Date-Driven Approach for Identifying State of Hemodialysis Fistulas: Entropy-Complexity and Formal Concept Analysis
This work addresses a domain-specific medical issue for patients with hemodialysis fistulas, offering an incremental improvement in diagnostic methods.
The paper tackled the problem of identifying pathological hemodialysis fistulas by distinguishing regular and chaotic time series in blood flow data, proposing a noise-resistant method that achieved high efficiency in classification.
The paper explores mathematical methods that differentiate regular and chaotic time series, specifically for identifying pathological fistulas. It proposes a noise-resistant method for classifying responding rows of normally and pathologically functioning fistulas. This approach is grounded in the hypothesis that laminar blood flow signifies normal function, while turbulent flow indicates pathology. The study explores two distinct methods for distinguishing chaotic from regular time series. The first method involves mapping the time series onto the entropy-complexity plane and subsequently comparing it to established clusters. The second method, introduced by the authors, constructs a concepts-objects graph using formal concept analysis. Both of these methods exhibit high efficiency in determining the state of the fistula.