Bradley M Dennis1, David P Stonko, Rachael A Callcut, Richard A Sidwell, Nicole A Stassen, Mitchell J Cohen, Bryan A Cotton, Oscar D Guillamondegui. 1. From the Division of Trauma and Surgical Critical Care, (B.M.D., O.D.G.), Vanderbilt University Medical Center, Nashville, Tennessee; Department of Surgery (D.P.S.), The Johns Hopkins Hospital, Baltimore, Maryland; Department of Surgery (R.A.C.), University of California San Francisco, San Francisco, California; Department of General Surgery, Iowa Methodist Medical Center (R.A.S.), Des Moines, Iowa; Division of Acute Care Surgery, Department of Surgery, University of Rochester Medical Center (N.A.S.), Rochester, New York; Department of Surgery, Denver Health Medical Center (M.J.C.), Denver, Colorado; and Center for Translational Injury Research, Division of Acute Care Surgery, Department of Surgery, Memorial Hermann Hospital/Texas Medical Center (B.A.C.), Houston, Texas.
Abstract
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: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.
Authors: David P Stonko; Bradley M Dennis; Rachael A Callcut; Richard D Betzold; Michael C Smith; Andrew J Medvecz; Oscar D Guillamondegui Journal: PLoS One Date: 2018-12-03 Impact factor: 3.240