A neural network for prediction of risk of nosocomial infection at intensive care units: a didactic preliminary model

ABSTRACT Objective: To propose a preliminary artificial intelligence model, based on artificial neural networks, for predicting the risk of nosocomial infection at intensive care units. Methods: An artificial neural network is designed that employs supervised learning. The generation of the datasets was based on data derived from the Japanese Nosocomial Infection Surveillance system. It is studied how the Java Neural Network Simulator learns to categorize these patients to predict their risk of nosocomial infection. The simulations are performed with several backpropagation learning algorithms and with several groups of parameters, comparing their results through the sum of the squared errors and mean errors per pattern. Results: The backpropagation with momentum algorithm showed better performance than the backpropagation algorithm. The performance improved with the xor. README file parameter values compared to the default parameters. There were no failures in the categorization of the patients into their risk of nosocomial infection. Conclusion: While this model is still based on a synthetic dataset, the excellent performance observed with a small number of patterns suggests that using higher numbers of variables and network layers to analyze larger volumes of data can create powerful artificial neural networks, potentially capable of precisely anticipating nosocomial infection at intensive care units. Using a real database during the simulations has the potential to realize the predictive ability of this model.

摘要：
研究目的：提出一种基于人工神经网络（artificial neural network）的初步人工智能模型，用于预测重症监护病房（intensive care units）内的医院获得性感染（nosocomial infection）风险。
方法：设计了一种采用监督学习（supervised learning）的人工神经网络。本数据集的生成源自日本医院感染监测系统（Japanese Nosocomial Infection Surveillance system）的采集数据。本研究探究了Java神经网络模拟器（Java Neural Network Simulator）如何通过学习对患者进行分类，以预测其医院获得性感染风险。本研究采用多种反向传播（backpropagation）学习算法与多组参数开展仿真实验，并通过均方误差（sum of the squared errors）与单模式平均误差（mean errors per pattern）对实验结果进行对比。
结果：带动量项的反向传播算法的性能优于普通反向传播算法。相较于默认参数，采用README文件中配置的参数（含异或（xor）相关设置）时，模型性能得到提升。所有患者的医院获得性感染风险分类均未出现失误。
结论：尽管本模型仍基于合成数据集，但在少量样本下展现出的优异性能表明，通过增加变量数量与网络层数以处理更大规模的数据，可构建出功能强大的人工神经网络，有望精准预测重症监护病房内的医院获得性感染风险。在仿真实验中采用真实数据库，有望进一步实现该模型的预测能力。