The University of Arizona, AZ, USA.
Virginia Tech, VA, USA.
AMIA Annu Symp Proc. 2022 Feb 21;2021:900-909. eCollection 2021.
We developed a prognostic model for longer-term outcome prediction in traumatic brain injury (TBI) using an attention-based recurrent neural network (RNN). The model was trained on admission and time series data obtained from a multi-site, longitudinal, observational study of TBI patients. We included 110 clinical variables as model input and Glasgow Outcome Score Extended (GOSE) at six months after injury as the outcome variable. Designed to handle missing values in time series data, the RNN model was compared to an existing TBI prognostic model using 10-fold cross validation. The area under receiver operating characteristic curve (AUC) for the RNN model is 0.86 (95% CI 0.83-0.89) for binary outcomes, whereas the AUC of the comparison model is 0.69 (95% CI 0.67-0.71). We demonstrated that including time series data into prognostic models for TBI can boost the discriminative ability of prediction models with either binary or ordinal outcomes.
我们使用基于注意力的循环神经网络 (RNN) 为创伤性脑损伤 (TBI) 的长期预后预测开发了一个预测模型。该模型是在多地点、纵向、TBI 患者观察性研究中获得的入院和时间序列数据上进行训练的。我们将 110 个临床变量作为模型输入，并将损伤后 6 个月的格拉斯哥结局评分扩展 (GOSE) 作为结果变量。该 RNN 模型旨在处理时间序列数据中的缺失值，并用 10 折交叉验证法与现有的 TBI 预后模型进行了比较。RNN 模型的二项结局的接收者操作特征曲线下面积 (AUC) 为 0.86(95%置信区间 0.83-0.89)，而比较模型的 AUC 为 0.69(95%置信区间 0.67-0.71)。我们证明，将时间序列数据纳入 TBI 的预后模型可以提高预测模型的判别能力，无论是二项结局还是有序结局。
