Kim Young-Tak, Kim Hakseung, Lee Choel-Hui, Yoon Byung C, Kim Jung Bin, Choi Young Hun, Cho Won-Sang, Oh Byung-Mo, Kim Dong-Joo
Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea.
Department of Radiology, Massachusetts General Hospital, Boston, MA, United States.
Front Pediatr. 2021 Nov 2;9:750272. doi: 10.3389/fped.2021.750272. eCollection 2021.
The inter- and intrarater variability of conventional computed tomography (CT) classification systems for evaluating the extent of ischemic-edematous insult following traumatic brain injury (TBI) may hinder the robustness of TBI prognostic models. This study aimed to employ fully automated quantitative densitometric CT parameters and a cutting-edge machine learning algorithm to construct a robust prognostic model for pediatric TBI. Fifty-eight pediatric patients with TBI who underwent brain CT were retrospectively analyzed. Intracranial densitometric information was derived from the supratentorial region as a distribution representing the proportion of Hounsfield units. Furthermore, a machine learning-based prognostic model based on gradient boosting (i.e., CatBoost) was constructed with leave-one-out cross-validation. At discharge, the outcome was assessed dichotomously with the Glasgow Outcome Scale (favorability: 1-3 vs. 4-5). In-hospital mortality, length of stay (>1 week), and need for surgery were further evaluated as alternative TBI outcome measures. Densitometric parameters indicating reduced brain density due to subtle global ischemic changes were significantly different among the TBI outcome groups, except for need for surgery. The skewed intracranial densitometry of the unfavorable outcome became more distinguishable in the follow-up CT within 48 h. The prognostic model augmented by intracranial densitometric information achieved adequate AUCs for various outcome measures [favorability = 0.83 (95% CI: 0.72-0.94), in-hospital mortality = 0.91 (95% CI: 0.82-1.00), length of stay = 0.83 (95% CI: 0.72-0.94), and need for surgery = 0.71 (95% CI: 0.56-0.86)], and this model showed enhanced performance compared to the conventional CRASH-CT model. Densitometric parameters indicative of global ischemic changes during the acute phase of TBI are predictive of a worse outcome in pediatric patients. The robustness and predictive capacity of conventional TBI prognostic models might be significantly enhanced by incorporating densitometric parameters and machine learning techniques.
用于评估创伤性脑损伤（TBI）后缺血性水肿损伤程度的传统计算机断层扫描（CT）分类系统在不同评估者之间以及同一评估者内部的变异性，可能会妨碍TBI预后模型的稳健性。本研究旨在采用全自动定量密度测定CT参数和前沿的机器学习算法，构建一个针对小儿TBI的稳健预后模型。对58例接受脑部CT检查的小儿TBI患者进行了回顾性分析。颅内密度测定信息来自幕上区域，以代表亨氏单位比例的分布形式呈现。此外，基于梯度提升（即CatBoost）构建了一个基于机器学习的预后模型，并采用留一法交叉验证。出院时，使用格拉斯哥预后量表对结果进行二分评估（良好：1 - 3分与4 - 5分）。住院死亡率、住院时间（>1周）和手术需求作为TBI的替代结果指标进行了进一步评估。除手术需求外，因轻微全脑缺血变化导致脑密度降低的密度测定参数在TBI结果组之间存在显著差异。在48小时内的随访CT中，不良结果组颅内密度测定的偏态分布变得更加明显。通过颅内密度测定信息增强的预后模型在各种结果指标上都获得了足够的曲线下面积（AUC）[良好 = 0.83（95%可信区间：0.72 - 0.94），住院死亡率 = 0.91（95%可信区间：0.82 - 1.00），住院时间 = 0.83（95%可信区间：0.72 - 0.94），手术需求 = 0.71（95%可信区间：..56 - 0.86）]，并且该模型与传统的CRASH - CT模型相比表现更优。TBI急性期指示全脑缺血变化的密度测定参数可预测小儿患者的不良预后。通过纳入密度测定参数和机器学习技术，传统TBI预后模型的稳健性和预测能力可能会显著提高。
