Canadian benchmarks in trauma

An Artificial Intelligence Model for Predicting Trauma Mortality Among Emergency Department Patients in South Korea: Retrospective Cohort Study

BACKGROUND

Within the trauma system, the emergency department (ED) is the hospital's first contact and is vital for allocating medical resources. However, there is generally limited information about patients that die in the ED.

OBJECTIVE

The aim of this study was to develop an artificial intelligence (AI) model to predict trauma mortality and analyze pertinent mortality factors for all patients visiting the ED.

METHODS

We used the Korean National Emergency Department Information System (NEDIS) data set (N=6,536,306), incorporating over 400 hospitals between 2016 and 2019. We included the International Classification of Disease 10th Revision (ICD-10) codes and chose the following input features to predict ED patient mortality: age, sex, intentionality, injury, emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and vital signs. We compared three different feature set performances for AI input: all features (n=921), ICD-10 features (n=878), and features excluding ICD-10 codes (n=43). We devised various machine learning models with an ensemble approach via 5-fold cross-validation and compared the performance of each model with that of traditional prediction models. Lastly, we investigated explainable AI feature effects and deployed our final AI model on a public website, providing access to our mortality prediction results among patients visiting the ED.

RESULTS

Our proposed AI model with the all-feature set achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.9974 (adaptive boosting [AdaBoost], AdaBoost + light gradient boosting machine [LightGBM]: Ensemble), outperforming other state-of-the-art machine learning and traditional prediction models, including extreme gradient boosting (AUROC=0.9972), LightGBM (AUROC=0.9973), ICD-based injury severity scores (AUC=0.9328 for the inclusive model and AUROC=0.9567 for the exclusive model), and KTAS (AUROC=0.9405). In addition, our proposed AI model outperformed a cutting-edge AI model designed for in-hospital mortality prediction (AUROC=0.7675) for all ED visitors. From the AI model, we also discovered that age and unresponsiveness (coma) were the top two mortality predictors among patients visiting the ED, followed by oxygen saturation, multiple rib fractures (ICD-10 code S224), painful response (stupor, semicoma), and lumbar vertebra fracture (ICD-10 code S320).

CONCLUSIONS

Our proposed AI model exhibits remarkable accuracy in predicting ED mortality. Including the necessity for external validation, a large nationwide data set would provide a more accurate model and minimize overfitting. We anticipate that our AI-based risk calculator tool will substantially aid health care providers, particularly regarding triage and early diagnosis for trauma patients.

Model for Predicting In-Hospital Mortality of Physical Trauma Patients Using Artificial Intelligence Techniques: Nationwide Population-Based Study in Korea

BACKGROUND

Physical trauma-related mortality places a heavy burden on society. Estimating the mortality risk in physical trauma patients is crucial to enhance treatment efficiency and reduce this burden. The most popular and accurate model is the Injury Severity Score (ISS), which is based on the Abbreviated Injury Scale (AIS), an anatomical injury severity scoring system. However, the AIS requires specialists to code the injury scale by reviewing a patient's medical record; therefore, applying the model to every hospital is impossible.

OBJECTIVE

We aimed to develop an artificial intelligence (AI) model to predict in-hospital mortality in physical trauma patients using the International Classification of Disease 10th Revision (ICD-10), triage scale, procedure codes, and other clinical features.

METHODS

We used the Korean National Emergency Department Information System (NEDIS) data set (N=778,111) compiled from over 400 hospitals between 2016 and 2019. To predict in-hospital mortality, we used the following as input features: ICD-10, patient age, gender, intentionality, injury mechanism, and emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and procedure codes. We proposed the ensemble of deep neural networks (EDNN) via 5-fold cross-validation and compared them with other state-of-the-art machine learning models, including traditional prediction models. We further investigated the effect of the features.

RESULTS

Our proposed EDNN with all features provided the highest area under the receiver operating characteristic (AUROC) curve of 0.9507, outperforming other state-of-the-art models, including the following traditional prediction models: Adaptive Boosting (AdaBoost; AUROC of 0.9433), Extreme Gradient Boosting (XGBoost; AUROC of 0.9331), ICD-based ISS (AUROC of 0.8699 for an inclusive model and AUROC of 0.8224 for an exclusive model), and KTAS (AUROC of 0.1841). In addition, using all features yielded a higher AUROC than any other partial features, namely, EDNN with the features of ICD-10 only (AUROC of 0.8964) and EDNN with the features excluding ICD-10 (AUROC of 0.9383).

CONCLUSIONS

Our proposed EDNN with all features outperforms other state-of-the-art models, including the traditional diagnostic code-based prediction model and triage scale.

