Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm
Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm
复制标题
DOI：
10.1016/s0140-6736(96)90609-1
复制
发表时间：
1996-04-27
期刊：
影响因子：
168.9
通讯作者：
Gant, V
中科院分区：
文献类型：
--
作者：
Dybowski, R;Weller, P;Gant, V
决定哪些病人需要接受重症监护，以及让他们住院多久是很困难的。一个灵活的基于计算机的数学模型，对重症监护医学的复杂性敏感，并能准确地预测预后，似乎是非常可取的。我们创建了一个人工神经网络（ANN），并通过遗传算法进行了优化、训练和评估，该网络在全身性炎症反应综合征和血流动力学休克的临床环境中的表现。从伦敦教学医院的4484名重症监护患者数据库中选择258名患者，随机分配到网络训练集（168）和测试集（90）。评估的结果是住院期间的死亡，并将神经网络的性能（通过受试者工作特征曲线和Brier评分）与逻辑回归模型的性能进行比较。结果人工神经网络性能随代数的增加而提高；表现最好的人工神经网络在7代后创建，预测结果比逻辑回归模型更准确（ROC曲线面积0.863 vs 0.753）。在这项研究中，人工神经网络特别适合模拟复杂的临床情况；我们认为这与它们固有的灵活性有关，它可以适应临床输入领域之间的相互作用。此外，我们还展示了第二种计算技术（遗传算法）在“调整”人工神经网络性能方面的价值。这些技术可能在个别重症监护病房实施；他们将产生的结果模型将对当地的做法敏感。对这种准确的临床结果模型的分析可以使临床医生对其临床实践中与患者结果最相关的要素有迄今为止未被认识到的洞察力。
Background Decisions about which patients to admit to intensive care and how long to keep them there are difficult. A flexible computer-based mathematical model which is sensitive to the complexity of intensive care medicine, and which accurately models prognosis, seems highly desirable.Methods We have created, optimised by genetic algorithms, trained, and evaluated the performance of an artificial neural network (ANN) in the clinical setting of systemic inflammatory response syndrome and haemodynamic shock. 258 patients were selected from an intensive care database of 4484 patients al a London teaching hospital and randomised to a network training set (168) and a test set (90). The outcome evaluated was death during that hospital admission and the performance of the neural net was compared (by receiver operating characteristic [ROC] curves and by Brier scores) with that of a logistic regression model.Findings Artificial neural network performance increased with successive generations; the best-performing ANN was created after 7 generations and predicted outcome more accurately than the logistic regression model (ROC curve area 0.863 vs 0.753).Interpretation In this study, ANNs have lent themselves particularly well to modelling a complex clinical situation; we suggest that this relates to their inherently flexible nature which accommodates interactions between the clinical input fields. In addition, we have demonstrated the value of a second computational technique (genetic algorithms) in ''tuning'' ANN performance. These techniques can potentially be implemented in individual intensive care units; the outcome models which they will generate will be sensitive to local practice. Analysis of such accurate clinical outcome models may empower clinicians with a hitherto unappreciated degree of insight into those elements of their clinical practice which are most relevant to their patients' outcome.