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

More than half of patients with high spinal cord injury (SCI) suffer from episodes 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 the patient’s history and physiological invasively non-invasively. This work aims design machine learning-based system assist in initial diagnosis AD. For this purpose, 29 SCI participated test at Cruces University Hospital which data were collected both invasive non-invasive methods. The proposed article is based on two-level hierarchical classification diagnose only uses 35 features extracted stages experiment (clinical features). achieved 93.10% accuracy zero false negative rate for class having disease, an essential treating according medical criteria.