IMPORTANCE An intraoperative higher level of positive end-expiratory positive pressure (PEEP) with alveolar recruitment maneuvers improves respiratory function in obese patients undergoing surgery, but the effect on clinical outcomes is uncertain. OBJECTIVE To determine whether a higher level of PEEP with alveolar recruitment maneuvers decreases postoperative pulmonary complications in obese patients undergoing surgery compared with a lower level of PEEP. DESIGN, SETTING, AND PARTICIPANTS Randomized clinical trial of 2013 adults with body mass indices of 35 or greater and substantial risk for postoperative pulmonary complications who were undergoing noncardiac, nonneurological surgery under general anesthesia. The trial was conducted at 77 sites in 23 countries from July 2014-February 2018; final follow-up: May 2018. INTERVENTIONS Patients were randomized to the high level of PEEP group (n = 989), consisting of a PEEP level of 12 cm H 2 O with alveolar recruitment maneuvers (a stepwise increase of tidal volume and eventually PEEP) or to the low level of PEEP group (n = 987), consisting of a PEEP level of 4 cm H 2 O. All patients received volume-controlled ventilation with a tidal volume of 7 mL/kg of predicted body weight. MAIN OUTCOMES AND MEASURES The primary outcome was a composite of pulmonary complications within the first 5 postoperative days, including respiratory failure, acute respiratory distress syndrome, bronchospasm, new pulmonary infiltrates, pulmonary infection, aspiration pneumonitis, pleural effusion, atelectasis, cardiopulmonary edema, and pneumothorax. Among the 9 prespecified secondary outcomes, 3 were intraoperative complications, including hypoxemia (oxygen desaturation with SpO 2 Յ92% for >1 minute). RESULTS Among 2013 adults who were randomized, 1976 (98.2%) completed the trial (mean age, 48.8 years; 1381 [69.9%] women; 1778 [90.1%] underwent abdominal operations). In the intention-to-treat analysis, the primary outcome occurred in 211 of 989 patients (21.3%) in the high level of PEEP group compared with 233 of 987 patients (23.6%) in the low level of PEEP group (difference, −2.3% [95% CI, −5.9% to 1.4%]; risk ratio, 0.93 [95% CI, 0.83 to 1.04]; P = .23). Among the 9 prespecified secondary outcomes, 6 were not significantly different between the high and low level of PEEP groups, and 3 were significantly different, including fewer patients with hypoxemia (5.0% in the high level of PEEP group vs 13.6% in the low level of PEEP group; difference, −8.6% [95% CI, −11.1% to 6.1%]; P < .001). CONCLUSIONS AND RELEVANCE Among obese patients undergoing surgery under general anesthesia, an intraoperative mechanical ventilation strategy with a higher level of PEEP and alveolar recruitment maneuvers, compared with a strategy with a lower level of PEEP, did not reduce postoperative pulmonary complications.

No abstract

Aim: To develop an Artificial Intelligence (AI) based Automated Machine Learning (AutoML) toolkit to aid decision-making for mechanical thrombectomy (MT) based on readily available patient variables that could predict functional outcome following MT. Methods: Datasets of 1097 patients from Systematic Evaluation of Patients Treated With Stroke Devices for Acute Ischemic Stroke (STRATIS) Registry and SWIFT PRIME Trial were retrospectively evaluated. Linear and non-linear models were built using an automated ML platform, DataRobot. We developed two stage models for predicting the outcome of the patient: Model 1 predicted survival, defined as an mRS score of 0-5 (alive) or 6 (dead). Model 2 predicted good/bad survivor, defined as an mRS score of 0-2 (good) or 3-5 (poor). Results: The primary outcome was the modified Rankin Scale (mRS) score at 90 days after stroke. Prediction of survival was 83% accurate (area under the curve [AUC] 0.7780). Prediction of good/poor survivor was 61% accurate (AUC 0.7061). A two-stage machine learning model has an improved 80% overall accuracy of prediction. Conclusion: The proposed AI-based AutoML toolkit evaluates various baseline clinical and radiological characteristics and predicts significant variations in treatment benefit between patients. With its improved prediction accuracy, the toolkit is clinically useful as it helps in distinguishing between individual patients who may experience benefit from Mechanical Thrombectomy treatment for acute ischaemic stroke from those who may not.

No abstract