Publication Date
12-1-2023
Journal
The Journal of Thoracic and Cardiovascular Surgery
DOI
10.1016/j.jtcvs.2022.09.045
PMID
36347651
PMCID
PMC10071138
PubMedCentral® Posted Date
12-1-2024
PubMedCentral® Full Text Version
Author MSS
Published Open-Access
yes
Keywords
Humans, Creatinine, Cardiac Surgical Procedures, Acute Kidney Injury, Risk Assessment, Machine Learning, Retrospective Studies
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.
Included in
Cardiology Commons, Cardiovascular Diseases Commons, Medical Sciences Commons, Mental and Social Health Commons, Nephrology Commons, Pathological Conditions, Signs and Symptoms Commons, Surgery Commons