Division of Neurosurgery, Department of Surgery, Faculty of Medicine, Prince of Songkla University, Hat Yai, Songkhla, 90110, Thailand.
Division of Neurosurgery, Department of Surgery, Faculty of Medicine, Prince of Songkla University, Hat Yai, Songkhla, 90110, Thailand.
Chin J Traumatol. 2021 Nov;24(6):350-355. doi: 10.1016/j.cjtee.2021.06.003. Epub 2021 Jun 8.
Traumatic brain injury (TBI) generally causes mortality and disability, particularly in children. Machine learning (ML) is a computer algorithm, applied as a clinical prediction tool. The present study aims to assess the predictability of ML for the functional outcomes of pediatric TBI.
A retrospective cohort study was performed targeting children with TBI who were admitted to the trauma center of southern Thailand between January 2009 and July 2020. The patient was excluded if he/she (1) did not undergo a CT scan of the brain, (2) died within the first 24 h, (3) had unavailable complete medical records during admission, or (4) was unable to provide updated outcomes. Clinical and radiologic characteristics were collected such as vital signs, Glasgow coma scale score, and characteristics of intracranial injuries. The functional outcome was assessed using the King's Outcome Scale for Childhood Head Injury, which was thus dichotomized into favourable outcomes and unfavourable outcomes: good recovery and moderate disability were categorized as the former, whereas death, vegetative state, and severe disability were categorized as the latter. The prognostic factors were estimated using traditional binary logistic regression. By data splitting, 70% of data were used for training the ML models and the remaining 30% were used for testing the ML models. The supervised algorithms including support vector machines, neural networks, random forest, logistic regression, naive Bayes and k-nearest neighbor were performed for training of the ML models. Therefore, the ML models were tested for the predictive performances by the testing datasets.
There were 828 patients in the cohort. The median age was 72 months (interquartile range 104.7 months, range 2-179 months). Road traffic accident was the most common mechanism of injury, accounting for 68.7%. At hospital discharge, favourable outcomes were achieved in 97.0% of patients, while the mortality rate was 2.2%. Glasgow coma scale score, hypotension, pupillary light reflex, and subarachnoid haemorrhage were associated with TBI outcomes following traditional binary logistic regression; hence, the 4 prognostic factors were used for building ML models and testing performance. The support vector machine model had the best performance for predicting pediatric TBI outcomes: sensitivity 0.95, specificity 0.60, positive predicted value 0.99, negative predictive value 1.0; accuracy 0.94, and area under the receiver operating characteristic curve 0.78.
The ML algorithms of the present study have a high sensitivity; therefore they have the potential to be screening tools for predicting functional outcomes and counselling prognosis in general practice of pediatric TBIs.
创伤性脑损伤（TBI）通常会导致死亡和残疾，尤其是在儿童中。机器学习（ML）是一种计算机算法，可用作临床预测工具。本研究旨在评估 ML 对儿科 TBI 功能结局的预测能力。
本研究为回顾性队列研究，纳入 2009 年 1 月至 2020 年 7 月期间在泰国南部创伤中心就诊的 TBI 患儿。如果患儿（1）未行颅脑 CT 检查，（2）伤后 24 h 内死亡，（3）入院期间无法获得完整的病历资料，或（4）无法提供最新结局，则将其排除。收集临床和影像学特征，如生命体征、格拉斯哥昏迷评分和颅内损伤特征。采用儿童头部创伤 Kings 结局量表评估功能结局，将结局分为有利结局和不利结局：良好恢复和中度残疾为有利结局，死亡、植物状态和重度残疾为不利结局。采用传统二项逻辑回归估计预后因素。通过数据分割，70%的数据用于训练 ML 模型，30%的数据用于测试 ML 模型。采用支持向量机、神经网络、随机森林、逻辑回归、朴素贝叶斯和 k-最近邻等有监督算法对 ML 模型进行训练。因此，通过测试数据集来测试 ML 模型的预测性能。
本研究纳入 828 例患儿。患儿的中位年龄为 72 个月（四分位距 104.7 个月，范围 2-179 个月）。道路交通伤是最常见的致伤机制，占 68.7%。出院时，97.0%的患儿结局良好，死亡率为 2.2%。格拉斯哥昏迷评分、低血压、瞳孔光反射和蛛网膜下腔出血与传统二项逻辑回归后的 TBI 结局相关，因此，选择这 4 个预后因素构建 ML 模型并测试性能。支持向量机模型在预测儿科 TBI 结局方面表现最佳：敏感度为 0.95，特异度为 0.60，阳性预测值为 0.99，阴性预测值为 1.0；准确率为 0.94，受试者工作特征曲线下面积为 0.78。
本研究的 ML 算法具有较高的敏感度，因此它们有可能成为儿科 TBI 功能结局预测和一般实践预后咨询的筛查工具。
