Machine Learning for the Prediction of Complications in Patients After Mitral Valve Surgery

Abstract

Background: This study intended to use a machine learning model to identify critical preoperative and intraoperative variables and predict the risk of several severe complications (myocardial infarction, stroke, renal failure, and hospital mortality) after cardiac valvular surgery.Study Design and Methods: A total of 1,488 patients undergoing cardiac valvular surgery in eight large tertiary hospitals in China were examined. Fifty-four perioperative variables, such as essential demographic characteristics, concomitant disease, preoperative laboratory indicators, operation type, and intraoperative information, were collected. Machine learning models were developed and validated by 10-fold cross-validation. In each fold, Recursive Feature Elimination was used to select key variables. Ten machine learning models and logistic regression were developed. The area under the receiver operating characteristic (AUROC), accuracy (ACC), Youden index, sensitivity, specificity, F1-score, positive predictive value (PPV), and negative predictive value (NPV) were used to compare the prediction performance of different models. The SHapley Additive ex Planations package was applied to interpret the best machine learning model. Finally, a model was trained on the whole dataset with the merged key variables, and a web tool was created for clinicians to use.Results: In this study, 14 vital variables, namely, intraoperative total input, intraoperative blood loss, intraoperative colloid bolus, Classification of New York Heart Association (NYHA) heart function, preoperative hemoglobin (Hb), preoperative platelet (PLT), age, preoperative fibrinogen (FIB), intraoperative minimum red blood cell volume (Hct), body mass index (BMI), creatinine, preoperative Hct, intraoperative minimum Hb, and intraoperative autologous blood, were finally selected. The eXtreme Gradient Boosting algorithms (XGBOOST) algorithm model presented a significantly better predictive performance (AUROC: 0.90) than the other models (ACC: 81%, Youden index: 70%, sensitivity: 89%, specificity: 81%, F1-score:0.26, PPV: 15%, and NPV: 99%).Conclusion: A model for predicting several severe complications after cardiac valvular surgery was successfully developed using a machine learning algorithm based on 14 perioperative variables, which could guide clinical physicians to take appropriate preventive measures and diminish the complications for patients at high risk.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

“…Development of postoperative complications: Most studies focused on the prediction of postoperative acute complications 26–28,42,44–49,59,99,110,112,113,118,123 such as pain and opioid use, 53–57 postoperative atrial fibrillation (new-onset atrial fibrillation), 82 postoperative risk of stroke or myocardial infarction, 50,71,77 and delirium or cognitive decline. 65–70 Other models focused on the risk of developing pneumonia or respiratory failure, 83,85,125 acute kidney injury, 43,52,58,60–63,120–122 liver failure 117 or development of sepsis or surgical site infection.…”

A Surgeon’s Guide to Artificial Intelligence-Driven Predictive Models

“…23 The GBM algorithm demonstrated high predictive performance and low computational costs in various disciplines, including cardiac surgery and breast reconstruction. 7,24…”

Development of a machine learning-based prediction model for systemic inflammatory response syndrome after percutaneous nephrolithotomy and comparison with nomogram model

“…Machine learning algorithms have increasingly been used to aid diagnosis, treatment, and automatic classi cation in medicine as statistical theory and computer technology have developed [7]. We must develop an e cient prediction model to identify patients with potential risk factors for post-PCNL SIRS and closely monitor their vital signs after surgery, which can signi cantly reduce the burden of false alarms.…”