Introduction Accurate identification of venous thromboembolism (VTE) is critical to develop replicable epidemiological studies and rigorous predictions models. Traditionally, VTE studies have relied on international classification of diseases (ICD) codes which are inaccurate – leading to misclassification bias. Here, we developed ClotCatcher, a novel deep learning model that uses natural language processing to detect VTE from radiology reports. Methods Radiology reports to detect VTE were obtained from patients admitted to Emory University Hospital (EUH) and Grady Memorial Hospital (GMH). Data augmentation was performed using the Google PEGASUS paraphraser. This data was then used to fine-tune ClotCatcher, a novel deep learning model. ClotCatcher was validated on both the EUH dataset alone and GMH dataset alone. Results The dataset contained 1358 studies from EUH and 915 studies from GMH (n = 2273). The dataset contained 1506 ultrasound studies with 528 (35.1%) studies positive for VTE, and 767 CT studies with 91 (11.9%) positive for VTE. When validated on the EUH dataset, ClotCatcher performed best (AUC = 0.980) when trained on both EUH and GMH dataset without paraphrasing. When validated on the GMH dataset, ClotCatcher performed best (AUC = 0.995) when trained on both EUH and GMH dataset with paraphrasing. Conclusion ClotCatcher, a novel deep learning model with data augmentation rapidly and accurately adjudicated the presence of VTE from radiology reports. Applying ClotCatcher to large databases would allow for rapid and accurate adjudication of incident VTE. This would reduce misclassification bias and form the foundation for future studies to estimate individual risk for patient to develop incident VTE.

OBJECTIVES: Integrate a predictive model for massive transfusion protocol (MTP) activation and delivery in the electronic medical record (EMR) using prospectively gathered data; externally validate the model and assess the accuracy and precision of the model over time. BACKGROUND: The Emory model for predicting MTP using only four input variables was chosen to be integrated into our hospital's EMR to provide a real time clinical decision support tool. The continuous variable output allows for periodic re-calibration of the model to optimize sensitivity and specificity. METHODS: Prospectively collected data from level 1 and 2 trauma activations were used to input heart rate, systolic blood pressure, base excess (BE) and mechanism of injury into the EMR-integrated model for predicting MTP activation and delivery. MTP delivery was defined as: 6 units of packed red blood cells/6 hours (MTP1) or 10 units in 24 hours (MTP2). The probability of MTP was reported in the EMR. ROC and PR curves were constructed at 6, 12, and 20 months to assess the adequacy of the model. RESULTS: Data from 1162 patients were included. Areas under ROC for MTP activation, MTP1 and MTP2 delivery at 6, 12, and 20 months were 0.800, 0.821, and 0.831; 0.796, 0.861, and 0.879; and 0.809, 0.875, and 0.905 (all P < 0.001). The areas under the PR curves also improved, reaching values at 20 months of 0.371, 0.339, and 0.355 for MTP activation, MTP1 delivery, and MTP2 delivery. CONCLUSIONS: A predictive model for MTP activation and delivery was integrated into our EMR using prospectively collected data to externally validate the model. The model's performance improved over time. The ability to choose the cut-points of the ROC and PR curves due to the continuous variable output of probability of MTP allows one to optimize sensitivity or specificity.

Introduction: This study assessed whether Georgia Senate Bill 360, a statewide law passed in August 2010, that prohibits text messaging while driving, resulted in a decrease in this behavior among emergency medicine (EM) and general surgery (GS) healthcare providers. Methods: Using SurveyMonkey®, we created a web-based survey containing up to 28 multiple choice and free-text questions about driving behaviors. EM and GS healthcare providers at a southeastern medical school and its affiliate county hospital received an email inviting them to complete this survey in February 2011. We conducted all analyses in SPSS (version 19.0, Chicago, IL, 2010), using chi-squared tests and logistic regression models. The primary outcome of interest was a change in participant texting or emailing while driving after passage of the texting ban in Georgia. Results: Two hundred and twenty-six providers completed the entire survey (response rate 46.8%). Participants ranged in age from 23 to 71 years, with an average age of 38 (SD=10.2; median=35). Only three-quarters of providers (n=173, 76.6%) were aware of a texting ban in the state. Out of these, 60 providers (36.6%) reported never or rarely sending texts while driving (0 to 2 times per year), and 30 engaged in this behavior almost daily (18.9%). Almost two-thirds of this group reported no change in texting while driving following passage of the texting ban (n=110, 68%), while 53 respondents texted less (31.8%). Respondents younger than 40 were more than twice as likely to report no change in texting post-ban compared to older participants (OR=2.31, p=0.014). Providers who had been pulled over for speeding in the previous 5 years were about 2.5 times as likely to not change their texting-while-driving behavior following legislation passage compared to those without a history of police stops for speeding (OR=2.55, p=0.011). Each additional ticket received in the past 5 years for a moving violation lessened the odds of reporting a decrease in texting by 45%. (OR=0.553, p=0.007). Conclusion: EM and GS providers, particularly those who are younger, have received more tickets for moving violations, and with a history of police stops for speeding, exhibit limited compliance with distracted driving laws, despite first-hand exposure to the motor vehicle crashes caused by distracted driving.

