Self-explaining Hierarchical Model for Intraoperative Time Series

TL;DR

This paper introduces a hierarchical, interpretable model combining attention and recurrent mechanisms to predict postoperative complications from intraoperative time series data, providing accurate and transparent insights for clinical decision-making.

Contribution

The paper presents a novel hierarchical model with an explanation module that enhances interpretability of intraoperative data predictions, addressing gaps in transparency and handling long, fine-grained time series.

Findings

Achieves high predictive accuracy on large surgical datasets.

Provides robust, fine-grained interpretability of model predictions.

Effective in predicting postoperative complications from intraoperative data.

Abstract

Major postoperative complications are devastating to surgical patients. Some of these complications are potentially preventable via early predictions based on intraoperative data. However, intraoperative data comprise long and fine-grained multivariate time series, prohibiting the effective learning of accurate models. The large gaps associated with clinical events and protocols are usually ignored. Moreover, deep models generally lack transparency. Nevertheless, the interpretability is crucial to assist clinicians in planning for and delivering postoperative care and timely interventions. Towards this end, we propose a hierarchical model combining the strength of both attention and recurrent models for intraoperative time series. We further develop an explanation module for the hierarchical model to interpret the predictions by providing contributions of intraoperative data in a fine-grained manner. Experiments on a large dataset of 111,888 surgeries with multiple outcomes and an external high-resolution ICU dataset show that our model can achieve strong predictive performance (i.e., high accuracy) and offer robust interpretations (i.e., high transparency) for predicted outcomes based on intraoperative time series.