Advantages of Metabolomics-Based Multivariate Machine Learning to Predict Disease Severity: Example of COVID
International Journal of Molecular Sciences · 2024
DOI: 10.3390/ijms252212199 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Maryne Lepoittevin und 9 weiteren Autor:innen. Beteiligte Einrichtung: Inserm Unit Ischémie Reperfusion, Métabolisme et Inflammation Stérile en Transplantation (IRMETIST), UMR U1313, F-86073 Poitiers, France. Hauptthemen laut MEDLINE: COVID-19, Machine Learning, Metabolomics, Severity of Illness Index. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Université de Poitiers, Centre Hospitalier Universitaire de Poitiers, Conseil Régional de Nouvelle-Aquitaine.
Abstract (Originalsprache)
The COVID-19 outbreak caused saturations of hospitals, highlighting the importance of early patient triage to optimize resource prioritization. Herein, our objective was to test if high definition metabolomics, combined with ML, can improve prognostication and triage performance over standard clinical parameters using COVID infection as an example. Using high resolution mass spectrometry, we obtained metabolomics profiles of patients and combined them with clinical parameters to design machine learning (ML) algorithms predicting severity (herein determined as the need for mechanical ventilation during patient care). A total of 64 PCR-positive COVID patients at the Poitiers CHU were recruited. Clinical and metabolomics investigations were conducted 8 days after the onset of symptoms. We show that standard clinical parameters could predict severity with good performance (AUC of the ROC curve: 0.85), using SpO2, first respiratory rate, Horowitz quotient and age as the most important variables. However, the performance of the prediction was substantially improved by the use of metabolomics (AUC = 0.92). Our small-scale study demonstrates that metabolomics can improve the performance of diagnosis and prognosis algorithms, and thus be a key player in the future discovery of new biological signals. This technique is easily deployable in the clinic, and combined with machine learning, it can help design the mathematical models needed to advance towards personalized medicine.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Inserm Unit Ischémie Reperfusion, Métabolisme et Inflammation Stérile en Transplantation (IRMETIST), UMR U1313, F-86073 Poitiers, France.
- Faculty of Medicine and Pharmacy, University of Poitiers, F-86073 Poitiers, France.
- UMR CNRS 7285, Institut de Chimie des Milieux et Matériaux de Poitiers (IC2MP), University of Poitiers, 4 rue Michel-Brunet, TSA 51106, F-86073 Poitiers cedex 9, France.
- LITEC, CHU de Poitiers, Laboratoire de Virologie et Mycobactériologie, Université de Poitiers, 2 r Milétrie, F-86000 Poitiers, France.
- Intensive Care Medicine Department, CHU Poitiers, F-86021 Poitiers, France.
- Geriatric Medicine Department, CHU Poitiers, F-86021 Poitiers, France.
ORCID-Profile: Arnaud W Thille, Luc Pellerin, Thierry Hauet, Raphael Thuillier
Förderung
- Université de Poitiers
- Centre Hospitalier Universitaire de Poitiers
- Conseil Régional de Nouvelle-Aquitaine
- Région Nouvelle Aquitaine (AMI COVID grant)
- CHU de Poitiers
- University of Poitiers
Zitieren
APA
Lepoittevin, M., Remaury, Q. B., Lévêque, N., Thille, A. W., Brunet, T., Salaun, K., Catroux, M., Pellerin, L., Hauet, T., & Thuillier, R. (2024). Advantages of Metabolomics-Based Multivariate Machine Learning to Predict Disease Severity: Example of COVID. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms252212199
Vancouver
Lepoittevin M, Remaury QB, Lévêque N, Thille AW, Brunet T, Salaun K, et al. Advantages of Metabolomics-Based Multivariate Machine Learning to Predict Disease Severity: Example of COVID. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms252212199
BibTeX
@article{Lepoittevin2024,
author = {Lepoittevin, Maryne and Remaury, Quentin Blancart and Lévêque, Nicolas and Thille, Arnaud W and Brunet, Thomas and Salaun, Karine and Catroux, Mélanie and Pellerin, Luc and Hauet, Thierry and Thuillier, Raphael},
title = {Advantages of Metabolomics-Based Multivariate Machine Learning to Predict Disease Severity: Example of COVID},
journal = {International Journal of Molecular Sciences},
year = {2024},
doi = {10.3390/ijms252212199}
}
EUVIMED