Guay Samuel, Charlebois-Plante Camille, Vinet Sophie-Andrée, Bourassa Marie-Eve, De Beaumont Louis
University of Montreal, Montreal, Canada.
Centre de Recherche, Hôpital du Sacré-Cœur de Montréal, Montreal, Canada.
Neurotrauma Rep. 2025 Jan 31;6(1):136-147. doi: 10.1089/neur.2024.0094. eCollection 2025.
Brain age prediction algorithms using structural magnetic resonance imaging (MRI) estimate the biological age of the brain by comparing it to a normal aging trajectory, allowing for the identification of deviations that may indicate slower or accelerated biological aging. Traumatic brain injury (TBI) and sports-related concussion (SRC) have been associated with greater brain age gap (BAG) compared to healthy controls. In this study, we aimed to investigate BAG in athletes suffering from persistent postconcussion syndrome (PCS+) compared to PCS- athletes, and used SHapley Additive exPlanations (SHAP), an explainable artificial intelligence framework, to provide further details on which specific features drive the brain age predictions. Brain age was derived from T1-weighted MRI images in a cohort of 50 athletes (24 with PCS+) from 22 to 73 years old from the general population. The results revealed that athletes with PCS+ had a brain age approximately 5 years older than the PCS- athletes, with no clinical variable associated with it. Exploratory analyses also showed a greater brain age in athletes who self-reported five or more SRCs. Regarding SHAP, the third ventricle was found to be the most informative feature in the PCS+ group, while the superior temporal sulcus posterior area was more informative in the PCS- group. This study demonstrated the potential of using brain age and explainable artificial intelligence frameworks to study athletes with PCS. Further research is needed to explore the underlying mechanisms driving brain aging in this population and to identify potential biomarkers for early detection and intervention.
使用结构磁共振成像（MRI）的脑年龄预测算法通过将大脑与正常衰老轨迹进行比较来估计大脑的生物学年龄，从而能够识别可能表明生物学衰老减缓或加速的偏差。与健康对照组相比，创伤性脑损伤（TBI）和与运动相关的脑震荡（SRC）与更大的脑年龄差距（BAG）有关。在本研究中，我们旨在调查患有持续性脑震荡后综合征（PCS+）的运动员与PCS-运动员相比的BAG，并使用可解释人工智能框架SHapley Additive exPlanations（SHAP）来进一步详细说明哪些特定特征驱动脑年龄预测。脑年龄来自于一组年龄在22至73岁之间、来自普通人群的50名运动员（24名PCS+）的T1加权MRI图像。结果显示，PCS+运动员的脑年龄比PCS-运动员大约大5岁，且没有与之相关的临床变量。探索性分析还显示，自我报告有五次或更多次SRC的运动员脑年龄更大。关于SHAP，在PCS+组中，第三脑室被发现是最具信息性的特征，而在PCS-组中，颞上沟后部区域更具信息性。这项研究证明了使用脑年龄和可解释人工智能框架来研究患有PCS的运动员的潜力。需要进一步研究来探索该人群中驱动脑衰老的潜在机制，并识别用于早期检测和干预的潜在生物标志物。
