Universidad de Alcalá, Escuela Politécnica Superior, 28805, Madrid, Spain.
Leiden University Medical Center, Department of Public Health and Primary Care, 2333 ZA, Leiden, The Netherlands.
Comput Methods Programs Biomed. 2024 Nov;256:108363. doi: 10.1016/j.cmpb.2024.108363. Epub 2024 Aug 8.
Generative Deep Learning has emerged in recent years as a significant player in the Artificial Intelligence field. Synthesizing new data while maintaining the features of reality has revolutionized the field of Deep Learning, proving to be particularly useful in contexts where obtaining data is challenging. The objective of this study is to employ the DoppelGANger algorithm, a cutting-edge approach based on Generative Adversarial Networks for time series, to enhance patient admissions forecasting in a hospital Emergency Department.
We employed the DoppelGANger algorithm in a sequential methodology, conditioning generated time series with unique attributes to optimize data utilization. After confirming the successful creation of synthetic data with new attribute values, we adopted the Train-Synthetic-Test-Real framework to ensure the reliability of our synthetic data validation. We then augmented the original series with synthetic data to enhance the Prophet model's performance. This process was applied to two datasets derived from the original: one with four years of training followed by one year of testing, and another with three years of training and two years of testing.
The experimental results show that the generative model outperformed Prophet on the forecasting task, improving the SMAPE from 7.30 to 6.99 with the four-year training set, and from 22.84 to 7.41 for the three-year training set, all in daily aggregations. For the data replacement task, the Prophet SMAPE values decreased to 6.84 and 7.18 for four and three-year sets on the same aggregation. Additionally, data augmentation reduced the SMAPE to 6.79 for a one-year test set and achieved 8.56 for the two-year test set, surpassing the performance achieved by the same Prophet model when trained only on real data. Results for the remaining aggregations were consistent.
The findings of this study suggest that employing a generative algorithm to extend a training dataset can effectively enhance predictive models within the domain of Emergency Department admissions. The improvement can lead to more efficient resource allocation and patient management.
生成式深度学习近年来在人工智能领域崭露头角。它通过生成新数据并保持数据的真实性，彻底改变了深度学习领域，在获取数据具有挑战性的情况下尤其有用。本研究旨在运用 DoppelGANger 算法——一种基于生成对抗网络的时间序列前沿方法，增强医院急诊科的患者入院预测。
我们采用序贯方法，利用具有独特属性的生成时间序列对 DoppelGANger 算法进行条件设置，以优化数据利用。在确认成功生成具有新属性值的合成数据后，我们采用 Train-Synthetic-Test-Real 框架来确保合成数据验证的可靠性。然后，我们用合成数据扩充原始序列，以提高 Prophet 模型的性能。该过程应用于两个从原始数据衍生的数据集：一个数据集有四年的训练数据和一年的测试数据，另一个数据集有三年的训练数据和两年的测试数据。
实验结果表明，生成模型在预测任务中优于 Prophet 模型，在四年训练集的日汇总中，将 SMAPE 从 7.30 提高到 6.99，在三年训练集的日汇总中，将 SMAPE 从 22.84 提高到 7.41。对于数据替换任务，在相同的日汇总中，对于四年和三年的数据集， Prophet 的 SMAPE 值分别降至 6.84 和 7.18。此外，数据扩充将一年测试集的 SMAPE 降至 6.79，并将两年测试集的 SMAPE 提高到 8.56，超过了仅使用真实数据训练的相同 Prophet 模型的性能。其余汇总结果也一致。
本研究结果表明，在急诊科入院预测领域，使用生成算法扩展训练数据集可以有效地增强预测模型。这种改进可以实现更高效的资源分配和患者管理。
