Joshua Parreco

Risk factors and costs associated with nationwide nonelective readmission after trauma

BACKGROUND Most prior studies of readmission after trauma have been limited to single institutions, whereas multi-institutional studies have been limited to single states and an inability to distinguish between elective and nonelective readmissions. The purpose of this study was to identify the risk factors and costs associated with nonelective readmission after trauma across the United States. METHODS The Nationwide Readmission Database was queried for all patients with nonelective admissions in 2013 and 2014 with a primary diagnosis of trauma. Univariate and multivariate logistic regression identified risk factors for 30-day nonelective same- and different-hospital readmission. The diagnosis groups on readmission were evaluated, and the total cost of readmissions was calculated. RESULTS There were 1,180,144 patients admitted for trauma, the 30-day readmission rate was 9.4%, and 26.4% of readmissions occurred at a different hospital. The median readmission cost for patients readmitted to the same hospital was

Predicting central line-associated bloodstream infections and mortality using supervised machine learning

8,298 (interquartile range,

Risk factors for nonelective 30-day readmission in pediatric assault victims

4,899–

Hidden Costs of Hospitalization After Firearm Injury: National Analysis of Different Hospital Readmission

14,911), whereas the median readmission cost for patients readmitted to a different hospital was

Thirty-day readmissions following parathyroidectomy: Evidence from the National Readmissions Database, 2013–2014

8,568 (interquartile range,

Comparing industry compensation of cardiothoracic surgeons and interventional cardiologists

4,935–

Underestimation of Unplanned Readmission after Colorectal Surgery: A National Analysis

16,078; p < 0.01). Multivariate regression revealed that patients discharged against medical advice were at increased risk of readmission (odds ratio, 2.79; p < 0.01) and readmission to a different facility (odds ratio, 1.58; p < 0.01). Home health care was associated with a decreased risk of readmission to a different hospital (odds ratio, 0.74; p < 0.01). Septicemia and disseminated infections were the most common diagnoses on readmission (8.4%) and readmission to a different hospital (8.6%). CONCLUSIONS A significant portion of US readmissions occur at different hospitals with implications for continuity of care, quality metrics, cost, and resource allocation. Home health care reduces the likelihood of nonelective readmission to a different hospital. Infection was the most common reason for readmission, with ramifications for outcomes research and quality improvement. LEVEL OF EVIDENCE Care management/epidimeological, level IV.

Machine Learning Models for Prediction of Reinjury After Penetrating Trauma

Purpose: The purpose of this study was to compare machine learning techniques for predicting central line‐associated bloodstream infection (CLABSI). Materials and methods: The Multiparameter Intelligent Monitoring in Intensive Care III database was queried for all ICU admissions. The variables included six different severities of illness scores calculated on the first day of ICU admission with their components and comorbidities. The outcomes of interest were in‐hospital mortality, central line placement, and CLABSI. Predictive models were created for these outcomes using classifiers with different algorithms: logistic regression, gradient boosted trees, and deep learning. Results: There were 57,786 total hospital admissions and the mortality rate was 10.1%. There were 38.4% patients with a central line and the rate of CLABSI was 1.5%. The classifiers using deep learning performed with the highest AUC for mortality, 0.885 ± 0.010 (p < 0.01) and central line placement, 0.816 ± 0.006 (p < 0.01). The classifier using logistic regression for predicting CLABSI performed with an AUC of 0.722 ± 0.048 (p < 0.01). Conclusions: This study demonstrates models for identifying patients who will develop CLABSI. Early identification of these patients has implications for quality, cost, and outcome improvements. HIGHLIGHTSMachine learning has proven to be useful for developing prediction models for outcomes in intensive care unit patients.This study uses illness severity scores and comorbidities provided to train artificial intelligence classifiers.These classifiers were highly accurate for predicting central line‐associated bloodstream infections and mortality.Such predictive models can be incorporated into existing medical record systems to support clinical decision making.

PC056. Hidden Readmissions After Carotid Endarterectomy and Stenting: A National Analysis

PURPOSE Hospital readmission in trauma patients is associated with significant morbidity and increased healthcare costs. There is limited published data on early hospital readmission in pediatric trauma patients. As presently in healthcare outcomes and readmissions rates are increasingly used as hospital quality indicators, it is paramount to recognize risk factors for readmission. We sought to identify national readmission rates in pediatric assault victims and identify the most common readmission diagnoses among these patients. METHODS The Nationwide Readmission Database (NRD) for 2013 was queried for all patients under 18years of age with a non-elective admission with an E-code that is designed as assault using National Trauma Data Bank Standards. Multivariate logistic regression was implemented using 18 variables to determine the odds ratios (OR) for non-elective readmission within 30-days. RESULTS There were 4050 pediatric victims of assault and 92 (2.27%) died during the initial admission. Of the surviving patients 128 (3.23%) were readmitted within 30days. Of these readmitted patients 24 (18.75%) were readmitted to a different hospital and 31 (24.22%) were readmitted for repeated assault. The variables associated with the highest risk for non-elective readmission within 30-days were: length of stay (LOS) >7days (OR 3.028, p<0.01, 95% CI 1.67-5.50), psychoses (OR 3.719, p<0.01, 95% CI 1.70-8.17), and weight loss (OR 4.408, p<0.01, 95% CI 1.92-10.10). The most common readmission diagnosis groups were bipolar disorders (8.2%), post-operative, posttraumatic, or other device infections (6.2%), or major depressive disorders and other/unspecified psychoses (5.2%). CONCLUSIONS Readmission after pediatric assault represents a significant resource burden and almost a quarter of those patients are readmitted after a repeated assault. Understanding risk factors and reasons for readmission in pediatric trauma assault victims can improve discharge planning, family education, and outpatient support, thereby decreasing overall costs and resource burden. Psychoses, weight loss, and prolonged hospitalization are independent prognostic indicators of readmission in pediatric assault patients. LEVEL OF EVIDENCE Level IV - Prognostic and Epidemiological - Retrospective Study.

Hidden burden of venous thromboembolism after trauma: A national analysis

Objective: To compare the risk factors and costs associated with readmission after firearm injury nationally, including different hospitals. Background: No national studies capture readmission to different hospitals after firearm injury. Methods: The 2013 to 2014 Nationwide Readmissions Database was queried for patients admitted after firearm injury. Logistic regression identified risk factors for 30-day same and different hospital readmission. Cost was calculated. Survey weights were used for national estimates. Results: There were 45,462 patients admitted for firearm injury during the study period. The readmission rate was 7.6%, and among those, 16.8% were readmitted to a different hospital. Admission cost was