Preliminary Study on the Detection of Autonomic Dysreflexia Using Machine Learning Techniques

Sagastibeltza, Nagore; Salazar-Ramirez, Asier; Yera, Ainhoa; Martínez, Raquel; Muguerza, Javier; Sánchez, Nora Cívicos; Acera, Marian

doi:10.1007/978-3-030-97719-1_20

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work continues with the previous study conducted by this team in which they analysed the detection of AD with the data collected from 5 SCI patients [22]. In that work, the classifiers proposed for diagnosing the AD gave promising results and 4 of the 5 patients were classified correctly (2 without AD and 3 with AD).…”

Section: The Data Collection Experimentssupporting

confidence: 69%

“…In this work, the research team has presented an expansion of their previous work [22] that focused on performing the initial diagnostic of AD in patients with SCI using ML algorithms. To the extent of the authors' knowledge, the bibliography that seeks to detect this disease using ML is very scarce [20] and even moreso the one focusing on its initial diagnostic.…”

Section: Discussionmentioning

confidence: 99%

“…However, the classification error that took place resulted in an FN and, as explained in the introduction, the errors of this type are not acceptable because not diagnosing a patient with the disease may have deadly consequences. For this reason, the researchers teamed with the medical team of CUH and repeated the same experimentation of [22] to expand the sample of the study to 29 SCI patients (20 male and 9 female) ranging between 32 and 85 years old (mean = 52.24 and SD = 12.79 years). In this new sample, 21 of the 29 participants had already been diagnosed with AD and the other 8 were free from the disease.…”

Section: The Data Collection Experimentsmentioning

confidence: 99%

“…Twenty-four hours before the experiment, the patients signed a consent form and had their bladder emptied. Concerning the process inside the laboratory, the data collection was performed according to the same experimental protocol [22], which received the approval of the Clinical Research Committee of Basque under the PI2013132 validation code. The protocol was divided into the three stages shown in Figure 1, which will be described below.…”

Section: The Data Collection Experimentsmentioning

confidence: 99%

“…The team's objective was to design a ML-based system for diagnosing AD in patients with SCI. Thus, they expanded the previous work of [22] and conducted a pilot experiment with 29 patients with SCI at Cruces University Hospital (CUH, from now on). Some of the data collected in these experiments are of a non-invasive nature: clinical history data, analyses of hormonal variations obtained through blood extraction, monitorisation of physiological variables at rest, etc.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Hierarchical Machine Learning Solution for the Non-Invasive Diagnostic of Autonomic Dysreflexia

et al. 2022

Self Cite

View full text Add to dashboard Cite

More than half of patients with high spinal cord injury (SCI) suffer from episodes of autonomic dysreflexia (AD), a condition that can lead to lethal situations, such as cerebral haemorrhage, if not treated correctly. Clinicians assess AD using clinical variables obtained from the patient’s history and physiological variables obtained invasively and non-invasively. This work aims to design a machine learning-based system to assist in the initial diagnosis of AD. For this purpose, 29 patients with SCI participated in a test at Cruces University Hospital in which data were collected using both invasive and non-invasive methods. The system proposed in this article is based on a two-level hierarchical classification to diagnose AD and only uses 35 features extracted from the non-invasive stages of the experiment (clinical and physiological features). The system achieved a 93.10% accuracy with a zero false negative rate for the class of having the disease, an essential condition for treating patients according to medical criteria.

show abstract

Section: The Data Collection Experimentssupporting

confidence: 69%

Section: Discussionmentioning

confidence: 99%

Section: The Data Collection Experimentsmentioning

confidence: 99%

Section: The Data Collection Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Hierarchical Machine Learning Solution for the Non-Invasive Diagnostic of Autonomic Dysreflexia

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Kinect-Enabled Electronic Game for Developing Cognitive and Gross Motor Skills in 4-5-Year-Old Children

Núñez

López

Nuñez

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

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

Kirby,

Pancholi,

Anderson

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionAutonomic 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.MethodsImplanted 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.ResultsWe 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.DiscussionUtilizing 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.

show abstract

Preliminary Study on the Detection of Autonomic Dysreflexia Using Machine Learning Techniques

Cited by 3 publications

References 9 publications

A Hierarchical Machine Learning Solution for the Non-Invasive Diagnostic of Autonomic Dysreflexia

A Hierarchical Machine Learning Solution for the Non-Invasive Diagnostic of Autonomic Dysreflexia

Kinect-Enabled Electronic Game for Developing Cognitive and Gross Motor Skills in 4-5-Year-Old Children

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

Contact Info

Product

Resources

About