Objective

Electronic Medical Records (EMRs) contain temporal and heterogeneous doctor order information that can be used for treatment pattern discovery. Our objective is to identify “right patient”, “right drug”, “right dose”, “right route”, and “right time” from doctor order information.

Methods

We propose a fusion framework to extract typical treatment patterns based on multi-view similarity Network Fusion (SNF) method. The multi-view SNF method involves three similarity measures: content-view similarity, sequence-view similarity and duration-view similarity. An EMR dataset and two metrics were utilized to evaluate the performance and to extract typical treatment patterns.

Results

Experimental results on a real-world EMR dataset show that the multi-view similarity network fusion method outperforms all the single-view similarity measures and also outperforms the existing similarity measure methods. Furthermore, we extract and visualize typical treatment patterns by clustering analysis.

Conclusion

The extracted typical treatment patterns by combining doctor order content, sequence, and duration views can provide data-driven guidelines for artificial intelligence in medicine and help clinicians make better decisions in clinical practice.

中文翻译：

---

一个融合框架，可从电子病历中提取典型的治疗模式。

目的

电子病历（EMR）包含可用于治疗模式发现的时间和异构医生订单信息。我们的目标是从医生医嘱信息中识别“正确的患者”，“正确的药物”，“正确的剂量”，“正确的途径”和“正确的时间”。

方法

我们提出一种融合框架，以基于多视图相似性网络融合（SNF）方法提取典型的治疗模式。多视图SNF方法涉及三个相似性度量：内容视图相似性，序列视图相似性和持续时间视图相似性。使用EMR数据集和两个指标来评估性能并提取典型的治疗模式。

结果

在实际EMR数据集上的实验结果表明，多视图相似性网络融合方法优于所有单视图相似性度量，并且也优于现有的相似性度量方法。此外，我们通过聚类分析提取和可视化典型的治疗模式。

结论

通过结合医生订单内容，顺序和持续时间视图而提取的典型治疗模式，可以为医学中的人工智能提供数据驱动的指南，并帮助临床医生在临床实践中做出更好的决策。