Summary
Dementia is an umbrella term for age-related brain disease, of which Alzheimer’s Disease (AD) is the most common. Around 5-7% of adults over 60 years suffer dementia worldwide, with approx. 8.7 m people in the EU. A frequent precursor of AD is amnestic mild cognitive impairment (aMCI), a clinical condition characterised by declines in memory skills. By predicting
aMCI progression, health-care services will have new opportunities to deliver early interventions that could delay AD onset. This will ultimately promote functional independence in vulnerable adults and meet the societal challenge Health, Demographic Change and Wellbeing of Horizon 2020.
Clinical outcomes of aMCI patients are influenced by the severity of cognitive (dys-) function. However, these deficits may occur at an advanced stage of neurodegeneration. This fellowship aims to identify a predictive model of cognitive function based on brain activity measured with electro-encephalography (EEG). Previous studies suggest that the capacity to learn a new task (practice effects) can help classify a person into healthy, aMCI or AD. Also, cross-sectional studies using EEG have found differences between normal controls, aMCI and AD patients during rest and cognitive tasks. The behavioural and EEG evidence combined shows the potential of using behavioural practice and EEG measures to predict cognitive function.
This potential will be investigated and exploited in this fellowship via advanced machine learning methods on a large EEG
data sample. This fellowship will take place in BrainWaveBank (BWB), an innovative company developing the largest database of EEG data in older adults along with cutting-edge analytics. This fellowship will allow the researcher to apply her experience on neural engineering and expand her knowledge and expertise to machine learning and clinical neuroscience in BWB. This will build the researcher’s independence and build prospects for a career in the medical technology sector.
aMCI progression, health-care services will have new opportunities to deliver early interventions that could delay AD onset. This will ultimately promote functional independence in vulnerable adults and meet the societal challenge Health, Demographic Change and Wellbeing of Horizon 2020.
Clinical outcomes of aMCI patients are influenced by the severity of cognitive (dys-) function. However, these deficits may occur at an advanced stage of neurodegeneration. This fellowship aims to identify a predictive model of cognitive function based on brain activity measured with electro-encephalography (EEG). Previous studies suggest that the capacity to learn a new task (practice effects) can help classify a person into healthy, aMCI or AD. Also, cross-sectional studies using EEG have found differences between normal controls, aMCI and AD patients during rest and cognitive tasks. The behavioural and EEG evidence combined shows the potential of using behavioural practice and EEG measures to predict cognitive function.
This potential will be investigated and exploited in this fellowship via advanced machine learning methods on a large EEG
data sample. This fellowship will take place in BrainWaveBank (BWB), an innovative company developing the largest database of EEG data in older adults along with cutting-edge analytics. This fellowship will allow the researcher to apply her experience on neural engineering and expand her knowledge and expertise to machine learning and clinical neuroscience in BWB. This will build the researcher’s independence and build prospects for a career in the medical technology sector.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/893823 |
| Start date: | 01-10-2020 |
| End date: | 30-09-2022 |
| Total budget - Public funding: | 184 590,72 Euro - 184 590,00 Euro |
Cordis data
Original description
Dementia is an umbrella term for age-related brain disease, of which Alzheimer’s Disease (AD) is the most common. Around 5-7% of adults over 60 years suffer dementia worldwide, with approx. 8.7 m people in the EU. A frequent precursor of AD is amnestic mild cognitive impairment (aMCI), a clinical condition characterised by declines in memory skills. By predictingaMCI progression, health-care services will have new opportunities to deliver early interventions that could delay AD onset. This will ultimately promote functional independence in vulnerable adults and meet the societal challenge Health, Demographic Change and Wellbeing of Horizon 2020.
Clinical outcomes of aMCI patients are influenced by the severity of cognitive (dys-) function. However, these deficits may occur at an advanced stage of neurodegeneration. This fellowship aims to identify a predictive model of cognitive function based on brain activity measured with electro-encephalography (EEG). Previous studies suggest that the capacity to learn a new task (practice effects) can help classify a person into healthy, aMCI or AD. Also, cross-sectional studies using EEG have found differences between normal controls, aMCI and AD patients during rest and cognitive tasks. The behavioural and EEG evidence combined shows the potential of using behavioural practice and EEG measures to predict cognitive function.
This potential will be investigated and exploited in this fellowship via advanced machine learning methods on a large EEG
data sample. This fellowship will take place in BrainWaveBank (BWB), an innovative company developing the largest database of EEG data in older adults along with cutting-edge analytics. This fellowship will allow the researcher to apply her experience on neural engineering and expand her knowledge and expertise to machine learning and clinical neuroscience in BWB. This will build the researcher’s independence and build prospects for a career in the medical technology sector.
Status
CLOSEDCall topic
MSCA-IF-2019Update Date
28-04-2024
Images
No images available.
Geographical location(s)
