Summary
The central aim of the project is to apply multimodal spectroscopy combined with machine learning to identify a fingerprint for Frontal Temporal Dementia (FTD) and Alzheimer’s disease (AD) in saliva and plasma. FTD is the second most common dementia and usually affects individuals younger than 60 years old. FTD is difficult to diagnose, since there is no single exam that determines the disease, but instead many costly or painful exams that together link the disease. Some of the symptoms of the disease may be confounding with others such as AD. While the usual search for biomarkers focuses on individual patterns, the present proposal is to use a holistic approach. Vibrational spectroscopy provides a snapshot of the entire chemical finger print in a label-free way. In this project, samples from FTD, AD, and healthy subjects of >45 years old, will be analysed using Raman, mid and near infrared spectroscopy @Monash University in Australia, and complemented with Mass Spectrometry on the same samples @ICGEB in Italy. Advanced machine learning tools provide a powerful approach for data analysis unravelling hidden trends, correlations and also identify the main contributions that characterize the type of sample. The spectra recorded using the extended wavelength range encompassing the mid-infrared and near-infrared spectral regions will be processed with state-of-the-art machine learning tools to identify the molecular phenotype and establish markers in patients with TDP and AD. These findings will pave the way to the development of a new screening tool that would decrease the costs associated with the current diagnosis of FTD and in general for neurodegenerative disorders.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101106307 |
| Start date: | 01-10-2023 |
| End date: | 30-09-2026 |
| Total budget - Public funding: | - 287 152,00 Euro |
Cordis data
Original description
The central aim of the project is to apply multimodal spectroscopy combined with machine learning to identify a fingerprint for Frontal Temporal Dementia (FTD) and Alzheimer’s disease (AD) in saliva and plasma. FTD is the second most common dementia and usually affects individuals younger than 60 years old. FTD is difficult to diagnose, since there is no single exam that determines the disease, but instead many costly or painful exams that together link the disease. Some of the symptoms of the disease may be confounding with others such as AD. While the usual search for biomarkers focuses on individual patterns, the present proposal is to use a holistic approach. Vibrational spectroscopy provides a snapshot of the entire chemical finger print in a label-free way. In this project, samples from FTD, AD, and healthy subjects of >45 years old, will be analysed using Raman, mid and near infrared spectroscopy @Monash University in Australia, and complemented with Mass Spectrometry on the same samples @ICGEB in Italy. Advanced machine learning tools provide a powerful approach for data analysis unravelling hidden trends, correlations and also identify the main contributions that characterize the type of sample. The spectra recorded using the extended wavelength range encompassing the mid-infrared and near-infrared spectral regions will be processed with state-of-the-art machine learning tools to identify the molecular phenotype and establish markers in patients with TDP and AD. These findings will pave the way to the development of a new screening tool that would decrease the costs associated with the current diagnosis of FTD and in general for neurodegenerative disorders.Status
SIGNEDCall topic
HORIZON-MSCA-2022-PF-01-01Update Date
31-07-2023
Images
No images available.
Geographical location(s)