Mass casualty events (MCE) are an infrequent occurrence to most daily healthcare systems however these incidents are the causation for new hospital preparedness and the development of coordinated emergency services. The broad support and operational plans outside the hospital include emergency medical services, local law enforcement, government agencies, and city officials. Modern-day hospital disaster preparedness goals include scheduled training for healthcare personnel to ensure effective and accurate triage for a high volume of injured patients. This MDT collaboration strengthens the emergency response to optimize the delivery of life-saving care during MCEs. This review identifies the clinical importance of the interdisciplinary team interactions and the lessons learned from past MCE experiences, strengthening healthcare system readiness for such critical incidents.

Background: Recent conflicts in Afghanistan and Iraq produced a substantial number of critically wounded service-members. We collected biomarker and clinical information from 73 patients who sustained 116 life-threatening combat wounds, and sought to determine if the data could be used to predict the likelihood of wound failure. Methods: From each patient, we collected clinical information, serum, wound effluent, and tissue prior to and at each surgical débridement. Inflammatory cytokines were quantified in both the serum and effluent, as were gene expression targets. The primary outcome was successful wound healing. Computer intensive methods were used to derive prognostic models that were internally validated using target shuffling and cross-validation methods. A second cohort of eighteen critically injured civilian patients was evaluated to determine if similar inflammatory responses were observed. Findings: The best-performing models enhanced clinical observation with biomarker data from the serum and wound effluent, an indicator that systemic inflammatory conditions contribute to local wound failure. A Random Forest model containing ten variables demonstrated the highest accuracy (AUC 0.79). Decision Curve Analysis indicated that the use of this model would improve clinical outcomes and reduce unnecessary surgical procedures. Civilian trauma patients demonstrated similar inflammatory responses and an equivalent wound failure rate, indicating that the model may be generalizable to civilian settings. Interpretation: Using advanced analytics, we successfully codified clinical and biomarker data from combat patients into a potentially generalizable decision support tool. Analysis of inflammatory data from critically ill patients with acute injury may inform decision-making to improve clinical outcomes and reduce healthcare costs. Funding: United States Department of Defense Health Programs.

Background The role of minimally invasive surgery in trauma has continued to evolve over the past 20 years. Diagnostic laparoscopy (DL) has become increasingly utilized for the diagnosis and management of both blunt and penetrating injuries. Objective While the safety and feasibility of laparoscopy has been established for penetrating thoracoabdominal trauma, it remains a controversial tool for other injury patterns due to the concern for complications and missed injuries. We sought to examine the role of laparoscopy for the initial management of traumatic injuries at our urban Level 1 trauma center. Methods All trauma patients who underwent DL for blunt or penetrating trauma between 2009 and 2018 were retrospectively reviewed. Demographic data, indications for DL, injuries identified, rate of conversion to open surgery, and outcomes were evaluated. Results A total of 316 patients were included in the cohort. The mean age was 34.9 years old (± 13.7), mean GCS 14 (± 3), and median ISS 10 (4–18). A total of 110/316 patients (35%) sustained blunt injury and 206/316 patients (65%) sustained penetrating injury. Indications for DL included evaluation for peritoneal violation (152/316, 48%), free fluid without evidence of solid organ injury (52/316, 16%), evaluation of bowel injury (42/316, 13%), and evaluation for diaphragmatic injury (35/316, 11%). Of all DLs, 178/316 (56%) were negative for injury requiring intervention, which was 58% of blunt cases and 55% of penetrating cases. There were no missed injuries noted. Average hospital length of stay was significantly shorter for patients that underwent DL vs conversion to open exploration (2.2 days vs. 4.5 days, p < 0.05). Conclusion In this single institution, retrospective study, the high volume of cases appears to show that DL is a reliable tool for detecting injury and avoiding potential negative or non-therapeutic laparotomies. However, when injuries were present, the high rate of conversion to open exploration suggests that its utility for therapeutic intervention warrants further study.

The authors regret that a resource of funding was not included in the original article publication. The authors would like to note that this research is supported by NIH T32 Training Grant in Critical Care, NIGMS (5T32GM095442-11). The authors would like to apologise for any inconvenience caused.

