Pre-operative prediction of post-operative urinary retention in lumbar surgery: a prospective validation of machine learning model.

PURPOSE: Predicting urinary retention is difficult. The aim of this study is to prospectively validate a previously developed model using machine learning techniques. METHODS: Patients were recruited from pre-operative clinic. Prediction of urinary retention was completed pre-operatively by 4 individuals and compared to ground truth POUR outcomes. Inter-rater reliability was calculated with intercorrelation coefficient (2,1). RESULTS: 171 patients were included with age 63 ± 14 years, 58.5% (100/171) male, BMI 30.4 ± 5.9 kg/m2, American Society of Anesthesiologists class 2.6 ± 0.5, 1.7 ± 1.0 levels, 56% (96/171) fusions. The observed rate of POUR was 25.7%. The model's performance was found to be 0.663 (0.567-0.759). With a regression model probability cutoff of 0.24 and a neural network cutoff of 0.23, the following predictive power was achieved: specificity 90.6%, sensitivity 22.7%, negative predictive value 77.2%, positive predictive value 45.5%, and accuracy 73.1%. Intercorrelation coefficient for the regression aspect of the model was found to be 0.889 and intercorrelation coefficient for the neural network aspect of the model was found to be 0.874. CONCLUSIONS: This prospective study confirms performance of the prediction model for POUR developed with retrospective data, showing great correlation. This supports the use of machine learning techniques in the prediction of postoperative complications such as urinary retention.

The use of cangrelor in neurovascular interventions: a multicenter experience.

PURPOSE: Thromboembolic events represent the most common procedure-related complication associated with neurointerventions. Cangrelor is a potent, intravenous (IV), P2Y12-receptor antagonist with a rapid onset and offset presented as an alternative antiplatelet agent. We aim to evaluate the safety and effectiveness of IV cangrelor in neurovascular intervention. METHODS: This is a retrospective analysis of data from four cerebrovascular interventional centers. We identified patients who underwent acute neurovascular intervention and received cangrelor as part of their optimum care. Patients were divided into 2 groups: ischemic and aneurysm. Periprocedural thromboembolic events, hemorrhagic complications, and outcomes were analyzed. RESULTS: Sixty-six patients were included, 42 allocated into the ischemic group (IG), and 24 into aneurysm group (AG). The IG periprocedural symptomatic complication rate was 9.5%, represented by 3 postoperative intracranial hemorrhages and 1 retroperitoneal hematoma. At discharge, 47.6% had a favorable outcome and the mortality rate was 2.4%, related to clinical deterioration of a large infarct. In the AG, 4.2% had a periprocedural complication during or after cangrelor infusion, represented by an intracranial hemorrhage in an initially ruptured aneurysm. Favorable clinical outcome was seen in 56.2% and 87.7% of ruptured and unruptured aneurysms, respectively, upon discharge. CONCLUSIONS: Cangrelor may be a feasible alternative for patients requiring immediate intervention with the use of endoluminal devices. It allows the possibility for a secure transition to long-term ticagrelor and progression to surgery in the setting of unexpected complications.