1
|
Ryan CT, Zeng Z, Chatterjee S, Wall MJ, Moon MR, Coselli JS, Rosengart TK, Li M, Ghanta RK. Machine learning for dynamic and early prediction of acute kidney injury after cardiac surgery. J Thorac Cardiovasc Surg 2023; 166:e551-e564. [PMID: 36347651 PMCID: PMC10071138 DOI: 10.1016/j.jtcvs.2022.09.045] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Revised: 08/29/2022] [Accepted: 09/10/2022] [Indexed: 11/05/2022]
Abstract
OBJECTIVE Acute kidney injury after cardiac surgery increases morbidity and mortality. Diagnosis relies on oliguria or increased serum creatinine, which develop 48 to 72 hours after injury. We hypothesized machine learning incorporating preoperative, operative, and intensive care unit data could dynamically predict acute kidney injury before conventional identification. METHODS Cardiac surgery patients at a tertiary hospital (2008-2019) were identified using electronic medical records in the Medical Information Mart for Intensive Care IV database. Preoperative and intraoperative parameters included demographics, Charlson Comorbidity subcategories, and operative details. Intensive care unit data included hemodynamics, medications, fluid intake/output, and laboratory results. Kidney Disease: Improving Global Outcomes creatinine criteria were used for acute kidney injury diagnosis. An ensemble machine learning model was trained for hourly predictions of future acute kidney injury within 48 hours. Performance was evaluated by area under the receiver operating characteristic curve and balanced accuracy. RESULTS Within the cohort (n = 4267), there were approximately 7 million data points. Median baseline creatinine was 1.0 g/dL (interquartile range, 0.8-1.2), with 17% (735/4267) of patients having chronic kidney disease. Postoperative stage 1 acute kidney injury occurred in 50% (2129/4267), stage 2 occurred in 8% (324/4267), and stage 3 occurred in 4% (183/4267). For hourly prediction of any acute kidney injury over the next 48 hours, area under the receiver operating characteristic curve was 0.82, and balanced accuracy was 75%. For hourly prediction of stage 2 or greater acute kidney injury over the next 48 hours, area under the receiver operating characteristic curve was 0.95 and balanced accuracy was 86%. The model predicted acute kidney injury before clinical detection in 89% of cases. CONCLUSIONS Ensemble machine learning models using electronic medical records data can dynamically predict acute kidney injury risk after cardiac surgery. Continuous postoperative risk assessment could facilitate interventions to limit or prevent renal injury.
Collapse
Affiliation(s)
- Christopher T Ryan
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex
| | - Zijian Zeng
- Department of Statistics, Rice University, Houston, Tex
| | - Subhasis Chatterjee
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Tex
| | - Matthew J Wall
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex
| | - Marc R Moon
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Tex
| | - Joseph S Coselli
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Tex
| | - Todd K Rosengart
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Tex
| | - Meng Li
- Department of Statistics, Rice University, Houston, Tex
| | - Ravi K Ghanta
- Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex.
| |
Collapse
|
2
|
Doukas P, Frese JP, Eierhoff T, Hellfritsch G, Raude B, Jacobs MJ, Greiner A, Oberhuber A, Gombert A. The NephroCheck bedside system for detecting stage 3 acute kidney injury after open thoracoabdominal aortic repair. Sci Rep 2023; 13:11096. [PMID: 37423933 DOI: 10.1038/s41598-023-38242-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Accepted: 07/05/2023] [Indexed: 07/11/2023] Open
Abstract
Acute kidney injury (AKI) is a common complication after complex aortic procedures and it is associated with relevant mortality and morbidity. Biomarkers for early and specific AKI detection are lacking. The aim of this work is to investigate the reliability of the NephroCheck bedside system for diagnosing stage 3 AKI following open aortic surgery. In this prospective, multicenter, observational study,- https://clinicaltrials.gov/ct2/show/NCT04087161 -we included 45 patients undergoing open thoracoabdominal aortic repair. AKI risk (AKIRisk-Index) was calculated from urine samples at 5 timepoints: baseline, immediately postoperatively and at 12, 24, 48, and 72 h post-surgery. AKIs were classified according to the KDIGO criteria. Contributing factors were identified in univariable and multivariable logistic regression. Predictive ability was assessed with the area under the receiver operator curve (ROCAUC). Among 31 patients (68.8%) that developed AKIs, 21 (44.9%) developed stage-3 AKIs, which required dialysis. AKIs were correlated with increased in-hospital mortality (p = .006), respiratory complications (p < .001), sepsis (p < .001), and multi-organ dysfunction syndrome (p < .001). The AKIRisk-Index showed reliable diagnostic accuracy starting at 24 h post-surgery (ROCAUC: .8056, p = .001). In conclusion, starting at 24 h after open aortic repair, the NephroCheck system showed adequate diagnostic accuracy for detecting the patients at risk for stage 3 AKIs.
