arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.02554cs.LGstat.ML
收藏

电子健康记录的自适应预测定时

Adaptive Prediction Timing for Electronic Health Records

University of Cambridge(剑桥大学)

Jacob Deasy, Ari Ercole, Pietro Liò

摘要:

在现实场景中,多变量时间序列在逐个案例的时间尺度上演变。这在医学中尤其明显,临床事件的发生率因病房、患者和应用而异。越来越复杂的模型已被证明可以有效地预测患者的结果,但未能使粒度适应这些固有的时间分辨率。因此,我们引入了一种新的,更现实的,方法来生成患者的预后预测在自适应率的基础上的不确定性积累贝叶斯循环模型。我们使用一个递归神经网络(RNN)和贝叶斯嵌入层与一个新的聚合方法来证明自适应预测时间。当事件密集或模型确定事件潜在表示时,我们的模型预测频率更高,而当读数稀疏或模型不确定时,预测频率较低。在患者入院后48小时,我们的模型与静态窗口模型相比具有相同的性能,同时生成特定于患者和事件的预测时间,从而在患者住院的关键前12小时内提高预测性能。

英文摘要:

In realistic scenarios, multivariate timeseries evolve over case-by-case time-scales. This is particularly clear in medicine, where the rate of clinical events varies by ward, patient, and application. Increasingly complex models have been shown to effectively predict patient outcomes, but have failed to adapt granularity to these inherent temporal resolutions. As such, we introduce a novel, more realistic, approach to generating patient outcome predictions at an adaptive rate based on uncertainty accumulation in Bayesian recurrent models. We use a Recurrent Neural Network (RNN) and a Bayesian embedding layer with a new aggregation method to demonstrate adaptive prediction timing. Our model predicts more frequently when events are dense or the model is certain of event latent representations, and less frequently when readings are sparse or the model is uncertain. At 48 hours after patient admission, our model achieves equal performance compared to its static-windowed counterparts, while generating patient- and event-specific prediction timings that lead to improved predictive performance over the crucial first 12 hours of the patient stay.

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。

↑