Center for Bionics, Korea Institute of Science and Technology, Seoul 02792, Korea.
School of Mechanical Engineering, Yonsei University, Seoul 03722, Korea.
Int J Environ Res Public Health. 2022 Feb 18;19(4):2349. doi: 10.3390/ijerph19042349.
Sepsis is a life-threatening condition with a high mortality rate. Early prediction and treatment are the most effective strategies for increasing survival rates. This paper proposes a neural architecture search (NAS) model to predict the onset of sepsis with a low computational cost and high search performance by applying a genetic algorithm (GA). The proposed model shares the weights of all possible connection nodes internally within the neural network. Externally, the search cost is reduced through the weight-sharing effect between the genotypes of the GA. A predictive analysis was performed using the Medical Information Mart for Intensive Care III (MIMIC-III), a medical time-series dataset, with the primary objective of predicting sepsis onset 3 h before occurrence. In addition, experiments were conducted under various prediction times (0-12 h) for comparison. The proposed model exhibited an area under the receiver operating characteristic curve (AUROC) score of 0.94 (95% CI: 0.92-0.96) for 3 h, which is 0.31-0.26 higher than the scores obtained using the Sequential Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Simplified Acute Physiology Score (SAPS) II scoring systems. Furthermore, the proposed model exhibited a 12% improvement in the AUROC value over a simple model based on the long short-term memory neural network. Additionally, it is not only optimally searchable for sepsis onset prediction, but also outperforms conventional models that use similar predictive purposes and datasets. Notably, it is sufficiently robust to shape changes in the input data and has less structural dependence.
脓毒症是一种具有高死亡率的危及生命的病症。早期预测和治疗是提高生存率的最有效策略。本文提出了一种神经架构搜索（NAS）模型，通过应用遗传算法（GA）以低计算成本和高搜索性能来预测脓毒症的发作。所提出的模型在神经网络内部共享所有可能的连接节点的权重。在外部，通过 GA 的基因型之间的权重共享效应降低了搜索成本。使用医疗时间序列数据集 Medical Information Mart for Intensive Care III（MIMIC-III）进行了预测分析，主要目的是预测 3 小时前发生的脓毒症发作。此外，还在各种预测时间（0-12 小时）下进行了实验以进行比较。所提出的模型在 3 小时时的接收者操作特征曲线（AUROC）评分为 0.94（95%CI：0.92-0.96），比使用序贯器官衰竭评估（SOFA）、快速 SOFA（qSOFA）和简化急性生理学评分（SAPS）II 评分系统获得的分数高 0.31-0.26。此外，与基于长短期记忆神经网络的简单模型相比，该模型的 AUROC 值提高了 12%。此外，它不仅可以针对脓毒症发作预测进行最佳搜索，而且还优于使用类似预测目的和数据集的传统模型。值得注意的是，它足够健壮，可以适应输入数据的形状变化，并且结构依赖性较小。
