Using machine learning models to identify severe subjective cognitive decline and related factors in nurses during the menopause transition: a pilot study

Menopause The Journal of The North American Menopause Society, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 14, 2025

This study aims to develop and validate a machine learning model for identifying individuals within the nursing population experiencing severe subjective cognitive decline (SCD) during menopause transition, along with their associated factors. A secondary analysis was performed using cross-sectional data from 1,264 nurses undergoing transition. The set randomly split into training (75%) validation sets (25%), Bortua algorithm employed feature selection. Seven models were constructed optimized. Model performance assessed area under receiver operating characteristic curve, accuracy, sensitivity, specificity, F1 score. Shapley Additive Explanations used elucidate weights characteristics of various factors SCD. average SCD score among in transition (5.38 ± 2.43). identified 13 significant Among seven models, support vector exhibited best overall performance, achieving an curve 0.846, accuracy 0.789, sensitivity 0.753, specificity 0.802, 0.658. two variables most strongly menopausal symptoms stage menopause. effectively identify related These findings offer valuable insights management health women

Language: Английский

Cardiorespiratory Fitness and Sleep, but not Physical Activity, are Associated with Functional Connectivity in Older Adults

Sports Medicine - Open, Journal Year: 2024, Volume and Issue: 10(1)

Published: Oct. 19, 2024

Abstract Background Aging results in changes resting state functional connectivity within key networks associated with cognition. Cardiovascular function, physical activity, sleep, and body composition may influence these age-related the brain. Better understanding associations help clarify mechanisms related to brain aging guide interventional strategies reduce changes. Methods In a large (n = 398) sample of healthy community dwelling older adults that were part larger trial, we conducted cross sectional analyses baseline data examine relationships between several modifiable behaviors cognition emotional regulation. Additionally, maximal aerobic capacity, quality assessed. Associations explored both through correlation best vs. worst group comparisons. Results Greater cardiovascular fitness, but not quantity daily was greater Default Mode ( p 0.008 r 0.142) Salience Networks 0.005, 0.152). sleep (greater efficiency fewer nighttime awakenings) also multiple including Mode, Executive Control, Networks. When population split into quartiles, highest fat displayed higher Dorsal Attentional Network compared lowest percentage 0.011; 95% CI − 0.0172 0.0023). Conclusion These findings confirm expand on previous work indicating that, adults, levels fitness better quality, total time, or lower are increased networks.

Language: Английский

Independent associations of sleep and physical activity with cognition are mediated by hippocampal microstructure in middle-aged and older adults

Neurobiology of Aging, Journal Year: 2024, Volume and Issue: 147, P. 22 - 31

Published: Dec. 5, 2024

Language: Английский