Background

Trauma has long been considered unpredictable. Artificial neural networks (ANN) have recently shown the ability to predict admission volume, acuity, and operative needs at a single trauma center with very high reliability. This model has not been tested in a multicenter model with differing climate and geography. We hypothesize that an ANN can accurately predict trauma admission volume, penetrating trauma admissions, and mean Injury Severity Score (ISS) with a high degree of reliability across multiple trauma centers.

Methods

Three years of admission data were collected from five geographically distinct US Level I trauma centers. Patients with incomplete data, pediatric patients, and primary thermal injuries were excluded. Daily number of traumas, number of penetrating cases, and mean ISS were tabulated from each center along with National Oceanic and Atmospheric Administration data from local airports. We trained a single two-layer feed-forward ANN on a random majority (70%) partitioning of data from all centers using Bayesian Regularization and minimizing mean squared error. Pearson's product-moment correlation coefficient was calculated for each partition, each trauma center, and for high- and low-volume days (>1 standard deviation above or below mean total number of traumas).

Results

There were 5,410 days included. There were 43,380 traumas, including 4,982 penetrating traumas. The mean ISS was 11.78 (SD = 6.12). On the training partition, we achieved R = 0.8733. On the testing partition (new data to the model), we achieved R = 0.8732, with a combined R = 0.8732. For high- and low-volume days, we achieved R = 0.8934 and R = 0.7963, respectively.

Conclusion

An ANN successfully predicted trauma volumes and acuity across multiple trauma centers with very high levels of reliability. The correlation was highest during periods of peak volume. This can potentially provide a framework for determining resource allocation at both the trauma system level and the individual hospital level.

Level of evidence

Care Management, level IV.

Background

Increased knowledge of the temporal patterns in the distribution of trauma admissions could be beneficial to staffing and resource allocation efforts. However, little work has been done to understand how this distribution varies based on patient acuity, trauma mechanism or need for intervention. We hypothesize that temporal patterns exist in the distribution of trauma admissions, and that deep patterns exist when traumas are analyzed by their type and severity.

Study design

We conducted a cross-sectional observational study of adult patient flow at a level one trauma center over three years, 7/1/2013-6/30/2016. Primary thermal injuries were excluded. Frequency analysis was performed for patients grouped by ED disposition and mechanism against timing of admission; in subgroup analysis additional exclusion criteria were imposed.

Results

10,684 trauma contacts were analyzed. Trauma contacts were more frequent on Saturdays and Sundays than on weekdays (p<0.001). Peak arrival time was centered around evening shift change (6-7pm), but differed based on ED disposition: OR and ICU or Step-Down admissions (p = 0.0007), OR and floor admissions (p<0.0001), and ICU or Step-Down and floor admissions (p<0.0001). Step-Down and ICU arrival times (p = 0.42) were not different. Penetrating injuries peaked later than blunt (p<0.0001). Trauma varies throughout the year; we establish a high incidence trauma season (April to late October). Different mechanisms have varying dependence upon season; Motorcycle crashes (MCCs) have the greatest dependence.

Conclusion

We identify new patterns in the temporal and seasonal variation of trauma and of specific mechanisms of injury, including the novel findings that 1) penetrating trauma tends to present at later times than blunt, and 2) critically ill patients requiring an OR tend to present later than those who are less acute and require an ICU or Step-Down unit. These patients present later than those who are admitted to the floor. Penetrating trauma patients arriving later than blunt may be the underlying reason why operative patients arrive later than other patients.