Clinical pathway variance prediction using artificial neural network for acute decompensated heart failure clinical pathway

摘要: Patients in modern healthcare demand superior quality. Clinical pathways are introduced as the main tools to manage this A clinical pathway is a task-oriented care plan that specifies steps be taken for patient care. It follows course according specific problem. During execution, variance or deviation from specified could occur, and may endanger patient’s life. In paper, proposed framework artificial neural networks (ANNs) predictions presented. This research method predicts occur during Acute Decompensated Heart Failure Pathway. By using Artificial Neural Network, 3 variances (Dialysis, PCI, Cardiac Catherization) predicted 55 input. The results show with Levenberg-Marquadt training algorithm 55-27-27-1 architecture achieve best prediction rate, an average accuracy of 87.4425% dataset 85.255% test dataset.