Determining the readiness of the patient for weaning from long-term mechanical ventilation with high degree of accuracy is a prerequisite for successful weaning attempt. A computer system for the determination of the moment for beginning the weaning process is proposed and realized as a program package WeaningMV. It is designed on the basis of four classification methods: stepwise discriminant analysis, stepwise logistic regression; intuitionistic fuzzy Voronoi diagrams and non-pulmonary weaning index, applied to 17 features (variables). The system is designed and preliminary tested on 151 patients with features in two classes "not ready for weaning" and "ready for weaning" and it has a high degree for sensitivity (0.99) and specificity (0.89). After the application of the system in the everyday physician's practice a set of 72 patients has been examined. For that set the sensitivity is 0.92 and the specificity 0.88. The system consults the medical team on the basis of objective processing of the information contained in the data and is suitable for use in the clinical practice as well as in the training of the respective specialists.
展开▼
