Dementia and Neurocognitive Disorders (대한치매학회지)

Korean Dementia Association (대한치매학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of East Asian Brain Age using Machine Learning Algorithms Trained With Community-based Healthy Brain MRI

  • Chanda Simfukwe (Department of Neurology, College of Medicine, Chung-Ang University) ;
  • Young Chul Youn (Department of Neurology, College of Medicine, Chung-Ang University)
  • Received : 2022.08.31
  • Accepted : 2022.10.31
  • Published : 2022.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Background and Purpose: Magnetic resonance imaging (MRI) helps with brain development analysis and disease diagnosis. Brain volumes measured from different ages using MRI provides useful information in clinical evaluation and research. Therefore, we trained machine learning models that predict the brain age gap of healthy subjects in the East Asian population using T1 brain MRI volume images. Methods: In total, 154 T1-weighted MRIs of healthy subjects (55-83 years of age) were collected from an East Asian community. The information of age, gender, and education level was collected for each participant. The MRIs of the participants were preprocessed using FreeSurfer(https://surfer.nmr.mgh.harvard.edu/) to collect the brain volume data. We trained the models using different supervised machine learning regression algorithms from the scikit-learn (https://scikit-learn.org/) library. Results: The trained models comprised 19 features that had been reduced from 55 brain volume labels. The algorithm BayesianRidge (BR) achieved a mean absolute error (MAE) and r squared (R2) of 3 and 0.3 years, respectively, in predicting the age of the new subjects compared to other regression methods. The results of feature importance analysis showed that the right pallidum, white matter hypointensities on T1-MRI scans, and left hippocampus comprise some of the essential features in predicting brain age. Conclusions: The MAE and R2 accuracies of the BR model predicting brain age gap in the East Asian population showed that the model could reduce the dimensionality of neuroimaging data to provide a meaningful biomarker for individual brain aging.

Keywords

Acknowledgement

We would like to thank the Department of Neurology at Chung-Ang University Hospital for providing the tools to make this research successful.

References

  1. Yeung WJ, Lee Y. Aging in East Asia: new findings on retirement, health, and well-being. J Gerontol B Psychol Sci Soc Sci 2022;77:589-591. https://doi.org/10.1093/geronb/gbab055
  2. Hou Y, Dan X, Babbar M, Wei Y, Hasselbalch SG, Croteau DL, et al. Ageing as a risk factor for neurodegenerative disease. Nat Rev Neurol 2019;15:565-581. https://doi.org/10.1038/s41582-019-0244-7
  3. Cristea M, Noja GG, Stefea P, Sala AL. The impact of population aging and public health support on EU labor markets. Int J Environ Res Public Health 2020;17:1439.
  4. Tocchio S, Kline-Fath B, Kanal E, Schmithorst VJ, Panigrahy A. MRI evaluation and safety in the developing brain. Semin Perinatol 2015;39:73-104. https://doi.org/10.1053/j.semperi.2015.01.002
  5. Anaturk M, Kaufmann T, Cole JH, Suri S, Griffanti L, Zsoldos E, et al. Prediction of brain age and cognitive age: quantifying brain and cognitive maintenance in aging. Hum Brain Mapp 2021;42:1626-1640. https://doi.org/10.1002/hbm.25316
  6. Lancaster J, Lorenz R, Leech R, Cole JH. Bayesian optimization for neuroimaging pre-processing in brain age classification and prediction. Front Aging Neurosci 2018;10:28.
  7. Hwang I, Yeon EK, Lee JY, Yoo RE, Kang KM, Yun TJ, et al. Prediction of brain age from routine T2-weighted spin-echo brain magnetic resonance images with a deep convolutional neural network. Neurobiol Aging 2021;105:78-85. https://doi.org/10.1016/j.neurobiolaging.2021.04.015
  8. Sarker IH. Machine learning: algorithms, real-world applications and research directions. SN Comput Sci 2021;2:160.
  9. Beheshti I, Ganaie MA, Paliwal V, Rastogi A, Razzak I, Tanveer M. Predicting brain age using machine learning algorithms: a comprehensive evaluation. IEEE J Biomed Health Inform 2022;26:1432-1440. https://doi.org/10.1109/JBHI.2021.3083187
  10. Pandis N. Linear regression. Am J Orthod Dentofacial Orthop 2016;149:431-434. https://doi.org/10.1016/j.ajodo.2015.11.019
  11. Martin-Guerrero JD, Camps-Valls G, Soria-Olivas E, Serrano-Lopez AJ, Perez-Ruixo JJ, Jimenez-Torres NV. Dosage individualization of erythropoietin using a profile-dependent support vector regression. IEEE Trans Biomed Eng 2003;50:1136-1142. https://doi.org/10.1109/TBME.2003.816084
  12. Li X, Li W, Xu Y. Human age prediction based on DNA methylation using a gradient boosting regressor. Genes (Basel) 2018;9:424.
  13. da Silva FA, Viana AP, Correa CC, Santos EA, de Oliveira JA, Andrade JD, et al. Bayesian ridge regression shows the best fit for SSR markers in Psidium guajava among Bayesian models. Sci Rep 2021;11:13639.
  14. Ly M, Yu GZ, Karim HT, Muppidi NR, Mizuno A, Klunk WE, et al. Improving brain age prediction models: incorporation of amyloid status in Alzheimer's disease. Neurobiol Aging 2020;87:44-48. https://doi.org/10.1016/j.neurobiolaging.2019.11.005
  15. Wang J, Knol MJ, Tiulpin A, Dubost F, de Bruijne M, Vernooij MW, et al. Gray matter age prediction as a biomarker for risk of dementia. Proc Natl Acad Sci U S A 2019;116:21213-21218. https://doi.org/10.1073/pnas.1902376116
  16. Paul H, Simon J, Gilles W, Thomas C. Brain age prediction of healthy subjects on anatomic MRI with deep learning: going beyond with an "explainable AI" mindset. bioRxiv 2018 Sep 10.
  17. Aycheh HM, Seong JK, Shin JH, Na DL, Kang B, Seo SW, et al. Biological brain age prediction using cortical thickness data: a large scale cohort study. Front Aging Neurosci 2018;10:252.
  18. Lidauer K, Pulli EP, Copeland A, Silver E, Kumpulainen V, Hashempour N, et al. Subcortical and hippocampal brain segmentation in 5-year-old children: validation of FSL-FIRST and FreeSurfer against manual segmentation. Eur J Neurosci 2022.56:4619-4641. https://doi.org/10.1111/ejn.15761
  19. Fujihara K, Takei Y. FreeSurfer as a platform for associating brain structure with function. Brain Nerve 2018.70:841-848.
  20. Gomez-Ramirez J, Fernandez-Blazquez MA, Gonzalez-Rosa JJ. Prediction of chronological age in healthy elderly subjects with machine learning from MRI brain segmentation and cortical parcellation. Brain Sci 2022;12:579.
  21. Hong J, Feng Z, Wang SH, Peet A, Zhang YD, Sun Y, et al. Brain age prediction of children using routine brain MR images via deep learning. Front Neurol 2020;11:584682.
  22. Cole JH, Franke K. Predicting age using neuroimaging: innovative brain ageing biomarkers. Trends Neurosci 2017;40:681-690.