Predictive Factors of Kinematics in Traumatic Brain Injury from Head Impacts Based on Statistical Interpretation

Zhan, Xianghao; Li, Yi‐Heng; Liu, Yuzhe; Domel, August G.; Alizadeh, Hossein Vahid; Zhou, Zhou; Cecchi, Nicholas J.; Raymond, Samuel; Tiernan, Stephen; Ruan, Jesse; Barbat, Saeed; Gevaert, Olivier; Zeineh, Michael; Grant, Gerald A.; Camarillo, David B.

doi:10.48550/arxiv.2102.05020

Cited by 1 publication

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we applied PCA to simplify our previously developed DLHM [27] and showed that the simplified models can accurately predict the MPS, MPSR and MPS×MPSR. Because of different impact conditions (e.g., helmeted or unhelmeted, head to head or punch), the head kinematics and the relationship between head kinematics and brain deformation varies largely across different impact datasets [33], [42]. As a result, the brain regions that often experience severe deformation also vary among the types of impacts.…”

Section: Discussionmentioning

confidence: 99%

“…In this study, to cover a broader range of head impacts, we included 3,161 impact data from four different impact sources: 1) 2,130 football-like impacts simulated by a finite element model of a Hybrid III anthropomorphic test device headform (ATD) (labeled as HM for head model) [26], [27]; 2) 302 college football impacts measured by the Stanford Instrumented Mouthguard (labeled as CF) [28]- [30]; 3) 457 mixed martial arts impacts measured by the Stanford Instrumented Mouthguard (labeled as MMA) [7], [31]; 4) 272 reconstructed impacts from the National Association for Stock Car Auto Racing (labeled as NASCAR) [32], [33].…”

Section: A Datasets: Head Kinematics and Brain Finite Element Modelmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts

Zhan¹,

Liu

Cecchi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Strain and strain rate are effective traumatic brain injury predictors. Kinematics-based models estimating these metrics suffer from significant different distributions of both kinematics and the injury metrics across head impact types. To address this, previous studies focus on the kinematics but not the injury metrics. We have previously shown the kinematic features vary largely across head impact types, resulting in different patterns of brain deformation. This study analyzes the spatial distribution of brain deformation and applies principal component analysis (PCA) to extract the representative patterns of injury metrics (maximum principal strain (MPS), MPS rate (MPSR) and MPS×MPSR) in four impact types (simulation, football, mixed martial arts and car crashes). Methods: We apply PCA to decompose the patterns of the injury metrics for all impacts in each impact type, and investigate the distributions among brain regions using the first principal component (PC1). Furthermore, we developed a deep learning head model (DLHM) to predict PC1 and then inverse-transform to predict for all brain elements. Results: PC1 explained > 80% variance on the datasets. Based on PC1 coefficients, the corpus callosum and midbrain exhibit high variance on all datasets. We found MPS×MPSR the most sensitive metric on which the top 5% of severe impacts further deviates from the mean and there is a higher variance among the severe impacts. Finally, the DLHM reached mean absolute errors of < 0.018 for MPS, < 3.7s −1 for MPSR and < 1.1s −1 for MPS×MPSR, much smaller than the injury thresholds. Conclusion: The brain injury metric in a dataset can be decomposed into mean components and PC1 with high explained variance. Significance: The brain dynamics decomposition enables better interpretation of the patterns in brain injury metrics and the sensitivity of brain injury metrics across impact types. The decomposition also reduces the dimensionality of DLHM.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Datasets: Head Kinematics and Brain Finite Element Modelmentioning

confidence: 99%

Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts

Zhan¹,

Liu

Cecchi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Predictive Factors of Kinematics in Traumatic Brain Injury from Head Impacts Based on Statistical Interpretation

Cited by 1 publication

References 58 publications

Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts

Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts

Contact Info

Product

Resources

About