Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.
Fitzwilliam College, University of Cambridge, Cambridge, UK.
Pediatr Res. 2019 Nov;86(5):641-645. doi: 10.1038/s41390-019-0510-9. Epub 2019 Jul 26.
Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.
A retrospective review of patients admitted to Cambridge University Hospital's Paediatric Intensive Care Unit between 2009 and 2013 with a TBI. The data for 14 admission serum parameters were recorded. Logistic regression and a support vector machine (SVM) were trained with these data against dichotimised outcomes from the recorded 6-month Glasgow Outcome Scale.
Ninety-four patients were identified. Admission levels of lactate, H+, and glucose were identified as being the most informative of 6-month outcomes. Four different models were produced. The SVM using just the three most informative parameters was the best able to predict favourable outcomes at 6 months (sensitivity = 80%, specificity = 99%).
Our results demonstrate the potential for highly accurate outcome prediction after severe paediatric TBI using admission laboratory data.
严重创伤性脑损伤（TBI）是儿童死亡的主要原因，但在入院时准确预测结果仍然极具挑战性。入院实验室结果是有前途的潜在预后数据来源，但尚未在儿科队列中广泛探索。在此，我们使用机器学习方法来综合分析 14 种不同的血清参数，并开发一个预后模型来预测严重 TBI 儿童的 6 个月结局。
回顾性分析 2009 年至 2013 年期间在剑桥大学医院儿科重症监护病房收治的 TBI 患儿。记录了 14 项入院时血清参数的数据。使用逻辑回归和支持向量机（SVM）根据记录的 6 个月格拉斯哥结局量表的二分结局对这些数据进行训练。
共确定了 94 名患者。入院时的乳酸、H+和葡萄糖水平被确定为最能反映 6 个月结局的信息。生成了四个不同的模型。仅使用三个最具信息量的参数的 SVM 最能预测 6 个月时的良好结局（敏感性=80%，特异性=99%）。
我们的结果表明，使用入院实验室数据可以对严重儿科 TBI 后的结果进行高度准确的预测。
