Machine Learning of Diffusion Weighted Imaging for Prediction of Seizure Susceptibility Following Traumatic Brain Injury

Sharma, Akul; Garner, Rachael; Rocca, Marianna La; Alba, Celina; Lee, Yenlin; Yang, Karina; Brawer-Cohen, Maya; Duncan, Dominique

doi:10.23919/annsim52504.2021.9552121

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Greater number of samples: Our study encompassed a substantially larger cohort of subjects than previous investigations, with 48 subjects in our analysis. This sample size surpassed the participant numbers in aforementioned TBI studies, such as 39 subjects in (Sharma et al, 2021), 33 subjects in (Irimia et al, 2017), 25 rats in (Bao et al, 2011), 22 subjects in (Akbar et al, 2021), and 16 subjects in (Meng et al, 2010). Notably, our dataset only fell short in size when compared to a non-TBI study involving 94 subjects (Owen et al, 2021).…”

Section: Discussionmentioning

confidence: 95%

“…7(a). For example: SS (sagittal stratum) from EEG and structural MRI has been associated with PTS (Irimia et al, 2017; Sharma et al, 2021); FX/ST (fornix/stria terminalis) from dMRI has been associated with LPTS in humans (Akbar et al, 2021) and rats (Bao et al, 2011); and CGH (cingulum hippocampus) from dMRI has been associated with LPTS (Akbar et al, 2020) and TLE (Owen et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Advancing Post-Traumatic Seizure Classification and Biomarker Identification: Information Decomposition Based Multimodal Fusion and Explainable Machine Learning with Missing Neuroimaging Data

Akbar

Ruf

Singh

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Late post-traumatic seizure (LPTS) is a complication of traumatic brain injury (TBI), which can lead to a potentially lifelong condition of post-traumatic epilepsy (PTE). Currently, the patho-mechanism that induces epileptogenesis in TBI subjects is unclear. As such, the epilepsy community strives to identify which TBI subjects will develop epilepsy and find potential biomarkers. To that end, this study collects longitudinal multimodal data from TBI subjects at multiple participating institutes. A supervised, binary classification task is formed with data from the LPTS versus no LPTS subjects. Missing modalities in certain subjects is handled in two ways. First, we extend a graphical model based Bayesian estimator to directly classify subjects with missing modality, and second, we investigate standard imputation techniques. The multimodal information is then combined, following several fusion and dimensionality reduction techniques found in literature, and eventually fitted to a kernelor a tree-based classifier. For this fusion, we propose two new algorithms: recursive elimination of correlated components (RECC) which filters information based on correlation, and information decomposition and selective fusion (IDSF) which meaningfully recombines information from decomposed multimodal features. Based on the cross-validated area under the curve (AUC) score, we find the proposed IDSF algorithm provides the best performance. Finally, following statistical analyses of the frequently selected features, we recommend alterations in inferior temporal gyrus as a potential biomarker.

show abstract