Development and validation of machine learning models for the prediction of blunt cerebrovascular injury in children.

BACKGROUND: Blunt cerebrovascular injury (BCVI) is a rare finding in trauma patients. The previously validated BCVI (Denver and Memphis) prediction model in adult patients was shown to be inadequate as a screening option in injured children. We sought to improve the detection of BCVI by developing a prediction model specific to the pediatric population. METHODS: The National Trauma Databank (NTDB) was queried from 2007 to 2015. Test and training datasets of the total number of patients (885,100) with complete ICD data were used to build a random forest model predicting BCVI. All ICD features not used to define BCVI (2268) were included within the random forest model, a machine learning method. A random forest model of 1000 decision trees trying 7 variables at each node was applied to training data (50% of the dataset, 442,600 patients) and validated with test data in the remaining 50% of the dataset. In addition, Denver and Memphis model variables were re-validated and compared to our new model. RESULTS: A total of 885,100 pediatric patients were identified in the NTDB to have experienced blunt pediatric trauma, with 1,998 (0.2%) having a diagnosis of BCVI. Skull fractures (OR 1.004, 95% CI 1.003-1.004), extremity fractures (OR 1.001, 95% 1.0006-1.002), and vertebral injuries (OR 1.004, 95% CI 1.003-1.004) were associated with increased risk for BCVI. The BCVI prediction model identified 94.4% of BCVI patients and 76.1% of non-BCVI patients within the NTDB. This study identified ICD9/ICD10 codes with strong association to BCVI. The Denver and Memphis criteria were re-applied to NTDB data to compare validity and only correctly identified 13.4% of total BCVI patients and 99.1% of non BCVI patients. CONCLUSION: The prediction model developed in this study is able to better identify pediatric patients who should be screened with further imaging to identify BCVI. LEVEL OF EVIDENCE: Retrospective diagnostic study-level III evidence.

Evaluation of Pelvic Anastomosis by Endoscopic and Contrast Studies Prior to Ileostomy Closure: Are Both Necessary? A Single Institution Review.

Contrast enema is the gold standard technique for evaluating a pelvic anastomosis (PA) prior to ileostomy closure. With the increasing use of flexible endoscopic modalities, the need for contrast studies may be unnecessary. The objective of this study is to compare flexible endoscopy and contrast studies for anastomotic inspection prior to defunctioning stoma reversal. Patients with a protected PA undergoing ileostomy closure between July 2014 and June 2019 at our institution were retrospectively identified. Demographics and clinical outcomes in patients undergoing preoperative evaluation with endoscopic and/or contrast studies were analyzed. We identified 207 patients undergoing ileostomy closure. According to surgeon's preference, 91 patients underwent only flexible endoscopy (FE) and 100 patients underwent both endoscopic and contrast evaluation (FE + CE) prior to reversal. There was no significant difference in pelvic anastomotic leak (2.2% vs. 1%), anastomotic stricture (1.1% vs. 6%), pelvic abscess (2.2% vs. 3.0%), or postoperative anastomotic complications (4.4% vs. 9%) between groups FE and FE + CE (P > .05). Flexible endoscopy alone appears to be an acceptable technique for anastomotic evaluation prior to ileostomy closure. Further studies are needed to determine the effectiveness of different diagnostic modalities for pelvic anastomotic inspection.