arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.02308cs.LGcs.CY
收藏

电子健康档案的概念模型解释

Concept-based model explanations for Electronic Health Records

Google Research(谷歌研究院);Google Health(谷歌健康);DeepMind(深度思维)

Diana Mincu, Eric Loreaux, Shaobo Hou, Sebastien Baur, Ivan Protsyuk, Martin G Seneviratne, Anne Mottram, Nenad Tomasev, Alan Karthikesanlingam, Jessica Schrouff

摘要:

递归神经网络(RNN)通常用于电子健康记录(EHR)中不良结果的顺序建模,因为它们能够对过去的临床状态进行编码。与其他建模方法相比,这些深度的循环架构在许多任务中表现出更高的性能,从而激发了在临床环境中部署深度模型的兴趣。确保安全的模型部署和建立用户信任的关键要素之一是模型的可解释性。使用概念激活向量(TCAV)的测试最近被引入作为一种通过将高级概念与网络的梯度进行比较来提供人类可理解的解释的方式。虽然该技术在现实世界的成像应用中已经显示出有前途的结果,但它还没有被应用于结构化的时间输入。为了使应用程序的TCAV顺序预测的EHR,我们提出了一个扩展的方法,时间序列数据。我们评估所提出的方法上的一个开放的EHR基准从重症监护病房,以及合成数据,我们能够更好地隔离个人的影响。

英文摘要:

Recurrent Neural Networks (RNNs) are often used for sequential modeling of adverse outcomes in electronic health records (EHRs) due to their ability to encode past clinical states. These deep, recurrent architectures have displayed increased performance compared to other modeling approaches in a number of tasks, fueling the interest in deploying deep models in clinical settings. One of the key elements in ensuring safe model deployment and building user trust is model explainability. Testing with Concept Activation Vectors (TCAV) has recently been introduced as a way of providing human-understandable explanations by comparing high-level concepts to the network's gradients. While the technique has shown promising results in real-world imaging applications, it has not been applied to structured temporal inputs. To enable an application of TCAV to sequential predictions in the EHR, we propose an extension of the method to time series data. We evaluate the proposed approach on an open EHR benchmark from the intensive care unit, as well as synthetic data where we are able to better isolate individual effects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