Fuzzy Decision Tree Based Method in Decision-Making of COVID-19 Patients’ Treatment

Abstract

A new method in decision-making of timing of tracheostomy in COVID-19 patients is developed and discussed in this paper. Tracheostomy is performed in critically ill coronavirus disease (COVID-19) patients. The timing of tracheostomy is important for anticipated prolonged ventilatory wean when levels of respiratory support were favorable. The analysis of this timing has been implemented based on classification method. One of principal conditions for the developed classifiers in decision-making of timing of tracheostomy in COVID-19 patients was a good interpretation of result. Therefore, the proposed classifiers have been developed as decision tree based because these classifiers have very good interpretability of result. The possible uncertainty of initial data has been considered by the application of fuzzy classifiers. Two fuzzy classifiers as Fuzzy Decision Tree (FDT) and Fuzzy Random Forest (FRF) have been developed for the decision-making in tracheostomy timing. The evaluation of proposed classifiers and their comparison with other show the efficiency of the proposed classifiers. FDT has best characteristics in comparison with other classifiers.

Z-number Decision Tree and Its Appliction

“…Where m 1 and m 2 are the fuzzifier of IFCM (1 < m 1 < m 2 ), µ k ij (i = 1, 2, ..., N, j = 1, 2, ..., C, k = 1, 2, ..., n) needs to satisfy: make the objective function (7) obtain the minimum value under the constraint condition (8). The Lagrangian extremum method can be used to solve µ k ij (i = 1, 2, ..., N, j = 1, 2, ..., C, k = 1, 2, ..., n):…”

“…Fuzzy decision tree algorithm [1] is an improved algorithm of decision tree algorithm [2]. As fuzzy classifification systems based on fuzzy decision tree are generally robust, FDT have been widely and successfully applied to many fields, such as decision-making [3,4], classification and prediction [5,6], medical treatment [7,8,9], etc.…”

A New Fuzzy-Based Classification Method for Use in Smart/Precision Medicine

“…The transformation of the pre-processing result into the fuzzy domain extends the classification attribute value borders and decreases the impact of lost information. In other studies [29,37] the efficiency of fuzzy classifiers for use with large dimensional data has been investigated.…”

“…Laboratory research into tumors, based on an analysis of blood parameter classification, is considered an example of large dimensional data classification [35]. Numeric data classification is illustrated by the timing of tracheostomies in COVID-19 patients [37]. Expert data classification is considered for an analysis of the influence of the human factor in a medical team [30].…”

“…At the same time, a new method for classifier induction should allow its development for the different types of initial data. In particular, we intend to consider and systemize classification signals [29,34], large-dimensional data [35,36], numeric data [37,38] and linguistic data [28,39]. An analysis of these studies shows that there are differences in the pre-processing steps of the initial data.…”