Traumatic Brain Injury (TBI) poses a significant global public health challenge, contributing to high morbidity and mortality rates and placing a substantial economic burden on healthcare systems worldwide. The diagnosis and prognosis of TBI relies on a combination of clinical and imaging data often acquired using a Computed Tomography (CT) scanner. Addressing the multifaceted challenges posed by TBI requires innovative, data-driven approaches, for this complex condition. As such, we provide a summary of the state-of-the-art Machine Learning (ML) and Deep Learning (DL) techniques applied to clinical and images in TBI, with a particular focus on mild TBI (mTBI). We explore the rich spectrum of ML and DL techniques used and highlight their impact in TBI . We categorize ML and DL methods by TBI severity and showcase their application in mTBI and moderate-to-severe TBI scenarios. Finally, we emphasize the role of ML and DL in mTBI diagnosis, where conventional methods often fall short, and comment on the potential of CT-based ML applications in TBI. This review may serve as a source of inspiration for future research endeavours aimed at improving the diagnosis and prognosis of TBI.

创伤性脑损伤（TBI）是一个全球公共卫生挑战，对医疗系统造成巨大负担，诊断和预测TBI依赖于临床和影像数据以及机器学习和深度学习技术的应用。这篇综述聚焦于应用机器学习和深度学习技术解决轻度TBI的诊断问题，探索了不同技术在不同严重程度的TBI中的应用，并强调了机器学习和深度学习在轻度TBI诊断方面的潜力。

机器学习在创伤性脑损伤诊断和预后中的应用：以轻度脑损伤和CT成像为焦点