RÉSUMÉ
The neurodevelopmental outcomes of preterm infants can be stratified based on the level of prematurity. We explored brain structural networks in extremely preterm (EP; < 28 weeks of gestation) and very-to-late (V-LP; ≥ 28 and < 37 weeks of gestation) preterm infants at term-equivalent age to predict 2-year neurodevelopmental outcomes. Using MRI and diffusion MRI on 62 EP and 131 V-LP infants, we built a multimodal feature set for volumetric and structural network analysis. We employed linear and nonlinear machine learning models to predict the Bayley Scales of Infant and Toddler Development, Third Edition (BSID-III) scores, assessing predictive accuracy and feature importance. Our findings revealed that models incorporating local connectivity features demonstrated high predictive performance for BSID-III subsets in preterm infants. Specifically, for cognitive scores in preterm (variance explained, 17%) and V-LP infants (variance explained, 17%), and for motor scores in EP infants (variance explained, 15%), models with local connectivity features outperformed others. Additionally, a model using only local connectivity features effectively predicted language scores in preterm infants (variance explained, 15%). This study underscores the value of multimodal feature sets, particularly local connectivity, in predicting neurodevelopmental outcomes, highlighting the utility of machine learning in understanding microstructural changes and their implications for early intervention.
Sujet(s)
Encéphale , Prématuré , Imagerie par résonance magnétique , Humains , Mâle , Encéphale/imagerie diagnostique , Encéphale/croissance et développement , Femelle , Nouveau-né , Imagerie par résonance magnétique/méthodes , Enfant d'âge préscolaire , Développement de l'enfant/physiologie , Apprentissage machine , Nourrisson , Âge gestationnel , Très grand prématuré/croissance et développementRÉSUMÉ
BACKGROUND AND PURPOSE: The association between physical activity and dementia has been shown in various observational studies. We aimed to determine the risk of dementia in the elderly with lower-body fractures. METHODS: We reconstructed a population-based matched cohort from the National Health Insurance Service-Senior Cohort data set that covers 511,953 recipients of medical insurance in South Korea. RESULTS: Overall 53,776 subjects with lower-body fractures were identified during 2006-2012, and triplicate control groups were matched randomly by sex, age, and years from the index date for each subject with a fracture. There were 3,573 subjects (6.6%) with and 7,987 subjects (4.9%) without lower-body fractures who developed dementia from 2008 up to 2015. Lower-body fractures were independently associated with a subsequent dementia diagnosis with a higher adjusted hazard ratio (aHR) (1.55, 95% confidence interval [CI]=1.49-1.62) compared with upper-body fractures (aHR=1.19, 95% CI=1.14-1.23). CONCLUSIONS: These results support the protective role of physical activity against dementia and highlight the importance of promoting fracture prevention in the elderly.