Interpretable and accurate medical data classification – a multi-objective genetic-fuzzy optimization approach
作者：
Highlights：
• Novel fuzzy rule-based system (FRBS) for medical data classification tasks is proposed.
• FRBSs are designed using multi-objective evolutionary optimization algorithms.
• Set of FRBSs with various levels of accuracy-interpretability trade-off is generated.
• Benchmark medical data sets are used to evaluate the effectiveness of the system.
• Highly interpretable and accurate medical decision support is provided by our approach.
摘要
•Novel fuzzy rule-based system (FRBS) for medical data classification tasks is proposed.•FRBSs are designed using multi-objective evolutionary optimization algorithms.•Set of FRBSs with various levels of accuracy-interpretability trade-off is generated.•Benchmark medical data sets are used to evaluate the effectiveness of the system.•Highly interpretable and accurate medical decision support is provided by our approach.
论文关键词：Accuracy and interpretability of medical classification systems,Medical decision support,Multi-objective evolutionary optimization,Fuzzy rule-based systems,Genetic computations
论文评审过程：Received 12 February 2015, Revised 15 October 2016, Accepted 14 November 2016, Available online 19 November 2016, Version of Record 26 November 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.11.017
