A Decision Tree-Initialised Neuro-fuzzy Approach for Clinical Decision Support

作者：

Highlights：

• A practical case study on diabetes is conducted, illustrating how the overall diagnosis may be achieved and validated in a step-by-step manner.

• A decision tree-initialised neuro-fuzzy system is proposed, which tolerates uncertainties embedded in medical entities and facilitates approximate reasoning, supporting linguistic delivery of medical expertise.

• Experimental studies on popular medical benchmarks are reported, demonstrating statistically better or comparable performance to state-of-the-art fuzzy classifiers, with compact rule bases generated involving simple antecedents.

摘要

•A practical case study on diabetes is conducted, illustrating how the overall diagnosis may be achieved and validated in a step-by-step manner.•A decision tree-initialised neuro-fuzzy system is proposed, which tolerates uncertainties embedded in medical entities and facilitates approximate reasoning, supporting linguistic delivery of medical expertise.•Experimental studies on popular medical benchmarks are reported, demonstrating statistically better or comparable performance to state-of-the-art fuzzy classifiers, with compact rule bases generated involving simple antecedents.

论文关键词：Clinical decision support,Medical diagnostic systems,Fuzzy rule-based systems

论文评审过程：Received 23 September 2019, Revised 23 August 2020, Accepted 3 November 2020, Available online 12 November 2020, Version of Record 10 December 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101986