Trauma Registry Data as a Policy-Making Tool: A Systematic Review on the Research Dimensions

Objective:

To review the research dimensions of trauma registry data on health policy making.

Methods:

PubMed and EMBASE were searched until July 2020. Keywords were used on the search process included Trauma, Injury, Registry and Research, which were searched by using appropriate search strategies. The included articles had to: 1. be extracted from data related to trauma registries; 2- be written in English; 3- define a time period and a patient population; 4- preferably have more details and policy recommendations; and 5- preferably have a discussion on how to improve diagnosis and treatment. The results obtained from the included studies were qualitatively analyzed using thematic synthesis and comparative tables.

Results:

In the primary round of search, 19559 studies were retrieved. According to PRISMA statement and also performing quality appraisal process, 30 studies were included in the final phase of analysis. In the final papers’ synthesis, 14 main research domains were extracted and classified in terms of the policy implication and research priority. The domains with the highest frequency were “The relationship between trauma registry data and hospital care protocols for trauma patients” and “The causes of Disability Adjusted Life Years (DALYs) due to trauma”.

Conclusion:

Using trauma registry data as a tool for policy-making could be helpful in several ways, namely increasing the quality of patient care, preventing injuries and decreasing their number, figuring out the details of socioeconomic status effects, and improving the quality of researches in practical ways. Also, follow-up of patients after trauma surgery as one of the positive effects of the trauma registry can be the focus of attention of policy-making bodies.

Strategies to Improve Information Transfer for Multitrauma Patients

The aim of this multiphase mixed-method study was to improve access, flow, and consistency of information transfer for multitrauma patients leaving the Emergency Department. Methods included literature review, focus group interviews, chart audits, staff surveys, and a review of international trauma forms to inform an intervention developed with a researcher-led, clinician stakeholder group. Analysis included descriptive and inferential statistics. Baseline data revealed variability existed in patient-care documentation, showing little standardization. Improvement strategies implemented included a gold standard for information embedded in handover tools, raising staff awareness of complexities for information transfer. Improvement was seen in communication between wards coordinating transfer, improved documentation, decreased information duplication, improved legibility, and increased ease and efficiency in navigating to key information. Improvement in communication at patient transition is essential to continuity of safe, effective care, and is impacted by complex interactions between multiple factors. Difficulty increases for patients with high acuity.

Audit filters for improving processes of care and clinical outcomes in trauma systems

BACKGROUND

Traumatic injuries represent a considerable public health burden with significant personal and societal costs. The care of the severely injured patient in a trauma system progresses along a continuum that includes numerous interventions being provided by a multidisciplinary group of healthcare personnel. Despite the recent emphasis on quality of care in medicine, there has been little research to direct trauma clinicians and administrators on how optimally to monitor and improve upon the quality of care delivered within a trauma system. Audit filters are one mechanism for improving quality of care and are defined as specific clinical processes or outcomes of care that, when they occur, represent unfavorable deviations from an established norm and which prompt review and feedback. Although audit filters are widely utilized for performance improvement in trauma systems they have not been subjected to systematic review of their effectiveness.

OBJECTIVES

To determine the effectiveness of using audit filters for improving processes of care and clinical outcomes in trauma systems.

SEARCH STRATEGY

Our search strategy included an electronic search of the Cochrane Injuries Group Specialized Register, the Cochrane EPOC Group Specialized Register, CENTRAL (The Cochrane Library 2008, Issue 4), MEDLINE, PubMed, EMBASE, CINAHL, and ISI Web of Science: (SCI-EXPANDED and CPCI-S). We handsearched the Journal of Trauma, Injury, Annals of Emergency Medicine, Academic Emergency Medicine, and Injury Prevention. We searched two clinical trial registries: 1) The World Health Organization International Clinical Trials Registry Platform and, 2) Clinical Trials.gov. We also contacted content experts for further articles. The most recent electronic search was completed in December 2008 and the handsearch was completed up to February 2009.

SELECTION CRITERIA

We searched for randomized controlled trials, controlled clinical trials, controlled before-and-after studies, and interrupted time series studies that used audit filters as an intervention for improving processes of care, morbidity, or mortality for severely injured patients.

DATA COLLECTION AND ANALYSIS

Two authors independently screened the search results, applied inclusion criteria, and extracted data.

MAIN RESULTS

There were no studies identified that met the inclusion criteria for this review.

AUTHORS' CONCLUSIONS

We were unable to identify any studies of sufficient methodological quality to draw conclusions regarding the effectiveness of audit filters as a performance improvement intervention in trauma systems. Future research using rigorous study designs should focus on the relative effectiveness of audit filters in comparison to alternative quality improvement strategies at improving processes of care, functional outcomes, and mortality for injured patients.