Targeted serum metabolomic profiling and machine learning approach in Alzheimer's disease using the Alzheimer's disease diagnostics clinical study (ADDIA) cohort

BackgroundMetabolic biomarkers can potentially be used for early diagnosis, prognostic risk stratification and/or early treatment and prevention of individuals at risk to develop Alzheimer's disease (AD).ObjectiveOur goal was to evaluate changes in metabolite concentration levels associated with AD to identify biomarkers that could support early and accurate diagnosis and therapeutic interventions by using targeted mass spectrometry and machine learning approaches.MethodsSerum samples collected from a total of 107 individuals, including 55 individuals diagnosed with AD and 52 healthy controls (HC) enrolled previously to ADDIA cohort were analyzed using the biocrates AbsoluteIDQ<sup>®</sup> p400 HR kit metabolite and lipid panel. Several machine learning models including Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), Random Forest, and XGBoost were trained to classify AD and HC. Repeated cross-validation was used to ensure performance evaluation.ResultsThe LASSO and PLS models showed the strongest classification performance on the test set, achieving area under the ROC curve (AUC) values of 0.84 and 0.90, respectively. A refined model based on only the top 5 metabolites maintained strong performance, and the inclusion of Apolipoprotein E (<i>APOE</i>) genotype information notably improved classification accuracy, particularly by reducing false negatives in AD cases.ConclusionsThese results highlight important metabolic signatures that could help to reduce misdiagnosis and support the development of metabolomic panels to detect AD. The combination of multiple serum metabolic biomarkers and <i>APOE</i> genotyping can significantly improve classification accuracy and potentially assist in making non-invasive, cost-effective diagnostic approach.

Authors

Institutions

Publication Details

Journal
Journal of Alzheimer s Disease
Published
2025-09-26
DOI
https://doi.org/10.1177/13872877251378653
Citations
1
Primary Topic
Metabolomics and Mass Spectrometry Studies
Type
article
Field-Weighted Citation Impact
0.81

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Targeted serum metabolomic profiling and machine learning approach in Alzheimer's disease using the Alzheimer's disease diagnostics clinical study (ADDIA) cohort

Guillaume Sacco, Jean‐François Démonet, Hakan Gürvıt, Éloi Magnin et al.
1 citations
Journal of Alzheimer s Disease
Metabolomics and Mass Spectrometry Studies
0.81
article

Targeted serum metabolomic profiling and machine learning approach in Alzheimer's disease using the Alzheimer's disease diagnostics clinical study (ADDIA) cohort

Guillaume Sacco, Jean‐François Démonet, Hakan Gürvıt, Éloi Magnin, Frédérick Durand, Adrian Ivanoiu, Lucas Dinh Pham-Van, Florence Pasquier, Tamer Demıralp, Seval Kul, Renaud David, François Sellal, Moira Marizzoni, Stéphanie Boutillier, Frédéric Blanc, Audrey Gabelle, Giovanni B. Frisoni, Bruno Dubois, Dany Mukesha, Jean‐Christophe Bier, David Halter, Hüseyin Firat, Mélitine Dubray, Maité Sarter
article en
1 citations

Abstract

BackgroundMetabolic biomarkers can potentially be used for early diagnosis, prognostic risk stratification and/or early treatment and prevention of individuals at risk to develop Alzheimer's disease (AD).ObjectiveOur goal was to evaluate changes in metabolite concentration levels associated with AD to identify biomarkers that could support early and accurate diagnosis and therapeutic interventions by using targeted mass spectrometry and machine learning approaches.MethodsSerum samples collected from a total of 107 individuals, including 55 individuals diagnosed with AD and 52 healthy controls (HC) enrolled previously to ADDIA cohort were analyzed using the biocrates AbsoluteIDQ<sup>®</sup> p400 HR kit metabolite and lipid panel. Several machine learning models including Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), Random Forest, and XGBoost were trained to classify AD and HC. Repeated cross-validation was used to ensure performance evaluation.ResultsThe LASSO and PLS models showed the strongest classification performance on the test set, achieving area under the ROC curve (AUC) values of 0.84 and 0.90, respectively. A refined model based on only the top 5 metabolites maintained strong performance, and the inclusion of Apolipoprotein E (<i>APOE</i>) genotype information notably improved classification accuracy, particularly by reducing false negatives in AD cases.ConclusionsThese results highlight important metabolic signatures that could help to reduce misdiagnosis and support the development of metabolomic panels to detect AD. The combination of multiple serum metabolic biomarkers and <i>APOE</i> genotyping can significantly improve classification accuracy and potentially assist in making non-invasive, cost-effective diagnostic approach.

Journal of Alzheimer s DiseaseVol. 108(2)
Centre National de la Recherche Scientifique (FR), Cliniques Universitaires Saint-Luc (BE), European Union (BE), Université Libre de Bruxelles (BE), Inserm (FR), Université Côte d'Azur (FR), Centre Hospitalier Universitaire Vaudois (CH), Centre Hospitalier Universitaire de Lille (FR), Centre Hospitalier Universitaire de Nice (FR), Centre Hospitalier Universitaire de Besançon (FR), Hopitaux Civils de Colmar (FR), Centre Hospitalier Universitaire de Montpellier (FR), Assistance Publique – Hôpitaux de Paris (FR), University Hospital of Geneva (CH), Firalis (France) (FR), Centro San Giovanni di Dio Fatebenefratelli (IT), Institute for Neurosciences of Montpellier (FR), Gaziantep University (TR), Istanbul University (TR), Université de Strasbourg (FR)
European Commission, Ministero della Salute
Openalex Percentile: Top 23%
Metabolomics and Mass Spectrometry Studies
0.81
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.