患者在急诊室参观预测:自适应的LSTM模型用于不断变化的数据分布

Nicolas Haxaire¹, Farah Mourad-Chehade¹, Alice Yalaoui¹

¹University of Technology of Troyes, Troyes, 10000, France.

Computer methods and programs in biomedicine

|November 11, 2025

概括

本研究介绍了一种适应性深度学习模型,用于紧急部门 (ED) 访问预测. 该模型在变化的条件下保持准确性,无需手动重新训练,改善资源配置.

科学领域:

医疗保健运营研究研究研究
人工智能在医学中的应用
时间序列预测时间序列预测

背景情况:

紧急部门 (ED) 过度拥挤是一个持续的医疗保健挑战.
准确的患者访问预测对于资源优化至关重要.
传统模型难以应对数据分布的突然变化,需要人工重新训练.

研究的目的:

为ED访问开发一个深度学习预测框架.
在不断变化的条件下确保预测准确性,无需人工干预.
为动态的医疗保健环境创建一个强大的系统.

主要方法:

提出了一种使用Seq2Seq LSTM架构的自适应预测方法.
集成的每序缩放 (PSS) 和持续学习 (CL) 适应性更新.
与LSTM,ARIMA和Prophet进行评估,使用不同阶段 (COVID前,COVID后,COVID后) 的历史ED访问数据.

主要成果:

与基线相比,自适应的LSTM显著减少了短期至中期 (1天,1周) 的预测误差.
实现一致的平均绝对缩放误差 (MASE) 值低于1.
通过不断调整新的数据分布而没有完全重新培训,证明了稳健性,在后COVID条件下超过其他模型.

结论:

适应性Seq2Seq LSTM框架为动态环境中的ED预测提供了强大的解决方案.
它提供了运营可行性,一旦数据分布稳定,它将超过Prophet和ARIMA.
该模型的增量自我调整能力非常适合在隐私和IT限制下实时部署医院.

关键词:

持续的学习持续的学习紧急服务部门紧急服务部门预测患者访问的情况.这是LSTM的LSTM.在per-sequences上进行缩放.

相关概念视频

01:18

Steps in Outbreak Investigation

476

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

476

01:14

Parametric Survival Analysis: Weibull and Exponential Methods

1.0K

Parametric survival analysis models survival data by assuming a specific probability distribution for the time until an event occurs. The Weibull and exponential distributions are two of the most commonly used methods in this context, due to their versatility and relatively straightforward application.
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...

1.0K

01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

228

Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...

228

01:30

Pulse rhythm

1.3K

Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...