Evaluating the causal effect of tobacco smoking on white matter brain aging: a two‐sample Mendelian randomization analysis in UK Biobank

Mo, Chen; Wang, Jingtao; Ye, Zhenyao; Ke, Hongjie; Liu, Song; Hatch, Kathryn S.; Gao, Si; Magidson, Jessica F.; Chen, Chixiang; Mitchell, Braxton D.; Kochunov, Peter; Hong, L. Elliot; Ma, Tianzhou; Chen, Shuo

doi:10.1111/add.16088

Cited by 9 publications

(11 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the signal-to-noise ratio in BrainAGE is low, this may lead to some false positive results. Therefore, we included some non-IDPs that have been repeatedly identified in BrainAGE studies, such as diastolic blood pressure [ 13 , 40 , 41 ], systolic blood pressure [ 42 , 43 , 44 ], alcohol intake [ 45 , 46 , 47 ], a diabetes diagnosis [ 48 , 49 , 50 ], and smoking status [ 51 , 52 , 53 ], in the comparison to observe the model’s interpretability of these typical findings.…”

Section: Methodsmentioning

confidence: 99%

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Xiong

Lin

et al. 2023

Sensors

View full text Add to dashboard Cite

Machine learning (ML) has transformed neuroimaging research by enabling accurate predictions and feature extraction from large datasets. In this study, we investigate the application of six ML algorithms (Lasso, relevance vector regression, support vector regression, extreme gradient boosting, category boost, and multilayer perceptron) to predict brain age for middle-aged and older adults, which is a crucial area of research in neuroimaging. Despite the plethora of proposed ML models, there is no clear consensus on how to achieve better performance in brain age prediction for this population. Our study stands out by evaluating the impact of both ML algorithms and image modalities on brain age prediction performance using a large cohort of cognitively normal adults aged 44.6 to 82.3 years old (N = 27,842) with six image modalities. We found that the predictive performance of brain age is more reliant on the image modalities used than the ML algorithms employed. Specifically, our study highlights the superior performance of T1-weighted MRI and diffusion-weighted imaging and demonstrates that multi-modality-based brain age prediction significantly enhances performance compared to unimodality. Moreover, we identified Lasso as the most accurate ML algorithm for predicting brain age, achieving the lowest mean absolute error in both single-modality and multi-modality predictions. Additionally, Lasso also ranked highest in a comprehensive evaluation of the relationship between BrainAGE and the five frequently mentioned BrainAGE-related factors. Notably, our study also shows that ensemble learning outperforms Lasso when computational efficiency is not a concern. Overall, our study provides valuable insights into the development of accurate and reliable brain age prediction models for middle-aged and older adults, with significant implications for clinical practice and neuroimaging research. Our findings highlight the importance of image modality selection and emphasize Lasso as a promising ML algorithm for brain age prediction.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Xiong

Lin

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The WM BAG was calculated by subtracting individuals' chronological age from their predicted brain age. The age-dependent bias has been noted to distort clinical interpretation in many brain age prediction studies [46][47][48]. We used a simple linear regression model [49] to remove brain age prediction bias from WM BAG and evaluated the performance of our correction method by the MAE.…”

Section: Age Bias Corrected White Matter (Wm) Brain Age Gap (Bag)mentioning

confidence: 99%

“…We then applied the generalized inverse-variance weighted (gen-IVW) approach to estimate the causal effect of BP (i.e., SBP/DBP) on WM BAG using the previously selected valid IVs. The gen-IVW approach in MR analysis took the ratio of gene-outcome association and geneexposure association estimates and combined multiple independent IVs into an overall estimate to assess the causal effect of exposure on the outcome while controlling the impact from LD between pairs of genetic variants [48,53]. BH method was used to adjust for multiple comparisons in evaluating the causal effect of each BP on BAG.…”

Section: Estimating Causal Effect By Two-sample Mendelian Randomizati...mentioning

confidence: 99%

Elevated blood pressure accelerates white matter brain aging among late middle-aged women: a Mendelian Randomization study in the UK Biobank

