A Novel Tropical Geometry-based Interpretable Machine Learning Method: Application in Prognosis of Advanced Heart Failure

TL;DR

This paper introduces a tropical geometry-based interpretable machine learning method that models relationships with understandable rules, demonstrating high performance in clinical prognosis of heart failure and enabling knowledge transfer for improved generalizability.

Contribution

It presents a novel tropical geometry approach to fuzzy inference systems, enhancing interpretability and domain knowledge integration in machine learning models.

Findings

Achieved high classification accuracy on synthetic and clinical datasets.

Enabled transfer of existing fuzzy domain knowledge into the model.

Improved model generalizability through domain knowledge incorporation.

Abstract

A model's interpretability is essential to many practical applications such as clinical decision support systems. In this paper, a novel interpretable machine learning method is presented, which can model the relationship between input variables and responses in humanly understandable rules. The method is built by applying tropical geometry to fuzzy inference systems, wherein variable encoding functions and salient rules can be discovered by supervised learning. Experiments using synthetic datasets were conducted to investigate the performance and capacity of the proposed algorithm in classification and rule discovery. Furthermore, the proposed method was applied to a clinical application that identified heart failure patients that would benefit from advanced therapies such as heart transplant or durable mechanical circulatory support. Experimental results show that the proposed network achieved great performance on the classification tasks. In addition to learning humanly understandable rules from the dataset, existing fuzzy domain knowledge can be easily transferred into the network and used to facilitate model training. From our results, the proposed model and the ability of learning existing domain knowledge can significantly improve the model generalizability. The characteristics of the proposed network make it promising in applications requiring model reliability and justification.