A Framework for Feature Discovery in Intracranial Pressure Monitoring Data Using Neural Network Attention
By: Jonathan D. Socha , Seyed F. Maroufi , Dipankar Biswas and more
Potential Business Impact:
Helps doctors understand brain pressure using AI.
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.
Similar Papers
PMB-NN: Physiology-Centred Hybrid AI for Personalized Hemodynamic Monitoring from Photoplethysmography
Medical Physics
Measures blood pressure and heart health accurately.
A Fully Automatic Framework for Intracranial Pressure Grading: Integrating Keyframe Identification, ONSD Measurement and Clinical Data
CV and Pattern Recognition
Helps doctors check brain pressure without surgery.
A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking
Signal Processing
Predicts patient health problems in the ICU.