Decision support system to improve postoperative discharge: A novel multi-class classification approach
作者：
Highlights：
• We developed a novel hybrid algorithm for improving postoperative discharge decision making.
• We compared the performance of the hybrid algorithm against state-of-the-art classifiers.
• We also compared the performance of the hybrid algorithm against models from published studies.
• Optimisation of kernel and hyperparameters can improve the overall classification performance.
• Genetic Algorithm led to a higher control over the decision boundary in the hybrid model.
摘要
•We developed a novel hybrid algorithm for improving postoperative discharge decision making.•We compared the performance of the hybrid algorithm against state-of-the-art classifiers.•We also compared the performance of the hybrid algorithm against models from published studies.•Optimisation of kernel and hyperparameters can improve the overall classification performance.•Genetic Algorithm led to a higher control over the decision boundary in the hybrid model.
论文关键词：Machine learning,Decision support,Postoperative discharge,Genetic algorithm,Support vector machine,Multi-layer perceptron
论文评审过程：Received 26 January 2018, Revised 26 March 2018, Accepted 27 March 2018, Available online 28 March 2018, Version of Record 12 May 2018.
论文官网地址：https://doi.org/10.1016/j.knosys.2018.03.033
