Brachial artery peak velocity variation to predict fluid responsiveness in mechanically ventilated patients

INTRODUCTION Although several parameters have been proposed to predict the hemodynamic response to fluid expansion in critically ill patients, most of them are invasive or require the use of special monitoring devices. The aim of this study is to determine whether noninvasive evaluation of respiratory variation of brachial artery peak velocity flow measured using Doppler ultrasound could predict fluid responsiveness in mechanically ventilated patients. METHODS We conducted a prospective clinical research in a 17-bed multidisciplinary ICU and included 38 mechanically ventilated patients for whom fluid administration was planned due to the presence of acute circulatory failure. Volume expansion (VE) was performed with 500 mL of a synthetic colloid. Patients were classified as responders if stroke volume index (SVi) increased >or= 15% after VE. The respiratory variation in Vpeakbrach (DeltaVpeakbrach) was calculated as the difference between maximum and minimum values of Vpeakbrach over a single respiratory cycle, divided by the mean of the two values and expressed as a percentage. Radial arterial pressure variation (DeltaPPrad) and stroke volume variation measured using the FloTrac/Vigileo system (DeltaSVVigileo), were also calculated. RESULTS VE increased SVi by >or= 15% in 19 patients (responders). At baseline, DeltaVpeakbrach, DeltaPPrad and DeltaSVVigileo were significantly higher in responder than nonresponder patients [14 vs 8%; 18 vs. 5%; 13 vs 8%; P < 0.0001, respectively). A DeltaVpeakbrach value >10% predicted fluid responsiveness with a sensitivity of 74% and a specificity of 95%. A DeltaPPrad value >10% and a DeltaSVVigileo >11% predicted volume responsiveness with a sensitivity of 95% and 79%, and a specificity of 95% and 89%, respectively. CONCLUSIONS Respiratory variations in brachial artery peak velocity could be a feasible tool for the noninvasive assessment of fluid responsiveness in patients with mechanical ventilatory support and acute circulatory failure. TRIAL REGISTRATION ClinicalTrials.gov ID: NCT00890071.

Prediction of postpartum depression using multilayer perceptrons and pruning.

OBJECTIVE. The main goal of this paper is to obtain a classification model based on feed-forward multilayer perceptrons in order to improve postpartum depression prediction during the 32 weeks after childbirth with a high sensitivity and specificity and to develop a tool to be integrated in a decision support system for clinicians. MATERIALS AND METHODS. Multilayer perceptrons were trained on data from 1397 women who had just given birth, from seven Spanish general hospitals, including clinical, environmental and genetic variables. A prospective cohort study was made just after delivery, at 8 weeks and at 32 weeks after delivery. The models were evaluated with the geometric mean of accuracies using a hold-out strategy. RESULTS. Multilayer perceptrons showed good performance (high sensitivity and specificity) as predictive models for postpartum depression. CONCLUSIONS. The use of these models in a decision support system can be clinically evaluated in future work. The analysis of the models by pruning leads to a qualitative interpretation of the influence of each variable in the interest of clinical protocols.