Toward Transparent Sequence Models with Model-Based Tree Markov Model

TL;DR

This paper introduces MOB-HSMM, an interpretable sequence model that combines deep learning and probabilistic models to improve prediction and explainability of mortality risk in ICU data.

Contribution

The paper presents MOB-HSMM, a novel hybrid model that integrates deep neural networks with tree-based Hidden Semi-Markov Models for transparent sequence analysis.

Findings

MOB-HSMM improves mortality risk prediction accuracy.

LSTM-based MOB trees effectively learn sequential patterns.

Model-based trees enhance interpretability of sequence data.

Abstract

In this study, we address the interpretability issue in complex, black-box Machine Learning models applied to sequence data. We introduce the Model-Based tree Hidden Semi-Markov Model (MOB-HSMM), an inherently interpretable model aimed at detecting high mortality risk events and discovering hidden patterns associated with the mortality risk in Intensive Care Units (ICU). This model leverages knowledge distilled from Deep Neural Networks (DNN) to enhance predictive performance while offering clear explanations. Our experimental results indicate the improved performance of Model-Based trees (MOB trees) via employing LSTM for learning sequential patterns, which are then transferred to MOB trees. Integrating MOB trees with the Hidden Semi-Markov Model (HSMM) in the MOB-HSMM enables uncovering potential and explainable sequences using available information.