Project description
A wearable device to predict epileptic seizures
Epilepsy, the fourth most common neurological disorder, affects more than 50 million people of all ages worldwide, and can cause unpredictable seizures. It can incur costs amounting to billions of euros for European healthcare systems. The EU-funded ESPS project - the epileptic seizure prediction system - aims to use iBreve's technology a wearable, innovative device that analyses respiratory patterns within the field of epilepsy. ESPS uses machine-learning algorithms to calculate seizure probability and intensity. If needed, it alerts the caregiver. It allows to personalise treatment and offers support for respiratory and stress management. ESPS has the potential to improve the life of epileptic patients by making their life more predictable and saving up to 70% of their current treatment costs.
Objective
Epilepsy is one of the most common nervous system disorders and affects more than 50M people worldwide. The majority of new-onset cases occur in elderly and children. Currently there is no cure for epilepsy. Although antiepileptic drugs can help, one third of all patients do not respond to any pharmacological intervention. This staggering number has not changed in decades, despite over 14 new therapies entering the market.
The unpredictable nature of seizures causes the largest burden for patients as it literally disrupts their lives. Patients with several seizures a week are hesitant to leave the house & find it hard to obtain employment. Reliably predicting seizures enables an independent life for the patient and at the same time reduces healthcare costs caused by clinician visits, injuries & caretaking.
iBreve’s new patent-pending wearable technology analyzes respiratory patterns in real-time, enabling market applications for seizure prediction, respiratory treatment & stress management. iBreve’s technology received interest from Harvard’s Boston Children’s Hospital to be included in clinical trials for seizure detection & prediction. The ESPS machine learning algorithm calculates seizure probability & intensity and if desired an alert is sent to the patient’s caregiver. The tracking and analysis of seizures can be shared with clinicians & allows to personalize treatment.
Main objective of this feasibility study is the development of a comprehensive business plan to evaluate the opportunities & risks of introducing ESPS into the homecare market. All project activities follow the Healthcare Innovation Cycle methodology & are structured around 4 development pillars - Technology, Market & Business, Clinical and Regulatory.
The introduction of ESPS is prone to disrupt the epilepsy market by reducing treatment costs per patient by up to 70%. Thus, saving 14B€ in health care costs in Europe alone and creating a major shift towards preventive & personalized treatment.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
- natural sciencesbiological sciencesneurobiology
- medical and health sciencesbasic medicineneurologyepilepsy
- natural sciencescomputer and information sciencesinternetinternet of things
- social scienceseconomics and businessbusiness and managementemployment
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
You need to log in or register to use this function
Programme(s)
Funding Scheme
SME-1 - SME instrument phase 1Coordinator
D02 P593 Dublin
Ireland
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.