Pienaar Michael A, Sempa Joseph B, Luwes Nicolaas, George Elizabeth C, Brown Stephen C
Paediatric Critical Care Unit, Department of Paediatrics and Child Health, University of the Free State, Bloemfontein, South Africa.
Department of Biostatistics, Faculty of Health Sciences, University of the Free State, Bloemfontein, South Africa.
Front Pediatr. 2022 Nov 15;10:1008840. doi: 10.3389/fped.2022.1008840. eCollection 2022.
Failures in identification, resuscitation and appropriate referral have been identified as significant contributors to avoidable severity of illness and mortality in South African children. In this study, artificial neural network models were developed to predict a composite outcome of death before discharge from hospital or admission to the PICU. These models were compared to logistic regression and XGBoost models developed on the same data in cross-validation.
Prospective, analytical cohort study.
A single centre tertiary hospital in South Africa providing acute paediatric services.
Children, under the age of 13 years presenting to the Paediatric Referral Area for acute consultations.
Predictive models for a composite outcome of death before discharge from hospital or admission to the PICU.
None.
765 patients were included in the data set with 116 instances (15.2%) of the study outcome. Models were developed on three sets of features. Two derived from sequential floating feature selection (one inclusive, one parsimonious) and one from the Akaike information criterion to yield 9 models. All developed models demonstrated good discrimination on cross-validation with mean ROC AUCs greater than 0.8 and mean PRC AUCs greater than 0.53. ANN1, developed on the inclusive feature-et demonstrated the best discrimination with a ROC AUC of 0.84 and a PRC AUC of 0.64 Model calibration was variable, with most models demonstrating weak calibration. Decision curve analysis demonstrated that all models were superior to baseline strategies, with ANN1 demonstrating the highest net benefit.
All models demonstrated satisfactory performance, with the best performing model in cross-validation being an ANN model. Given the good performance of less complex models, however, these models should also be considered, given their advantage in ease of implementation in practice. An internal validation study is now being conducted to further assess performance with a view to external validation.
在南非儿童中，识别、复苏和适当转诊方面的失败已被确定为导致可避免的疾病严重程度和死亡率的重要因素。在本研究中，开发了人工神经网络模型来预测出院前死亡或入住儿科重症监护病房（PICU）的综合结局。将这些模型与在交叉验证中基于相同数据开发的逻辑回归模型和XGBoost模型进行比较。
前瞻性分析队列研究。
南非一家提供急性儿科服务的单中心三级医院。
13岁以下儿童，前往儿科转诊区进行急性会诊。
预测出院前死亡或入住PICU的综合结局的预测模型。
无。
数据集中纳入了765例患者，其中116例（15.2%）出现了研究结局。基于三组特征开发了模型。两组来自顺序浮动特征选择（一组包含所有特征，一组简约），一组来自赤池信息准则，共产生9个模型。所有开发的模型在交叉验证中均表现出良好的区分度，平均受试者工作特征曲线下面积（ROC AUC）大于0.8，平均精确召回率曲线下面积（PRC AUC）大于0.53。基于包含所有特征的特征集开发的ANN1表现出最佳的区分度，ROC AUC为0.84，PRC AUC为0.64。模型校准存在差异，大多数模型表现出较弱的校准。决策曲线分析表明，所有模型均优于基线策略，ANN1的净效益最高。
所有模型均表现出令人满意的性能，交叉验证中表现最佳的模型是一个人工神经网络模型。然而，鉴于较简单模型的良好性能，鉴于其在实际应用中易于实施的优势，也应考虑这些模型。目前正在进行一项内部验证研究，以进一步评估性能，以期进行外部验证。
