Objective: To develop predictive criteria for successful weaning from mechanical assistance to ventilation based upon simple clinical tests using discriminant analyses and neural network systems. Design: Retrospective development of predictive criteria and subsequent prospective testing of the same. Setting: Medical intensive care unit of a 300-bed teaching veterans administration hospital. Patients: Twenty-five ventilator-dependent elderly patients with acute respiratory failure. Interventions: Routine measurements of negative inspiratory force (NIF), tidal values (VT), minute ventilation (VE), respiratory rate (RR), vital capacity (FVC), and maximum voluntary ventilation (MVV), followed by weaning trial. Success or failure in 21 efforts analyzed by linear and quadratic discriminant model and neural network formulas to develop prediction criteria. The criteria so developed were tested for predictive power prospectively in nine trials in six patients. The analyses thus obtained predicted the success or failure of weaning within 9O-lOO% accuracy. Conclusion: Use of quadratic discriminant and neural network analyses could be useful in developing accurate predictive criteria for successful weaning based upon simple bedside measurements.
Ashutosh, K.; Lee, Hyungkeun; Mohan, Chilukuri; Ranka, Sanjay; Mehrotra, Kishan; and Alexander, C., "Prediction Criteria for Successful Weaning from Respiratory Support: Statistical and Connectionist Analyses" (1991). Electrical Engineering and Computer Science Technical Reports. Paper 115.