wFDT: weighted fuzzy decision trees for prognosis of breast cancer survivability

摘要: Accurate and less invasive personalized predictive medicine can spare many breast cancer patients from receiving complex surgical biopsies, unnecessary adjuvant treatments its expensive medical cost. Cancer prognosis estimates recurrence of disease predict survival patient; hence resulting in improved patient management. To develop such knowledge based prognostic system, this paper examines potential hybridization accuracy interpretability the form Fuzzy Logic Decision Trees, respectively. Effect rule weights on fuzzy decision trees is investigated to be an alternative membership function modifications for performance optimization. Experiments were performed using different combinations of: number tree rules, types functions inference techniques analysis. SEER data set (1973-2003), most comprehensible source information incidence United States, considered. Performance comparisons suggest that predictions weighted (wFDT) are more accurate balanced, than independently applied crisp classifiers; moreover it has a adapt significant enhancement.