Development of an Algorithm to Perform a Comprehensive Study of Autonomic Dysreflexia in Animals with High Spinal Cord Injury Using a Telemetry Device

Time and frequency domain analysis of physiological features during autonomic dysreflexia after spinal cord injury

Introduction

Autonomic dysreflexia (AD) affects about 70% of individuals with spinal cord injury (SCI) and can have severe consequences, including death if not promptly detected and managed. The current gold standard for AD detection involves continuous blood pressure monitoring, which can be inconvenient. Therefore, a non-invasive detection device would be valuable for rapid and continuous AD detection.

Methods

Implanted rodent models were used to analyze autonomic dysreflexia after spinal cord injury. Skin nerve activity (SKNA) features were extracted from ECG signals recorded non-invasively, using ECG electrodes. At the same time, blood pressure and ECG data sampled was collected using an implanted telemetry device. Heart rate variability (HRV) features were extracted from these ECG signals. SKNA and HRV parameters were analyzed in both the time and frequency domain.

Results

We found that SKNA features showed an increase approximately 18 seconds before the typical rise in systolic blood pressure, indicating the onset of AD in a rat model with upper thoracic SCI. Additionally, low-frequency components of SKNA in the frequency domain were dominant during AD, suggesting their potential inclusion in an AD detection system for improved accuracy.

Discussion

Utilizing SKNA measurements could enable early alerts to individuals with SCI, allowing timely intervention and mitigation of the adverse effects of AD, thereby enhancing their overall well-being and safety.

Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia

Feature selection plays a crucial role in the development of machine learning algorithms. Understanding the impact of the features on a model, and their physiological relevance can improve the performance. This is particularly helpful in the healthcare domain wherein disease states need to be identified with relatively small quantities of data. Autonomic Dysreflexia (AD) is one such example, wherein mismanagement of this neurological condition could lead to severe consequences for individuals with spinal cord injuries. We explore different methods of feature selection needed to improve the performance of a machine learning model in the detection of the onset of AD. We present different techniques used as well as the ideal metrics using a dataset of thirty-six features extracted from electrocardiograms, skin nerve activity, blood pressure and temperature. The best performing algorithm was a 5-layer neural network with five relevant features, which resulted in 93.4% accuracy in the detection of AD. The techniques in this paper can be applied to a myriad of healthcare datasets allowing forays into deeper exploration and improved machine learning model development. Through critical feature selection, it is possible to design better machine learning algorithms for detection of niche disease states using smaller datasets.