Commentary: Correction procedures in brain-age prediction

Lange, Ann-Marie G. de; Cole, James H.

doi:10.1016/j.nicl.2020.102229

Cited by 170 publications

(193 citation statements)

References 18 publications

Supporting

Mentioning

185

Contrasting

Order By: Relevance

“…Figures 4 , 5 show that although the DNN models exhibit the lowest correlation values ( R = 0.38 for cross-validation and R = 0.4 for the independent test), a systematic age underestimation in the age range 60−90 and overestimation in the age range 20−35 can be noted. This finding indicates that age bias correction techniques need to be further applied to achieve less biased models ( 52 , 53 ).…”

Section: Discussionmentioning

confidence: 99%

Brain Age Prediction With Morphological Features Using Deep Neural Networks: Results From Predictive Analytic Competition 2019

et al. 2021

View full text Add to dashboard Cite

Morphological changes in the brain over the lifespan have been successfully described by using structural magnetic resonance imaging (MRI) in conjunction with machine learning (ML) algorithms. International challenges and scientific initiatives to share open access imaging datasets also contributed significantly to the advance in brain structure characterization and brain age prediction methods. In this work, we present the results of the predictive model based on deep neural networks (DNN) proposed during the Predictive Analytic Competition 2019 for brain age prediction of 2638 healthy individuals. We used FreeSurfer software to extract some morphological descriptors from the raw MRI scans of the subjects collected from 17 sites. We compared the proposed DNN architecture with other ML algorithms commonly used in the literature (RF, SVR, Lasso). Our results highlight that the DNN models achieved the best performance with MAE = 4.6 on the hold-out test, outperforming the other ML strategies. We also propose a complete ML framework to perform a robust statistical evaluation of feature importance for the clinical interpretability of the results.

show abstract

Section: Discussionmentioning

confidence: 99%

Brain Age Prediction With Morphological Features Using Deep Neural Networks: Results From Predictive Analytic Competition 2019

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Finally, we tested the association between global brain aging and number of previous childbirths in the group of new participants, using a linear regression model with brain‐age delta as the dependent variable and number of childbirths as the independent variable. Chronological age was included as a covariate, adjusting for age‐bias in the brain‐age predictions as well as age‐dependence in number of childbirths (de Lange & Cole, 2020; Le et al, 2018). Note that the training set of 10,907 participants overlapping with the previous study showed a lower N relative to the original sample in (de Lange et al, 2019) due to variation in exclusion criteria (listed in Section 2.1; Sample charecteristics ).…”

Section: Methodsmentioning

confidence: 99%

The maternal brain: Region‐specific patterns of brain aging are traceable decades after childbirth

Lange

Barth

Kaufmann

et al. 2020

Human Brain Mapping

View full text Add to dashboard Cite

Pregnancy involves maternal brain adaptations, but little is known about how parity influences women's brain aging trajectories later in life. In this study, we replicated previous findings showing less apparent brain aging in women with a history of childbirths, and identified regional brain aging patterns linked to parity in 19,787 middleand older-aged women. Using novel applications of brain-age prediction methods, we found that a higher number of previous childbirths were linked to less apparent brain aging in striatal and limbic regions. The strongest effect was found in the accumbens-a key region in the mesolimbic reward system, which plays an important role in maternal behavior. While only prospective longitudinal studies would be conclusive, our findings indicate that subcortical brain modulations during pregnancy and postpartum may be traceable decades after childbirth.

show abstract

“…In line with recent brain-age studies [29,33,34,6,28], the XGBoost regressor model, which aging trajectories [18]. The delta estimates were corrected for chronological age using linear regression [36,37].…”

Section: Brain Age Predictionmentioning

confidence: 99%

Prominent health problems, socioeconomic deprivation, and higher brain age in lonely and isolated individuals: A population-based study

Lange¹,

Kaufmann²,

Ds³

et al. 2020

Preprint

View full text Add to dashboard Cite

Amidst the global COVID-19 pandemic, there is an urgent need for establishing knowledge about risk factors for adverse health outcomes associated with loneliness and social isolation. In this study, we show that self-perceived loneliness coincides with objective measures of social isolation as well as the personality trait neuroticism, and that these comorbidities contribute to differential associations with risk factors including depression, social deprivation, unhealthy lifestyle behaviors, cardiovascular risk, and aging of the brain. The findings contribute to identifying groups of individuals who may be vulnerable to loneliness and associated health problems, and emphasize the need for public-health initiatives addressing socioeconomic conditions as well as social, mental, and physical health to reduce the risk of loneliness and adverse health outcomes in the population.

show abstract

Commentary: Correction procedures in brain-age prediction

Cited by 170 publications

References 18 publications

Brain Age Prediction With Morphological Features Using Deep Neural Networks: Results From Predictive Analytic Competition 2019

Brain Age Prediction With Morphological Features Using Deep Neural Networks: Results From Predictive Analytic Competition 2019

The maternal brain: Region‐specific patterns of brain aging are traceable decades after childbirth

Prominent health problems, socioeconomic deprivation, and higher brain age in lonely and isolated individuals: A population-based study

Contact Info

Product

Resources

About