Collapse
Affiliation(s)
- Panagiotis Doukas
- Department of Vascular and Endovascular Surgery, University Hospital Aachen, RWTH Aachen University, Pauwelsstrasse 30, 52074, Aachen, Germany.
| | - Jan Paul Frese
- Department of Vascular Surgery, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Thorsten Eierhoff
- Department of Vascular and Endovascular Surgery, University Hospital Muenster, Münster, Germany
| | - Gabriel Hellfritsch
- Department of Vascular and Endovascular Surgery, University Hospital Aachen, RWTH Aachen University, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Ben Raude
- Department of Vascular Surgery, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Michael J Jacobs
- Department of Vascular and Endovascular Surgery, University Hospital Aachen, RWTH Aachen University, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Andreas Greiner
- Department of Vascular Surgery, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Alexander Oberhuber
- Department of Vascular and Endovascular Surgery, University Hospital Muenster, Münster, Germany
| | - Alexander Gombert
- Department of Vascular and Endovascular Surgery, University Hospital Aachen, RWTH Aachen University, Pauwelsstrasse 30, 52074, Aachen, Germany
| |
Collapse
|
3
|
Takkavatakarn K, Hofer IS. Artificial Intelligence and Machine Learning in Perioperative Acute Kidney Injury. ADVANCES IN KIDNEY DISEASE AND HEALTH 2023; 30:53-60. [PMID: 36723283 DOI: 10.1053/j.akdh.2022.10.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Revised: 09/30/2022] [Accepted: 10/28/2022] [Indexed: 12/24/2022]
Abstract
Acute kidney injury (AKI) is a common complication after a surgery, especially in cardiac and aortic procedures, and has a significant impact on morbidity and mortality. Early identification of high-risk patients and providing effective prevention and therapeutic approach are the main strategies for reducing the possibility of perioperative AKI. Consequently, several risk-prediction models and risk assessment scores have been developed for the prediction of perioperative AKI. However, a majority of these risk scores are only derived from preoperative data while the intraoperative time-series monitoring data such as heart rate and blood pressure were not included. Moreover, the complexity of the pathophysiology of AKI, as well as its nonlinear and heterogeneous nature, imposes limitations on the use of linear statistical techniques. The development of clinical medicine's digitization, the widespread availability of electronic medical records, and the increase in the use of continuous monitoring have generated vast quantities of data. Machine learning has recently shown promise as a method for automatically integrating large amounts of data in predicting the risk of perioperative outcomes. In this article, we discussed the development, limitations of existing work, and the potential future direction of models using machine learning techniques to predict AKI after a surgery.
Collapse
Affiliation(s)
- Kullaya Takkavatakarn
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY; Division of Nephrology, Department of Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Ira S Hofer
- Department of Anesthesiology, Pain and Perioperative Medicine, Icahn School of Medicine at Mount, Sinai, NY.
| |
Collapse
|
4
|
Abstract
Postoperative AKI is a common complication of major surgery and is associated with significant morbidity and mortality. The Kidney Disease Improving Global Outcomes AKI definition allows consensus classification and identification of postoperative AKI through changes in serum creatinine and/or urine output. However, such conventional diagnostic criteria may be inaccurate in the postoperative period, suggesting a potential to refine diagnosis by application of novel diagnostic biomarkers. Risk factors for the development of postoperative AKI can be thought of in terms of preoperative, intraoperative, and postoperative factors and, as such, represent areas that may be targeted perioperatively to minimize the risk of AKI. The treatment of postoperative AKI remains predominantly supportive, although application of management bundles may translate into improved outcomes.
Collapse
Affiliation(s)
- Naomi Boyer
- Department of Critical Care, Royal Surrey Hospital, Guildford, United Kingdom
- SPACeR Group (Surrey Peri-Operative, Anaesthesia and Critical Care Collaborative Research Group), Royal Surrey Hospital, Guildford, United Kingdom
| | - Jack Eldridge
- William Harvey Research Institute, Queen Mary University of London, London, United Kingdom
- Adult Critical Care Unit, Royal London Hospital Barts Health National Health Service Trust, London, United Kingdom
| | - John R. Prowle
- William Harvey Research Institute, Queen Mary University of London, London, United Kingdom
- Adult Critical Care Unit, Royal London Hospital Barts Health National Health Service Trust, London, United Kingdom
| | - Lui G. Forni
- Department of Critical Care, Royal Surrey Hospital, Guildford, United Kingdom
- SPACeR Group (Surrey Peri-Operative, Anaesthesia and Critical Care Collaborative Research Group), Royal Surrey Hospital, Guildford, United Kingdom
- Department of Clinical and Experimental Medicine, Faculty of Health Sciences, University of Surrey, Guildford, United Kingdom
| |
Collapse
|
5
|
Naorungroj T, Yanase F, Bittar I, Eastwood G, Bellomo R. The Relationship between Nephrocheck® Test Values, Outcomes, and Urinary Output in Critically Ill Patients at Risk of Acute Kidney Injury. Acta Anaesthesiol Scand 2022; 66:1219-1227. [DOI: 10.1111/aas.14133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2022] [Revised: 07/31/2022] [Accepted: 08/08/2022] [Indexed: 11/27/2022]
Affiliation(s)
- Thummaporn Naorungroj
- Department of Intensive Care Austin Hospital Melbourne Australia
- Department of Intensive Care, Faculty of Medicine Siriraj Hospital Mahidol University Bangkok Thailand
| | - Fumitaka Yanase
- Department of Intensive Care Austin Hospital Melbourne Australia
- ANZICS–Research Centre, Melbourne, Australia, Monash University School and Public Health and Preventive Medicine, Monash University
| | | | - Glenn Eastwood
- Department of Intensive Care Austin Hospital Melbourne Australia
| | - Rinaldo Bellomo
- Department of Intensive Care Austin Hospital Melbourne Australia
- ANZICS–Research Centre, Melbourne, Australia, Monash University School and Public Health and Preventive Medicine, Monash University
- Department of Critical Care University of Melbourne Melbourne Australia
- Data Analytics Research and Evaluation (DARE) Centre, Austin Hospital Melbourne Australia
- Department of Intensive Care Royal Melbourne Hospital Melbourne Australia
| |
Collapse
|