Metabolomics-Based Machine Learning for Predicting Mortality: Unveiling Multisystem Impacts on Health.
Abstract
Reliable predictors of long-term all-cause mortality are needed for middle-aged and older populations. Previous metabolomics mortality studies have limitations: a low number of participants and metabolites measured, measurements mainly using nuclear magnetic spectroscopy, and the use only of conventional statistical methods. To overcome these challenges, we applied liquid chromatography-tandem mass spectrometry and measured >1000 metabolites in the METSIM study including 10,197 men. We applied the machine learning approach together with conventional statistical methods to identify metabolites associated with all-cause mortality. The three independent machine learning methods (logistic regression, XGBoost, and Welch's
The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.
Research summary
The paper is relevant to longevity research as it focuses on predicting all-cause mortality using metabolomics, which can provide insights into biological aging and healthspan. However, while the study employs advanced methodologies and a large sample size, its findings appear to be an incremental advance rather than a groundbreaking discovery that fundamentally alters our understanding of aging or longevity.
Author of this paper? Send a correction.