Print  Close

Radiomics-informed Brain Age for Predicting Treatment Response of rTMS in Neurocognitive Disorder

Poster No:

106 

Submission Type:

Abstract Submission 

Authors:

Hanna LU1, Sandra Sau Man Chan1, Suk Ling Ma1, Arthur DP Mak2, Linda Chiu Wa Lam1

Institutions:

1The Chinese University of Hong Kong, Hong Kong, Hong Kong, 2University of Cambridge, London, United Kingdom

First Author:

Hanna LU  
The Chinese University of Hong Kong
Hong Kong, Hong Kong

Co-Author(s):

Sandra Sau Man Chan  
The Chinese University of Hong Kong
Hong Kong, Hong Kong
Suk Ling Ma  
The Chinese University of Hong Kong
Hong Kong, Hong Kong
Arthur DP Mak  
University of Cambridge
London, United Kingdom
Linda Chiu Wa Lam  
The Chinese University of Hong Kong
Hong Kong, Hong Kong

Introduction:

One major clinical challenge of repetitive transcranial magnetic stimulation (rTMS) is that the treatment responses to rTMS exhibited high individual variations. Anatomical factors that may contribute to the heterogeneity in rTMS effects on depression and cognition, and rTMS-induced neuroplastic changes, are less investigated.

Methods:

Fifty-five older patients (aged 65 years or over) with co-occurring depression and cognitive impairments were randomly assigned to receive either active or sham rTMS on left dorsolateral prefrontal cortex (DLPFC). Individual's brain age was calculated with morphometric features using support vector machine (SVM). Brain-predicted age difference (brain-PAD) was computed as the difference between estimated brain age and chronological age. The changes of motor threshold (MT) and brain-derived neurotrophic factor (BDNF) were used to evaluate the neuroplasticity.

Results:

The rTMS responders and remitters had younger brain age. Every additional year of brain-PAD at baseline decreased the odds of the relief of depressive symptoms by ~25.7% in responders (Odd ratio [OR] = 0.743, Nagelkerke R2 = 0.392, p = 0.045) and by ~39.5% in remitters (OR = 0.605, Nagelkerke R2 = 0.606, p = 0.022) at 3rd week in active rTMS group. Using brain-PAD as feature, responder-nonresponder classification accuracies of 85% (3rd week) and 84% (12th week), respectively were achieved.

Conclusions:

Pre-treatment brain age matrices by macro-level morphometric features in patients with neurocognitive disorders, may be relevant to inter-individual variability in treatment responses to rTMS treatment.

Brain Stimulation:

TMS 1

Disorders of the Nervous System:

Neurodegenerative/ Late Life (eg. Parkinson’s, Alzheimer’s)

Lifespan Development:

Aging

Neuroanatomy, Physiology, Metabolism and Neurotransmission:

Cortical Anatomy and Brain Mapping 2

Keywords:

Aging
Computational Neuroscience
Cortex
Morphometrics
Structures
Transcranial Magnetic Stimulation (TMS)

1|2Indicates the priority used for review
Supporting Image: Figure.jpg
   ·The differences of brain-PAD in responders and non-responders
 

Provide references using author date format

Polanía, R., Nitsche, M. A., & Ruff, C. C. (2018). Studying and modifying brain function with non-invasive brain stimulation. Nature neuroscience, 21(2), 174-187.
Lu, H., Chan, S. S. M., Ma, S., Lin, C., Mok, V. C. T., Shi, L., Wang, D., Mak, A. D. P., & Lam, L. C. W. (2022). Clinical and radiomic features for predicting the treatment response of repetitive transcranial magnetic stimulation in major neurocognitive disorder: Results from a randomized controlled trial. Human Brain Mapping, 43(18), 5579-5592.
de Lange, A. M. G., Anatürk, M., Rokicki, J., Han, L. K., Franke, K., Alnæs, D., Ebmeier, K. P., Draganski, B., Kaufmann, T., Westlye, L. T., Hahn, T., & Cole, J. H. (2022). Mind the gap: Performance metric evaluation in brain‐age prediction. Human Brain Mapping, 43(10), 3113-3129.