INTRODUCTION The pathophysiology of the inflammatory response after major trauma is complex, and the magnitude correlates with severity of tissue injury and outcomes. Study of infection-mediated immune pathways has demonstrated that cellular microRNAs may modulate the inflammatory response. The authors hypothesize that the expression of microRNAs would correlate to complicated recoveries in polytrauma patients (PtPs). METHODS Polytrauma patients enrolled in the prospective observational Tissue and Data Acquisition Protocol with Injury Severity Score of >15 were selected for this study. Polytrauma patients were divided into complicated recoveries and uncomplicated recovery groups. Polytrauma patients' blood samples were obtained at the time of admission (T0). Established biomarkers of systemic inflammation, including cytokines and chemokines, were measured using multiplexed Luminex-based methods, and novel microRNAs were measured in plasma samples using multiplex RNA hybridization. RESULTS Polytrauma patients (n = 180) had high Injury Severity Score (26 [20-34]) and complicated recovery rate of 33%. MicroRNAs were lower in PtPs at T0 compared with healthy controls, and bivariate analysis demonstrated that variations of microRNAs correlated with age, race, comorbidities, venous thromboembolism, pulmonary complications, complicated recovery, and mortality. Positive correlations were noted between microRNAs and interleukin 10, vascular endothelial growth factor, Acute Physiology and Chronic Health Evaluation, and Sequential Organ Failure Assessment scores. Multivariable Lasso regression analysis of predictors of complicated recovery based on microRNAs, cytokines, and chemokines revealed that miR-21-3p and monocyte chemoattractant protein-1 were predictive of complicated recovery with an area under the curve of 0.78. CONCLUSION Systemic microRNAs were associated with poor outcomes in PtPs, and results are consistent with previously described trends in critically ill patients. These early biomarkers of inflammation might provide predictive utility in early complicated recovery diagnosis and prognosis. Because of their potential to regulate immune responses, microRNAs may provide therapeutic targets for immunomodulation. LEVEL OF EVIDENCE Diagnostic Tests/Criteria; Level II.

Background: The American College of Surgeons Needs Based Assessment of Trauma Systems (NBATS) tool was developed to help determine the optimal regional distribution of designated trauma centers (DTC). The objectives of our current study were to compare the current distribution of DTCs in Georgia with the recommended allocation as calculated by the NBATS tool and to see if the NBATS tool identified similar areas of need as defined by our previous analysis using the International Classification of Diseases, Ninth Revision, Clinical Modification Injury Severity Score (ICISS). Methods Population counts were acquired from US Census publications. Transportation times were estimated using digitized roadmaps and patient zip codes. The number of severely injured patients was obtained from the Georgia Discharge Data System for 2010 to 2014. Severely injured patients were identified using two measures: ICISS<0.85 and Injury Severity Score >15. results The Georgia trauma system includes 19 level I, II, or III adult DTCs. The NBATS guidelines recommend 21; however, the distribution differs from what exists in the state. The existing DTCs exactly matched the NBATS recommended number of level I, II, or III DTCs in 2 of 10 trauma service areas (TSAs), exceeded the number recommended in 3 of 10 TSAs, and was below the number recommended in 5 of 10 TSAs. Densely populated, or urban, areas tend to be associated with a higher number of existing centers compared with the NBATS recommendation. Other less densely populated TSAs are characterized by large rural expanses with a single urban core where a DTC is located. The identified areas of need were similar to the ones identified in the previous gap analysis of the state using the ICISS methodology. Discussion The tool appears to underestimate the number of centers needed in extensive and densely populated areas, but recommends additional centers in geographically expansive rural areas. The tool signifies a preliminary step in assessing the need for state-wide inpatient trauma center services. Level of evidence Economic, level IV.

The management of massively transfused trauma patients has improved with a better understanding of trauma-induced coagulopathy, the limitations of crystalloid infusion, and the implementation of massive transfusion protocols (MTPs), which encompass transfusion management and other patient care needs to mitigate the “lethal triad” of acidosis, hypothermia, and coagulopathy. MTPs are currently changing in the United States and worldwide because of recent data showing that earlier and more aggressive transfusion intervention and resuscitation with blood components that approximate whole blood significantly decrease mortality. In this context, MTPs are a key element of “damage control resuscitation,” which is defined as the systematic approach to major trauma that addresses the lethal triad mentioned above. MTPs using adequate volumes of plasma, and thus coagulation factors, improve patient outcome. The ideal amounts of plasma, platelet, cryoprecipitate and other coagulation factors given in MTPs in relationship to the red blood cell transfusion volume are not known precisely, but until prospective, randomized, clinical trials are performed and more clinical data are obtained, current data support a target ratio of plasma:red blood cell:platelet transfusions of 1:1:1. Future prospective clinical trials will allow continued improvement in MTPs and thus in the overall management of patients with trauma.