Background

Alcohol screening and brief intervention (SBI) is used to decrease alcohol consumption, health care costs, and injury recidivism in trauma patients. Despite SBI being mandated for trauma centers, various concerns have led many centers to conduct SBI only on patients with a detectable blood alcohol concentration (BAC). We sought to determine the predictive nature of BAC on hazardous drinking behavior.

Study design

Adult trauma patients were included if they received an SBI before discharge. SBI was administered using a computerized alcohol screening and intervention (CASI) system with the Alcohol Use Disorder Identification Test (AUDIT). Data regarding demographics, injuries, and BAC were prospectively collected. Multivariate analyses were performed to identify independent predictors of hazardous drinking behavior.

Results

Data were complete for 1,340 patients, with a mean age of 43 years (SD 20 years). Sixty-eight percent were male, 33% had detectable BAC, and 19% had hazardous drinking behavior. Multivariate analysis identified age (odds ratio [OR] 0.97 per year), male sex (OR 3.1), BAC (OR 1.009 per mg/dL), detectable BAC (OR 3.9), and legal intoxication (OR 7.8) as independent predictors of hazardous drinking behavior. Asian/Pacific Islander ethnicity was a significant negative predictor (OR 0.53) compared with white. Thirty-eight percent of patients with hazardous drinking behavior had no detectable BAC.

Conclusions

Younger age, male sex, and higher BAC are early predictors of hazardous drinking behavior in adult trauma patients. Asian/Pacific Islander patients are half as likely to report hazardous drinking behavior compared with white patients. More than one-third of patients with hazardous drinking behavior do not have detectable BAC on admission and are not receiving interventions in centers that screen solely based on BAC.

Early prediction of whether a liver allograft will be utilized for transplantation may allow better resource deployment during donor management and improve organ allocation. The national donor management goals (DMG) registry contains critical care data collected during donor management. We developed a machine learning model to predict transplantation of a liver graft based on data from the DMG registry.

Methods

Several machine learning classifiers were trained to predict transplantation of a liver graft. We utilized 127 variables available in the DMG dataset. We included data from potential deceased organ donors between April 2012 and January 2019. The outcome was defined as liver recovery for transplantation in the operating room. The prediction was made based on data available 12-18 h after the time of authorization for transplantation. The data were randomly separated into training (60%), validation (20%), and test sets (20%). We compared the performance of our models to the Liver Discard Risk Index.

Results

Of 13 629 donors in the dataset, 9255 (68%) livers were recovered and transplanted, 1519 recovered but used for research or discarded, 2855 were not recovered. The optimized gradient boosting machine classifier achieved an area under the curve of the receiver operator characteristic of 0.84 on the test set, outperforming all other classifiers.

Conclusions

This model predicts successful liver recovery for transplantation in the operating room, using data available early during donor management. It performs favorably when compared to existing models. It may provide real-time decision support during organ donor management and transplant logistics.