Support Vector Machine-Based Classification of Vasovagal Syncope Using Head-Up Tilt Test

Abstract

Syncope is the medical condition of loss of consciousness triggered by the momentary cessation of blood flow to the brain. Machine learning techniques have been established to be very effective way to address such problems, where a class label is predicted for given input data. This work presents a Support Vector Machine (SVM) based classification of neuro-mediated syncope evaluated using train–test–split and K-fold cross-validation methods using the patient’s physiological data collected through the Head-up Tilt Test in pure clinical settings. The performance of the model has been analyzed over standard statistical performance indices. The experimental results prove the effectiveness of using SVM-based classification for the proactive diagnosis of syncope.

Diagnosing Neurally Mediated Syncope Using Classification Techniques

“…A model for vasovagal syncope classification using the Support Vector Machine (SVM)-based classification was presented in [ 16 ]. However, the work was limited to the use of the SVM in classification and lacked the exploration of other supervised machine learning models which could result in a better classification.…”

“…The test for this study found three main underlying mechanisms responsible for the triggering of the induction of syncope, viz. a sudden drop in blood pressure, drop in heart rate resulting in a drop in blood pressure and a continual drop in blood pressure as reported in [ 16 ].…”

“…The HUT test concluded with the findings that, out of 687 patients, only 96 patients were recognized to have the induction of syncope, while the remaining 592 patients were able to keep control of their BP and HR. A total of 48 different physiological indicators against each individual were recorded in a proper format as reported in [ 16 ]. These indicators were majorly grouped under five subgroups, viz.…”

“…In this regard, a syncope classification model is proposed for classifying syncope and non-syncope events. This work draws its origin from [ 16 ], where it was established that syncope classification can be performed using a Support Vector Machine (SVM)-based machine learning algorithm. However, there are many other machine learning algorithms that need to be evaluated for the purpose of syncope classification for an effective and efficient syncope detection.…”

“…However, there are many other machine learning algorithms that need to be evaluated for the purpose of syncope classification for an effective and efficient syncope detection. This work uses the dataset used in [ 16 ] to present an exhaustive exploration and comparison of some very relevant machine learning classification techniques, including the SVM, for syncope classification. The aim of the study is to further analyze the performance of the SVM with other machine learning peers in this context to explore their suitability in syncope classification.…”