Wearable Epileptic Seizure Prediction System Based on Machine Learning Techniques Using ECG, PPG and EEG Signals

Abstract

Epileptic seizures have a great impact on the quality of life of people who suffer from them and further limit their independence. For this reason, a device that would be able to monitor patients’ health status and warn them for a possible epileptic seizure would improve their quality of life. With this aim, this article proposes the first seizure predictive model based on Ear EEG, ECG and PPG signals obtained by means of a device that can be used in a static and outpatient setting. This device has been tested with epileptic people in a clinical environment. By processing these data and using supervised machine learning techniques, different predictive models capable of classifying the state of the epileptic person into normal, pre-seizure and seizure have been developed. Subsequently, a reduced model based on Boosted Trees has been validated, obtaining a prediction accuracy of 91.5% and a sensitivity of 85.4%. Thus, based on the accuracy of the predictive model obtained, it can potentially serve as a support tool to determine the status epilepticus and prevent a seizure, thereby improving the quality of life of these people.

Photoplethysmography Driven Hypertension Identification: A Pilot Study

“…Traditional machine learning methods have been extensively studied in PPG [ 34 , 35 , 36 , 37 ], and this study also compares SVM and KNN classification models with the LSTM-Attention model. Unlike neural networks, which can directly train on raw signals, feature extraction is required before training these two models.…”

Recent Developments and Future Directions of Wearable Skin Biosignal Sensors

“…Therefore, the use of machine learning algorithms in conjunction with PPG signals has significant potential for improving the diagnosis of cardiovascular and respiratory disorders with further potential for speculating various biosignals. [167,178,179] The utilization of PPG initially focused on detecting changes in blood volume in vessels, making it suitable for detecting blood loss. [180] Accurately assessing the severity of occult hemorrhage is crucial for trauma patients, as severe blood loss (exceeding 30% of blood volume) can result in lethal shock.…”

Künstliche Intelligenz in der Neurologie

“…B. Smart Watches, Knöchelsensoren oder retroauriku-lärer EEG-Systeme können epileptische Anfälle teils unterschiedlicher Semiologie detektiert werden [19]. Dadurch kann man die tatsächliche Anzahl der Anfälle besser erheben, aber auch zirkadiane Rhythmen erfassen und die Therapie anpassen [20].…”

“…Eine Vorwarnung könnte das Verletzungsrisiko minimieren, zusätzlich kann ein Alarm an Angehörige gesendet werden. Hierfür werden je nach Forschungsgruppe unterschiedliche Parameter verwendet: Veränderungen im vegetativen Nervensystem, Herzrate, Photoplethysmografie, EEG, Akzelerometer [19]. Noch ist die Vorhersagerate zu gering, um einen wirklichen Nutzen zu erzielen.…”

“…Je nach Studie ▶Abb. 1 Flussdiagramm zur Darstellung der Funktionsweise von Smart Devices in der Epilepsie (nach Daten aus [19]). wurde dabei eine Sensitivität von 80 % und eine Spezifität von 86 % erreicht [24].…”