Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jun 5;8(6):799.
doi: 10.3390/jcm8060799.

Machine Learning Models of Survival Prediction in Trauma Patients

Cheng-Shyuan Rau  1 , Shao-Chun Wu  2 , Jung-Fang Chuang  3 , Chun-Ying Huang  4 , Hang-Tsung Liu  5 , Peng-Chen Chien  6 , Ching-Hua Hsieh  7
Affiliations

Machine Learning Models of Survival Prediction in Trauma Patients

Cheng-Shyuan Rau et al. J Clin Med. .

Abstract

Background: We aimed to build a model using machine learning for the prediction of survival in trauma patients and compared these model predictions to those predicted by the most commonly used algorithm, the Trauma and Injury Severity Score (TRISS).

Methods: Enrolled hospitalized trauma patients from 2009 to 2016 were divided into a training dataset (70% of the original data set) for generation of a plausible model under supervised classification, and a test dataset (30% of the original data set) to test the performance of the model. The training and test datasets comprised 13,208 (12,871 survival and 337 mortality) and 5603 (5473 survival and 130 mortality) patients, respectively. With the provision of additional information such as pre-existing comorbidity status or laboratory data, logistic regression (LR), support vector machine (SVM), and neural network (NN) (with the Stuttgart Neural Network Simulator (RSNNS)) were used to build models of survival prediction and compared to the predictive performance of TRISS. Predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operating characteristic curves.

Results: In the validation dataset, NN and the TRISS presented the highest score (82.0%) for balanced accuracy, followed by SVM (75.2%) and LR (71.8%) models. In the test dataset, NN had the highest balanced accuracy (75.1%), followed by the TRISS (70.2%), SVM (70.6%), and LR (68.9%) models. All four models (LR, SVM, NN, and TRISS) exhibited a high accuracy of more than 97.5% and a sensitivity of more than 98.6%. However, NN exhibited the highest specificity (51.5%), followed by the TRISS (41.5%), SVM (40.8%), and LR (38.5%) models.

Conclusions: These four models (LR, SVM, NN, and TRISS) exhibited a similar high accuracy and sensitivity in predicting the survival of the trauma patients. In the test dataset, the NN model had the highest balanced accuracy and predictive specificity.

Keywords: Trauma and Injury Severity Score (TRISS); logistic regression (LR); machine learning (ML); neural networks (NN); support vector machine (SVM); survival.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interests.

Figures

Figure 1
Figure 1
Architecture of the four-layered neural network.
Figure 2
Figure 2
Receiver operating characteristic (ROC) curves for the LR, SVM, NN, and TRISS models in predicting the survival of trauma patients in the (A) train, (B) validation, and (C) test datasets.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Gabbe B.J., Cameron P.A., Wolfe R. TRISS: Does it get better than this? Acad. Emerg. Med. 2004;11:181–186. doi: 10.1111/j.1553-2712.2004.tb01432.x. - DOI - PubMed
    1. Glance L.G., Osler T. Beyond the major trauma outcome study: Benchmarking performance using a national contemporary, population-based trauma registry. J. Trauma. 2001;51:725–727. doi: 10.1097/00005373-200110000-00017. - DOI - PubMed
    1. de Munter L., Polinder S., Lansink K.W., Cnossen M.C., Steyerberg E.W., de Jongh M.A. Mortality prediction models in the general trauma population: A systematic review. Injury. 2017;48:221–229. doi: 10.1016/j.injury.2016.12.009. - DOI - PubMed
    1. Boyd C.R., Tolson M.A., Copes W.S. Evaluating trauma care: The TRISS method. Trauma Score and the Injury Severity Score. J. Trauma. 1987;27:370–378. doi: 10.1097/00005373-198704000-00005. - DOI - PubMed
    1. Champion H.R., Copes W.S., Sacco W.J., Lawnick M.M., Keast S.L., Bain L.W., Jr., Flanagan M.E., Frey C.F. The Major Trauma Outcome Study: Establishing national norms for trauma care. J. Trauma. 1990;30:1356–1365. doi: 10.1097/00005373-199011000-00008. - DOI - PubMed

LinkOut - more resources