Chan C H, Chan E Y, Ng D K, Chow P Y, Kwok K L
Department of Paediatrics, Kwong Wah Hospital, Waterloo Road, Hong Kong SAR, China.
Singapore Med J. 2006 Nov;47(11):928-34.
Paediatric risk of mortality and paediatric index of mortality (PIM) are the commonly-used mortality prediction models (MPM) in children admitted to paediatric intensive care unit (PICU). The current study was undertaken to develop a better MPM using artificial neural network, a domain of artificial intelligence.
The purpose of this retrospective case series was to compare an artificial neural network (ANN) model and PIM with the observed mortality in a cohort of patients admitted to a five-bed PICU in a Hong Kong non-teaching general hospital. The patients were under the age of 17 years and admitted to our PICU from April 2001 to December 2004. Data were collected from each patient admitted to our PICU. All data were randomly allocated to either the training or validation set. The data from the training set were used to construct a series of ANN models. The data from the validation set were used to validate the ANN and PIM models. The accuracy of ANN models and PIM was assessed by area under the receiver operator characteristics (ROC) curve and calibration.
All data were randomly allocated to either the training (n=274) or validation set (n=273). Three ANN models were developed using the data from the training set, namely ANN8 (trained with variables required for PIM), ANN9 (trained with variables required for PIM and pre-ICU intubation) and ANN23 (trained with variables required for ANN9 and 14 principal ICU diagnoses). Three ANN models and PIM were used to predict mortality in the validation set. We found that PIM and ANN9 had a high ROC curve (PIM: 0.808, 95 percent confidence interval 0.552 to 1.000, ANN9: 0.957, 95 percent confidence interval 0.915 to 1.000), whereas ANN8 and ANN23 gave a suboptimal area under the ROC curve. ANN8 required only five variables for the calculation of risk, compared with eight for PIM.
The current study demonstrated the process of predictive mortality risk model development using ANN. Further multicentre studies are required to produce a representative ANN-based mortality prediction model for use in different PICUs.
儿科死亡风险和儿科死亡指数（PIM）是儿科重症监护病房（PICU）收治患儿常用的死亡预测模型（MPM）。本研究旨在利用人工智能领域的人工神经网络开发一种更好的MPM。
本回顾性病例系列研究旨在比较人工神经网络（ANN）模型和PIM与香港一家非教学型综合医院五张床位的PICU收治的一组患者的实际死亡率。患者年龄在17岁以下，于2001年4月至2004年12月入住我们的PICU。收集了入住我们PICU的每位患者的数据。所有数据被随机分配到训练集或验证集。训练集的数据用于构建一系列ANN模型。验证集的数据用于验证ANN和PIM模型。通过受试者操作特征（ROC）曲线下面积和校准来评估ANN模型和PIM的准确性。
所有数据被随机分配到训练集（n = 274）或验证集（n = 273）。利用训练集的数据开发了三个ANN模型，即ANN8（用PIM所需变量训练）、ANN9（用PIM和ICU插管前所需变量训练）和ANN23（用ANN9所需变量和14种主要ICU诊断训练）。三个ANN模型和PIM用于预测验证集的死亡率。我们发现PIM和ANN9的ROC曲线较高（PIM：0.808，95%置信区间0.552至1.000，ANN9：0.957，95%置信区间0.915至1.000），而ANN8和ANN23的ROC曲线下面积不理想。ANN8计算风险仅需五个变量，而PIM需要八个变量。
本研究展示了使用ANN开发预测死亡风险模型的过程。需要进一步开展多中心研究，以产生一个具有代表性的基于ANN的死亡预测模型，供不同的PICU使用。
