A Framework for Feature Discovery in Intracranial Pressure Monitoring Data Using Neural Network Attention

TL;DR

This paper introduces an interpretable neural network framework that analyzes intracranial pressure waveforms to identify key features and improve understanding of clinical data.

Contribution

It presents a novel approach combining neural network attention with waveform analysis for intracranial pressure data, enhancing interpretability and potential diagnostics.

Findings

Neural network attention highlights physiologically relevant waveform regions.

The framework successfully classifies cardiac cycles into body positions.

Provides a basis for further exploration of intracranial pressure signals.

Abstract

We present a novel framework for analyzing intracranial pressure monitoring data by applying interpretability principles. Intracranial pressure monitoring data was collected from 60 patients at Johns Hopkins. The data was segmented into individual cardiac cycles. A convolutional neural network was trained to classify each cardiac cycle into one of seven body positions. Neural network attention was extracted and was used to identify regions of interest in the waveform. Further directions for exploration are identified. This framework provides an extensible method to further understand the physiological and clinical underpinnings of the intracranial pressure waveform, which could lead to better diagnostic capabilities for intracranial pressure monitoring.