Information Center, Academy of Military Medical Sciences, Beijing, People's Republic of China.
Medical Service Department, General Hospital of Xinjiang Military Region, Urumchi, People's Republic of China.
BMC Med Inform Decis Mak. 2020 Jul 9;20(Suppl 3):120. doi: 10.1186/s12911-020-1111-6.
Although clinical guidelines provide the best practice for medical activities, there are some limitations in using clinical guidelines to assistant decision-making in practical application, such as long update cycle and low compliance of doctors with the guidelines. Driven by data of actual cases, process mining technology provides the possibility to remedy these shortcomings of clinical guidelines.
We propose a clinical decision support method using predictive process monitoring, which could be complementary with clinical guidelines, to assist medical staff with thrombolytic therapy decision-making for stroke patients. Firstly, we construct a labeled data set of 1191 cases to show whether each case actually need thrombolytic therapy, and whether it conform to the clinical guidelines. After prefix extraction and filtering the control flow of completed cases, the sequences with data flow are encoded, and corresponding prediction models are trained.
Compared with the labeled results, the average accuracy of our prediction models for intravenous thrombolysis and arterial thrombolysis on the test set are 0.96 and 0.91, and AUC are 0.93 and 0.85 respectively. Compared with the recommendation of clinical guidelines, the accuracy, recall and AUC of our predictive models are higher.
The performance and feasibility of this method are verified by taking thrombolytic decision-making of patients with ischemic stroke as an example. When the clinical guidelines are not applicable, doctors could be provided with assistant decision-making by referring to similar historical cases using predictive process monitoring.
尽管临床指南为医疗活动提供了最佳实践，但在实际应用中，使用临床指南辅助决策仍存在一些局限性，例如更新周期长和医生对指南的遵从性低。受实际案例数据的驱动，流程挖掘技术为弥补临床指南的这些缺点提供了可能性。
我们提出了一种使用预测性流程监测的临床决策支持方法，可以与临床指南互补，辅助医务人员对脑卒中患者进行溶栓治疗决策。首先，我们构建了一个包含 1191 例病例的标记数据集，以显示每个病例是否确实需要溶栓治疗，以及是否符合临床指南。在提取前缀并过滤已完成病例的控制流后，对具有数据流的序列进行编码，并训练相应的预测模型。
与标记结果相比，我们的预测模型对静脉溶栓和动脉溶栓在测试集上的平均准确率分别为 0.96 和 0.91，AUC 分别为 0.93 和 0.85。与临床指南的推荐相比，我们的预测模型具有更高的准确率、召回率和 AUC。
以缺血性脑卒中患者溶栓决策为例，验证了该方法的性能和可行性。当临床指南不适用时，医生可以通过参考预测性流程监测中的类似历史病例为其提供辅助决策。
