From: Big Data in cardiac surgery: real world and perspectives
Author | Title | Year | AI Model | Conclusions |
---|---|---|---|---|
Diller et al. [66] | Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: Data from a single tertiary centre including 10 019 patients. | 2019 | Deep Learning | Prognostication and therapeutic guidance in patients with adult congenital heart disease (ACHD) or pulmonary hypertension |
Diller et al. [67] | Utility of machine learning algorithms in assessing patients with a systemic right ventricle. | 2018 | Deep Learning. Convolutional neural networks | Recognizing transposition of the great arteries (TGA) after atrial switch procedure or congenitally corrected TGA (ccTGA) based on routine transthoracic echocardiograms. Delineation and segmentation of the systemic ventricle |
Olive et al. [68] | Current monitoring and innovative predictive modeling to improve care in the pediatric cardiac intensive care unit. | 2018 | AI and machine learning | Predictive models created by AI and ML may lead to earlier detection of patients at risk for clinical decompensation, improving care for critically ill pediatric cardiac patients. |
Ruiz-Fernández et al. [69] | Aid decision algorithms to estimate the risk in congenital heart surgery. | 2017 | Multilayer perceptron, self-organizing map, radial basis function networks and decision trees | Feasibility of development of CDSSs using AI algorithms. Such system would help to forecast the level of risk related to a congenital heart disease surgery. |
Zhong et al. [70] | Machine learning prediction models for prognosis of critically ill patients after open-heart surgery | 2021 | Extreme gradient boosting, random forest, artificial neural network, and logistic regression | Model to predict 30-days mortality and complications (i.e.: septic shock, thrombocytopenia and liver disfunction) after open-heart surgery. |
Meyer et al. [71] | Machine learning for real-time prediction of complications in critical care: A retrospective study | 2018 | deep learning methods (recurrent neural networks) | Predict severe complications (i.e.: mortality, renal failure with a need for renal replacement therapy, and postoperative bleeding leading to operative revision) during critical care in real time after cardiothoracic surgery. |
Lei et al. [72] | Using Machine Learning to Predict Acute Kidney Injury After Aortic Arch Surgery | 2020 | Machine Learning: logistic regression model, support vector machine, random forest, and gradient boosting | Machine learning methods were found to predict AKI after aortic arch surgery significantly better than traditional logistic regression. |
Tseng et al. [73] | Prediction of the development of acute kidney injury following cardiac surgery by machine learning | 2020 | Logistic regression, support vector machine (SVM), random forest (RF), extreme gradient boosting (XGboost), and ensemble (RF + XGboost) | AI methods predict cardiac surgery-associated acute kidney injury, which determines risks following cardiac surgery, enabling the optimization of postoperative treatment strategies. |
Lee et al. [74] | Derivation and Validation of Machine Learning Approaches to Predict Acute Kidney Injury after Cardiac Surgery | 2018 | ML: decision tree, random forest, extreme gradient boosting, support vector machine, neural network classifier, and deep learning. | Using AI an Internet-based risk estimator was developed to estimate the risk of AKI at the end of surgery. |
Kilic et al. [75] | Performance of a machine learning algorithm in predicting outcomes of aortic valve replacement. | 2020 | Extreme gradient boosting (XGBoost) | Predicting outcomes of surgical aortic valve replacement. |
Wojnarski et al. [76] | Machine-learning phenotypic classification of bicuspid aortopathy | 2018 | Random forest analysis | Three distinct phenotypes of bicuspid valve-associated aortopathy were identified using machine-learning methodology. |
Baskaran et al. [77] | Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study | 2020 | ML: extreme gradient boosting (XGBoost) | For obstructive CAD, the ML model outperformed CAD consortium clinical score (CAD2). BMI is an important variable, although currently not included in most scores. In this ML model, imaging variables were most associated with revascularization |
Cikes et al. [78] | Machine learning-based pheno-grouping in heart failure to identify responders to cardiac resynchronization therapy | 2018 | Unsupervised multiple kernel learning algorithm (MKL) | Integrating clinical parameters and full heart cycle imaging data, unsupervised ML can provide a clinically meaningful classification of a phenotypically heterogeneous HF cohort and might aid in optimizing specific therapies. |
Ambale-Venkatesh et al. [79] | Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis | 2017 | Random survival forest (RF)Â alone or in combination with other statistical approaches. | Machine learning in conjunction with deep phenotyping improves prediction accuracy in cardiovascular event prediction in an initially asymptomatic population. |
Ayers et al. [80] | Using machine learning to improve survival prediction after heart transplantation | 2021 | Deep neural network, logistic regression, AdaBoost, and random forest | ML techniques can improve risk prediction in OHT compared to traditional approaches. This may have important implications in patient selection, programmatic evaluation, allocation policy, and patient counseling and prognostication. |