Project description
Effective diagnosis of a rare form of dementia
Frontotemporal dementia (FTD) is a rare disorder that primarily affects the frontal and temporal lobes of the brain, leading to cognitive and behavioural changes. However, its diagnosis is challenging as the symptoms overlap with those of Alzheimer’s disease (AD). Funded by the Marie Skłodowska-Curie Actions programme, the IR4FTD project aims to develop a diagnostic approach for FTD and AD by using multimodal spectroscopy and machine learning. Rather than focusing on individual biomarkers, the project proposes a holistic approach, using vibrational spectroscopy analysis of saliva and plasma samples. With the help of advanced machine learning techniques, researchers hope to uncover hidden trends and molecular markers that will lead to a more cost-effective diagnostic tool for FTD.
Objective
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.
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.
You need to log in or register to use this function
Keywords
Programme(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Funding Scheme
HORIZON-TMA-MSCA-PF-GF - HORIZON TMA MSCA Postdoctoral Fellowships - Global FellowshipsCoordinator
34149 Trieste
Italy