Application of individual brain connectome in chronic ischemia: mapping symptoms before and after reperfusion

Abstract

How brain functions in the distorted ischemic state before and after reperfusion is unclear. It is also uncertain whether there are any indicators within ischemic brain that could predict surgical outcomes. To alleviate these issues, we applied individual brain connectome in chronic steno-occlusive vasculopathy (CSOV) to map both ischemic symptoms and their postbypass changes. A total of 499 bypasses in 455 CSOV patients were collected and followed up for 47.8 ± 20.5 months. Using multimodal parcellation with connectivity-based and pathological distortion-independent approach, areal MR features of brain connectome were generated with three measurements of functional connectivity (FC), structural connectivity, and PageRank centrality at the single-subject level. Thirty-three machine-learning models were then trained with clinical and areal MR features to obtain acceptable classifiers for both ischemic symptoms and their postbypass changes, among which, 11 were deemed acceptable (AUC > 0.7). Notably, the FC feature-based model for long-term neurological outcomes performed very well (AUC > 0.8). Finally, a Shapley additive explanations plot was adopted to extract important individual features in acceptable models to generate “fingerprints” of brain connectome. This study not only establishes brain connectomic fingerprint databases for brain ischemia with distortion, but also provides informative insights for how brain functions before and after reperfusion.

Keywords

brain ischemia / cerebral revascularization / machine learning / neural networks

References

1	M Fujimura, T Tominaga, S Kuroda, et al. 2021 Japanese guidelines for the management of moyamoya disease: guidelines from the Research Committee on Moyamoya Disease and Japan Stroke Society. Neurol Med Chir (Tokyo). 2022;62(4):165-170.
2	BE Grüter, L Tosic, S Voglis, et al. Trends in literature on cerebral bypass surgery: a systematic review. Cerebrovasc Dis. 2022;51(1):102-113.
3	NR Khan, T Elarjani, AM Jamshidi, et al. Direct bypass surgery for moyamoya and steno-occlusive vasculopathy: clinical outcomes, intraoperative blood flow analysis, long-term follow-up, and long-term bypass patency in a single surgeon case series of 162 procedures. World Neurosurg. 2022;168:e500-e517.
4	M Ihara, Y Yamamoto, Y Hattori, et al. Moyamoya disease: diagnosis and interventions. Lancet Neurol. 2022;21(8):747-758.
5	CJ Rice, SM Cho, A Taqui, et al. Early versus delayed extracranial-intracranial bypass surgery in symptomatic atherosclerotic occlusion. Neurosurgery. 2019;85(5):656-663.
6	WN van Mook, RJ Rennenberg, GW Schurink, et al. Cerebral hyperperfusion syndrome. Lancet Neurol. 2005;4(12):877-888.
7	VN Nguyen, M Motiwala, T Elarjani, et al. Direct, indirect, and combined extracranial-to-intracranial bypass for adult moyamoya disease: an updated systematic review and meta-analysis. Stroke. 2022;53(12):3572-3582.
8	CH Pang, SU Lee, Y Lee, et al. Prediction of hemorrhagic cerebral hyperperfusion syndrome after direct bypass surgery in adult nonhemorrhagic moyamoya disease: combining quantitative parameters on RAPID perfusion CT with clinically related factors. J Neurosurg. 2023;138(3):683-692.
9	J Lu, Y Zhao, L Ma, et al. Predictors and clinical features of transient neurological events after combined bypass revascularization for moyamoya disease. Clin Neurol Neurosurg. 2019;186:105505.
10	M Teo, S Furtado, OF Kaneko, et al. Validation and application for the berlin grading system of moyamoya disease in adult patients. Neurosurgery. 2020;86(2):203-212.
11	MD Fox. Mapping symptoms to brain networks with the human connectome. N Engl J Med. 2018;379(23):2237-2245.
12	W Li, Y Tang, L Peng, Z Wang, S Hu, X Gao. The reconfiguration pattern of individual brain metabolic connectome for Parkinson's disease identification. MedComm. 2023;4(4):e305.
13	MF Glasser, TS Coalson, EC Robinson, et al. A multi-modal parcellation of human cerebral cortex. Nature. 2016;536(7615):171-178.
14	S Doyen, P Nicholas, A Poologaindran, et al. Connectivity-based parcellation of normal and anatomically distorted human cerebral cortex. Hum Brain Mapp. 2022;43(4):1358-1369.
15	O Tanglay, IM Young, NB Dadario, et al. Eigenvector PageRank difference as a measure to reveal topological characteristics of the brain connectome for neurosurgery. J Neurooncol. 2022;157(1):49-61.
16	DC Comstock, MJ Hove, R Balasubramaniam. Sensorimotor synchronization with auditory and visual modalities: behavioral and neural differences. Front Comput Neurosci. 2018;12:53.
17	MD Greicius, B Krasnow, AL Reiss, V Menon. Functional connectivity in the resting brain: a network analysis of the default mode hypothesis. Proc Nat Acad Sci USA. 2003;100(1):253-258.
18	M Velo, G Grasso, M Fujimura, et al. Moyamoya vasculopathy: cause, clinical manifestations, neuroradiologic features, and surgical management. World Neurosurg. 2022;159:409-425.
19	P Karzmark, PD Zeifert, TE Bell-Stephens, GK Steinberg, LJ Dorfman. Neurocognitive impairment in adults with moyamoya disease without stroke. Neurosurgery. 2012;70(3):634-638.
20	H Jiang, W Ni, B Xu, et al. Outcome in adult patients with hemorrhagic moyamoya disease after combined extracranial-intracranial bypass. J Neurosurg. 2014;121(5):1048-1055.
21	Y Lei, YJ Li, QH Guo, et al. Postoperative executive function in adult moyamoya disease: a preliminary study of its functional anatomy and behavioral correlates. J Neurosurg. 2017;126(2):527-536.
22	PB Gorelick, A Scuteri, SE Black, et al. Vascular contributions to cognitive impairment and dementia: a statement for healthcare professionals from the american heart association/american stroke association. Stroke. 2011;42(9):2672-2713.
23	E Garyfallidis, M Brett, B Amirbekian, et al. Dipy, a library for the analysis of diffusion MRI data. Front Neuroinform. 2014;8:8.
24	T Chen, C Guestrin, XGBoost: a Scalable Tree Boosting System. presented at: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016; San Francisco, California, USA.
25	Y Behzadi, K Restom, J Liau, TT Liu. A component based noise correction method (CompCor) for BOLD and perfusion based fMRI. Neuroimage. 2007;37(1):90-101.
26	SM Lundberg, S-I Lee, A unified approach to interpreting model predictions. presented at: Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017; Long Beach, California, USA.