Feng

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Elevated blood pressure (BP) is a modifiable risk factor associated with cognitive impairment and cerebrovascular diseases. However, the causal effect of BP on white matter (WM) brain aging remains unclear. Methods: In this study, we focused on N=219,968 non-pregnant, family-unrelated individuals of European ancestry who had genotype data and two non-null clinical BP measurements available (99,532 male and 120,436 female, mean age=56.55, including 16,901 participants with neuroimaging data available) collected from UK Biobank (UKB). We adopted a chronological age-adjusted brain age metric, Brain Age Gap (BAG), as the outcome variable to measure the brain aging status. As a first step, we established a machine learning model to compute BAG based on white matter microstructure integrity measured by fractional anisotropy (FA) derived from diffusion tensor imaging data in a training set of subjects without hypertension (N=7,728). We then performed a two-sample Mendelian Randomization (MR) analysis to estimate the causal effect of BP on WM BAG in the whole population and subgroups stratified by gender and age brackets using two non-overlapping data sets (N=20,3067 for the set with genotype and BP data but no FA data; and N=8,822 for the set with genotype, BP and FA data). The main MR method used was generalized inverse variance weighted (gen-IVW) with other MR methods also included as sensitivity analysis. Results: The hypertension group is on average 0.3098 years (95%CI=0.1313,0.4884; p <0.0001) older in WM brain age than the non-hypertension group of the same chronological age. Females are on average 0.8143 years (95% CI=0.6797 to 0.949; p <0.0001) younger in WM brain age than males of the same chronological age. The MR analyses showed an overall significant positive causal effect of diastolic blood pressure (DBP) on WM BAG, where every 10 mm Hg increase in DBP can lead to 0.371 years increase in brain age (CI: 0.034-0.709, p=0.0311). The stratified analysis by age and gender group found such significant causal effect of DBP on BAG to be most prominent among female women aged 50-59 (0.686 years/10mm Hg, CI: 0.054-1.318, p=0.0335) and aged 60-69 (0.962 years/10mm Hg, CI: 0.209-1.714, p=0.0122). Conclusion: Hypertension and genetic predisposition to higher BP can accelerate WM brain aging specifically targeting at late middle-aged women, providing insights on planning effective control of BP for women in this age group.

show abstract

“…The selection of a brain aging indicator is essential. Recent studies highlight the efficacy of advanced machine learning techniques applied to neuroimaging data, offering the age-adjusted BAG estimates with minimal predictive biases (16,17) proven to be linked to physical and brain health (9,(18)(19)(20)(21)(22). The single scalar metric BAG is a robust and easily interpretable outcome, simplifying the challenges of handling multiple variables and addressing dependencies typically encountered in complex multivariate brain imaging models (7,8,16).…”

Section: Introductionmentioning

confidence: 99%

Association between allostatic load and accelerated white matter brain aging: findings from the UK Biobank

Feng,

Ye,

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

White matter (WM) brain age, a neuroimaging-derived biomarker indicating WM microstructural changes, helps predict dementia and neurodegenerative disorder risks. The cumulative effect of chronic stress on WM brain aging remains unknown. In this study, we assessed cumulative stress using a multi-system composite allostatic load (AL) index based on inflammatory, anthropometric, respiratory, lipidemia, and glucose metabolism measures, and investigated its causal association with WM brain age gap (BAG), computed from diffusion tensor imaging data using a machine learning model, among 22 951 European ancestries aged 40 to 69 (51.40% women) from UK Biobank. Linear regression, Mendelian randomization, along with inverse probability weighting and doubly robust methods, were used to evaluate the impact of AL on WM BAG adjusting for age, sex, socioeconomic, and lifestyle behaviors. We found increasing one AL score unit significantly increased WM BAG by 0.29 years in association analysis and by 0.33 years in Mendelian randomization causal analysis. The age- and sex-stratified analysis showed consistent results among participants 45-54 and 55-64 years old, with no significant sex difference. This study demonstrated that higher chronic stress caused accelerated brain aging, highlighting the importance of stress management in reducing dementia and neurodegenerative disease risks.

show abstract

Evaluating the causal effect of tobacco smoking on white matter brain aging: a two‐sample Mendelian randomization analysis in UK Biobank

Cited by 9 publications

References 102 publications

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Elevated blood pressure accelerates white matter brain aging among late middle-aged women: a Mendelian Randomization study in the UK Biobank

Association between allostatic load and accelerated white matter brain aging: findings from the UK Biobank

Contact Info

Product

Resources

About