Improving medical decisions under incomplete data using interval–valued fuzzy aggregation

Abstract

We state a problem concerning how to make an effective and proper decision in the presence of data incompleteness. As an example we consider a medical diagnostic system where the problem of missing data is commonly encountered. We propose and evaluate an approach that makes it possible to reduce the influence of missing data on the final result and to improve the quality of the decision. The process involves interval-valued fuzzy set modelling, uncertaintification of classical methods, and finally aggregation of the incomplete results. It was verified that the aggregation results in meaningful and accurate decisions despite the missing data.

A framework for learning fuzzy rule-based models with epistemic set-valued data and generalized loss functions

“…This single model is assigned a different loss for each of the possible completions of every instance. In the interval case, these losses are aggregated first into an interval-valued loss for each instance, and interval losses are aggregated to obtain the risk function [21] [22].…”