Prematurity is a risk factor for the development of chronic adult diseases. Metabolomics can correlate the biochemical changes to a determined phenotype, obtaining real information about the state of health of a subject at that precise moment. Significative differences in the metabolomic profile of preterm newborns compared to those born at term have been already identified at birth. An observational case–control study was performed at the University Hospital of Siena. The aim was to evaluate and compare the metabolomic profiles of young adults born preterm to those born at term. Urinary samples were collected from 67 young adults (18–23 years old) born preterm (mean gestational age of 30 weeks, n = 49), and at term of pregnancy (mean gestational age of 38 weeks, n = 18). The urinary spectra of young adults born preterm was different from those born at term and resembled what was previously described at birth. The Random Forest algorithm gave the best classification (accuracy 82%) and indicated the following metabolites as responsible for the classification: citrate, CH2 creatinine, fumarate and hippurate. Urine spectra are promising tools for the early identification of neonates at risk of disease in adulthood and may provide insight into the pathogenesis and effects of fetal programming and infants’ outcomes.

Mitochondrial dysfunction is considered to be a major cause of primary mitochondrial myopathy in children and adults, as reduced mitochondrial respiration and morphological changes such as ragged red fibers (RRFs) are observed in muscle biopsies. However, it is also possible to hypothesize the role of mitochondrial dysfunction in aging muscle or in secondary mitochondrial dysfunctions. The recognition of true histological patterns of mitochondrial myopathy can avoid unnecessary genetic investigations. The aim of our study was to develop and validate machine-learning methods for RRF detection in light microscopy images of skeletal muscle tissue. We used image sets of 489 color images captured from representative areas of Gomori’s trichrome-stained tissue retrieved from light microscopy images at a 20× magnification. We compared the performance of random forest, gradient boosting machine, and support vector machine classifiers. Our results suggested that the advent of scanning technologies, combined with the development of machine-learning models for image classification, make neuromuscular disorders’ automated diagnostic systems a concrete possibility.