an IoT project to help epileptics

[ad_1]

In the UK, the Epilepsy Care Alliance has developed a project called MyCareCentric. This project aims to monitoring people with epilepsy to better understand this phenomenon and to be able to predict seizures in advance.

After the Embrace bracelet, anti-epilepsy, the project MyCareCentric aims to help people with epilepsy through the Internet of Things, and technology Machine Learning. The initiative combines smart health connected objects, health records, Machine Learning, and data analysis tools.

Data is collected from wearables, smartphones, portals, and integrated with clinical records of patients. The objective is to share medical records in real time between patients and clinician teams through a single network. This sharing will provide expert guidance and support at all times. The project could overcome the challenges facing people with epilepsy.

monitoring epileptics using the Microsoft Band

In the United Kingdom, health home country of the myCareCentric project, more than one million people suffer from epilepsy. It is with this large-scale problem that the Epilepsy Care Alliance Consortium decided to launch the project. This semi-public consortium brings together members from the University of Kent, NHS Foundration Trust Pool Hospital, Shearwater Systems and Graphnet.

A myCareCentric Epilepsy Review center has been open for some time in the Dorset Epilepsy Center. Whenever epileptic patients come to Dorset Center, ECA tries to get them to join the program and get their consent.

Microsoft's smart health connected Microsoft Band bracelet is part of the project. It was chosen for its API allowing full control. The ECA wanted to be able to control the autonomy, the activation of events and many other parameters. The application as for it capture data such as sleep cycles, exercise, heart rate or temperature.

MyCareCentric: towards the prediction of epileptic seizures

The goal of the center was to determine how to use the Microsoft Band to distinguish epileptic seizures. It exists groups and different types of crises, and each crisis is specific to the people who experience it. So, a lot of data has been collected.

Later, machine learning technology was used by the University of Kent to analyze this data. Analyzes using this technology allow individuals to better identify when the risks of crisis are increasing. Finally, the project could predict an epileptic seizure in advance. In parallel, an application allows the center to contact a patient as soon as he has an epileptic seizure.

In some cases, patients may not know that they have a seizure, if it occurs during their sleep. The center can thus warn them. In the near future, a localization service will be integrated to alert the family and friends of a victim of epileptic cries.

[ad_2]