Li Keyi, Kim Mary S, Zhang Wenjin, Yang Sen, Sippel Genevieve J, Sarcevic Aleksandra, Burd Randall S, Marsic Ivan
Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, USA.
Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA.
J Biomed Inform. 2025 Jan;161:104767. doi: 10.1016/j.jbi.2024.104767. Epub 2024 Dec 31.
Trauma resuscitation is the initial evaluation and management of injured patients in the emergency department. This time-critical process requires the simultaneous pursuit of multiple resuscitation goals. Recognizing whether the required goal is being pursued can reduce errors in goal-related task performance and improve patient outcomes. The intention to pursue a goal can often be inferred from ongoing and completed treatment activities, but monitoring goal pursuit is cognitively demanding and prone to errors. We introduced an interpretable deep learning-based approach to aid decision making by automatically recognizing goal pursuit during trauma resuscitation.
We developed a predictive model to recognize the pursuit of two resuscitation goals: airway stabilization and circulatory support. We used event logs of 381 pediatric trauma resuscitations from August 2014 to November 2022 to train a neural network model with a dual-GRU structure that learns from both time-level and activity-type-level features. Our model makes predictions based on a sequence of activities and corresponding timestamps. To enhance the model and facilitate interpretation of predictions, we used the attention weights assigned by our model to represent the importance of features. These weights identified the critical time points and contributing activities during a goal pursuit.
Our model achieved an average area under the receiver operating characteristic curve (AUC) score of 0.84 for recognizing airway stabilization and 0.83 for recognizing circulatory support. The most contributing activities and timestamps were aligned with domain knowledge.
Our interpretable predictive model can recognize provider intention based on a limited number of treatment activities. The model outperformed existing predictive models for medical events in accuracy and in interpretability. Integrating our model into a decision-support system would automate the tracking of provider actions, optimizing workflow to ensure timely delivery of care.
创伤复苏是急诊科对受伤患者进行的初始评估和处理。这个时间紧迫的过程需要同时追求多个复苏目标。识别是否正在追求所需目标可以减少与目标相关任务执行中的错误，并改善患者预后。追求目标的意图通常可以从正在进行和已完成的治疗活动中推断出来，但监测目标追求在认知上要求很高且容易出错。我们引入了一种基于深度学习的可解释方法，通过在创伤复苏期间自动识别目标追求来辅助决策。
我们开发了一个预测模型，以识别对两个复苏目标的追求：气道稳定和循环支持。我们使用了2014年8月至2022年11月期间381例儿科创伤复苏的事件日志，来训练一个具有双门控循环单元（dual-GRU）结构的神经网络模型，该模型从时间级别和活动类型级别特征中学习。我们的模型基于一系列活动和相应的时间戳进行预测。为了增强模型并便于对预测进行解释，我们使用模型分配的注意力权重来表示特征的重要性。这些权重确定了目标追求过程中的关键时间点和有贡献的活动。
我们的模型在识别气道稳定方面，受试者操作特征曲线（AUC）得分的平均值为0.84，在识别循环支持方面为0.83。最有贡献的活动和时间戳与领域知识一致。
我们的可解释预测模型可以基于有限数量的治疗活动识别医疗人员的意图。该模型在准确性和可解释性方面优于现有的医疗事件预测模型。将我们的模型集成到决策支持系统中，将使医疗人员行动的跟踪自动化，优化工作流程以确保及时提供护理。
