Prognostic networks for unraveling the biological mechanisms of Sarcopenia

Publication date: Available online 21 August 2019Source: Mechanisms of Ageing and DevelopmentAuthor(s): Ana Cernea, Juan Luis Fernández-Martínez, Enrique Juan de Andrés-Galiana, Zulima Fernández-Muñiz, Juan Carlos Bermejo-Millo, Laura González-Blanco, Juan José Solano, Pedro Abizanda, Ana Coto-Montes, Beatriz CaballeroAbstractSarcopenia is an age-related multifactorial process that involved several biological mechanisms, whose specific contribution and interplay is still unknown. The present study proposes prognostic networks based on machine learning approaches to unravel the interplay among those biological mechanisms mainly involved in the development of Sarcopenia. After analyzing 114 biological and clinical variables in adults older than 70 years, and using all the biological prognostic networks detected by machine learning with accuracy higher than 82%, we designed a consensus classifier based on majority vote that improve the predictive accuracy of Sarcopenia up to 91%. Additionally, we applied logistic regression analysis to propose the interplay among the most discriminative biological variables of Sarcopenia: anthropometry, body composition, functional performance of lower limbs, systemic oxidative stress, presence of depression and medication for the digestive system based on proton-pump inhibitors. Our data also demonstrate that besides a loss of muscle mass, impairments on functional performance of lower limbs are more relevant for develop Sarcopenia than ...
Source: Mechanisms of Ageing and Development - Category: Geriatrics Source Type: research