulin growth factor binding protein-7 showed pooled AUCs of 0.668 (0.606–0.729), 0.722 (0.575–0.868), and 0.857 (0.789–0.925), respectively. Conclusion Though several biomarkers showed promise and reasonable prediction of RRT use for critically ill patients with AKI, the strength of evidence currently precludes their routine use to guide decision-making on when to initiate RRT. Electronic supplementary material The online version of this article (10.1007/s00134-018-5126-8) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Sebastian J Klein
- Division of Intensive Care and Emergency Medicine, Department of Internal Medicine, Medical University Innsbruck, Anichstrasse 35, 6020, Innsbruck, Austria
| | - Anna K Brandtner
- Division of Intensive Care and Emergency Medicine, Department of Internal Medicine, Medical University Innsbruck, Anichstrasse 35, 6020, Innsbruck, Austria
| | - Georg F Lehner
- Division of Intensive Care and Emergency Medicine, Department of Internal Medicine, Medical University Innsbruck, Anichstrasse 35, 6020, Innsbruck, Austria
| | - Hanno Ulmer
- Department of Medical Statistics, Informatics and Health Economics, Medical University Innsbruck, Innsbruck, Austria
| | - Sean M Bagshaw
- Department of Critical Care Medicine, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, Canada
| | | | - Michael Joannidis
- Division of Intensive Care and Emergency Medicine, Department of Internal Medicine, Medical University Innsbruck, Anichstrasse 35, 6020, Innsbruck, Austria.
| |
Collapse
|