Department of Neuroscience, Division of Geriatric Medicine, UPRES EA 4638, UNAM, Angers University Hospital, Angers, France.
Department of Neuroscience, Division of Geriatric Medicine, UPRES EA 4638, UNAM, Angers University Hospital, Angers, France; Department of Medicine, Division of Geriatrics, Jewish General Hospital, McGill University, Montreal, Canada; Biomathics, Paris, France.
Eur J Intern Med. 2015 Sep;26(7):478-82. doi: 10.1016/j.ejim.2015.06.002. Epub 2015 Jul 2.
To examine performance criteria (i.e., sensitivity, specificity, positive predictive value [PPV], negative predictive value [NPV], likelihood ratios [LR], area under receiver operating characteristic curve [AUROC]) of a 10-item brief geriatric assessment (BGA) for the prediction of prolonged length hospital stay (LHS) in older patients hospitalized in acute care wards after an emergency department (ED) visit, using artificial neural networks (ANNs); and to describe the contribution of each BGA item to the predictive accuracy using the AUROC value.
A total of 993 geriatric ED users admitted to acute care wards were included in this prospective cohort study. Age >85years, gender male, polypharmacy, non use of formal and/or informal home-help services, history of falls, temporal disorientation, place of living, reasons and nature for ED admission, and use of psychoactive drugs composed the 10 items of BGA and were recorded at the ED admission. The prolonged LHS was defined as the top third of LHS. The ANNs were conducted using two feeds forward (multilayer perceptron [MLP] and modified MLP).
The best performance was reported with the modified MLP involving the 10 items (sensitivity=62.7%; specificity=96.6%; PPV=87.1; NPV=87.5; positive LR=18.2; AUC=90.5). In this model, presence of chronic conditions had the highest contributions (51.3%) in AUROC value.
The 10-item BGA appears to accurately predict prolonged LHS, using the ANN MLP method, showing the best criteria performance ever reported until now. Presence of chronic conditions was the main contributor for the predictive accuracy.
利用人工神经网络（ANNs）检验 10 项简要老年评估（BGA）在预测老年患者急诊就诊后入住急性护理病房时延长住院时间（LHS）方面的性能标准（即灵敏度、特异性、阳性预测值[PPV]、阴性预测值[NPV]、似然比[LR]、接受者操作特征曲线下面积[AUROC]）；并描述使用 AUROC 值，每个 BGA 项目对预测准确性的贡献。
这项前瞻性队列研究共纳入 993 名在急诊就诊后入住急性护理病房的老年 ED 使用者。年龄>85 岁、男性、多种药物治疗、未使用正式和/或非正式家庭援助服务、跌倒史、时间定向障碍、居住地点、ED 就诊的原因和性质、以及使用精神活性药物构成了 BGA 的 10 项内容，并在 ED 就诊时进行了记录。延长的 LHS 定义为 LHS 的前三分之一。ANNs 使用两种前馈（多层感知器[MLP]和改良 MLP）进行。
改良 MLP 涉及 10 项内容的报告显示出最佳性能（灵敏度=62.7%；特异性=96.6%；PPV=87.1%；NPV=87.5%；阳性 LR=18.2%；AUC=90.5%）。在该模型中，慢性疾病的存在在 AUROC 值中具有最高的贡献（51.3%）。
使用 ANN MLP 方法，10 项 BGA 似乎可以准确预测延长的 LHS，显示出迄今为止报道的最佳标准性能。慢性疾病的存在是预测准确性的主要因素。
