Poster (Scientific congresses, symposiums and conference proceedings)
Combining PET imaging and blood metabolomics data to improve machine learning models for Parkinson’s disease diagnosis
Glaab, Enrico; Trezzi, Jean-Pierre; Greuel et al.
20182018 International Congress of the International Parkinson and Movement Disorders Society
 

Files


Full Text
metabolomics PET machine learning poster 2018.pdf
Publisher postprint (3 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Parkinson; neuroimaging; metabolomics; PET; machine learning; integration; differential abundance
Abstract :
[en] Objective: To investigate whether the integration of PET imaging and metabolomics data can provide improved machine learning models for PD diagnosis. Background: The reliable diagnosis of PD can remain challenging, even at the motor stage. PET imaging can be used to confirm the clinical diagnosis. However, limitations in the robustness of predictive features extracted from the data and the costs associated with PET imaging restrict its application. Using blood metabolomics data as an additional information source may provide improved combined diagnostic models and/or an initial filter to decide on whether to apply PET imaging. Methods: Metabolomics profiling of blood plasma samples using gas chromatography coupled to mass spectrometry (GC­MS) was conducted in 60 IPD patients and 15 healthy controls. After pre-processing, these data were compared to neuroimaging data for subsets of the same individuals using FDOPA PET (44 patients and 14 controls) and FDG PET (51 patients and 15 controls). Machine learning models using linear support vector machines were trained on 50% of the data and evaluated on a 50% hold­out test set using Receiver Operating Characteristic (ROC) curves. Next, standardized FDOPA and FDG PET intensity measurements were combined with those from the metabolomics data to build and evaluate sample classification models in the same manner as for the individual datasets. Results: Both for the FDOPA and FDG PET data, the predictive performance given by the area under the ROC curve (AUC) was highest when combining imaging features with those from the metabolomics data (AUC for FDOPA + metabolomics: 0.98; AUC for FDG + metabolomics: 0.91). The performance was generally lower when using only the respective PET attributes (FDOPA: 0.94, FDG: 0.8) or only the metabolomics data (AUC: 0.66).
Research center :
- Luxembourg Centre for Systems Biomedicine (LCSB): Biomedical Data Science (Glaab Group)
Disciplines :
Life sciences: Multidisciplinary, general & others
Neurology
Biotechnology
Author, co-author :
Glaab, Enrico  ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Trezzi, Jean-Pierre ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Greuel
Jäger, Christian  ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Hodak, Zdenka ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Timmermann, Lars
Tittgemeyer, Marc
Diederich, Nico Jean
Eggers, Carsten
External co-authors :
yes
Language :
English
Title :
Combining PET imaging and blood metabolomics data to improve machine learning models for Parkinson’s disease diagnosis
Publication date :
08 October 2018
Event name :
2018 International Congress of the International Parkinson and Movement Disorders Society
Event place :
Esch-sur-Alzette, Luxembourg
Event date :
from 05-10-2018 to 09-10-2018
Audience :
International
Focus Area :
Systems Biomedicine
FnR Project :
FNR11651464 - Multi-dimensional Stratification Of Parkinson'S Disease Patients For Personalised Interventions, 2017 (01/07/2018-30/06/2021) - Enrico Glaab
Name of the research project :
Mito-PD, PD-Strat
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 02 December 2018

Statistics


Number of views
227 (29 by Unilu)
Number of downloads
116 (20 by Unilu)

WoS citations
 
0

Bibliography


Similar publications



Contact ORBilu