It has been often demonstrated that clinicians exhibit both inter-expert and intra-expert variability when making difficult decisions. In contrast, the vast majority of computerized models that aim to provide automated support for such decisions do not explicitly recognize or replicate this variability. Furthermore, the perfect consistency of computerized models is often presented as a de facto benefit. In this paper, we describe a novel approach to incorporate variability within a fuzzy inference system using non-stationary fuzzy sets in order to replicate human variability. We apply our approach to a decision problem concerning the recommendation of post-operative breast cancer treatment; specifically, whether or not to administer chemotherapy based on assessment of five clinical variables: NPI (the Nottingham Prognostic Index), estrogen receptor status, vascular invasion, age and lymph node status. In doing so, we explore whether such explicit modeling of variability provides any performance advantage over a more conventional fuzzy approach, when tested on a set of 1310 unselected cases collected over a fourteen year period at the Nottingham University Hospitals NHS Trust, UK. The experimental results show that the standard fuzzy inference system (that does not model variability) achieves overall agreement to clinical practice around 84.6% (95% CI: 84.1-84.9%), while the non-stationary fuzzy model can significantly increase performance to around 88.1% (95% CI: 88.0-88.2%), p<0.001. We conclude that non-stationary fuzzy models provide a valuable new approach that may be applied to clinical decision support systems in any application domain. © 2012 Elsevier Inc..
Garibaldi, J. M., Zhou, S. M., Wang, X. Y., John, R. I., & Ellis, I. O. (2012). Incorporation of expert variability into breast cancer treatment recommendation in designing clinical protocol guided fuzzy rule system models. Journal of Biomedical Informatics, 45(3), 447–459. https://doi.org/10.1016/j.jbi.2011.12.007