Highlights We model MAIS 3+ injury risk in frontal impact crashes through model-averaging. We utilize morphomic information extracted from CT images. The model with morphomics predicts risks as well as the model with demographics. Morphomics are more tangible measures compared to demographics. We show the need for morphomics in the development of human mathematical models.

    Abstract This study resulted in a model-averaging methodology that predicts crash injury risk using vehicle, demographic, and morphomic variables and assesses the importance of individual predictors. The effectiveness of this methodology was illustrated through analysis of occupant chest injuries in frontal vehicle crashes. The crash data were obtained from the International Center for Automotive Medicine (ICAM) database for calendar year 1996 to 2012. The morphomic data are quantitative measurements of variations in human body 3-dimensional anatomy. Morphomics are obtained from imaging records. In this study, morphomics were obtained from chest, abdomen, and spine CT using novel patented algorithms. A NASS-trained crash investigator with over thirty years of experience collected the in-depth crash data. There were 226 cases available with occupants involved in frontal crashes and morphomic measurements. Only cases with complete recorded data were retained for statistical analysis. Logistic regression models were fitted using all possible configurations of vehicle, demographic, and morphomic variables. Different models were ranked by the Akaike Information Criteria (AIC). An averaged logistic regression model approach was used due to the limited sample size relative to the number of variables. This approach is helpful when addressing variable selection, building prediction models, and assessing the importance of individual variables. The final predictive results were developed using this approach, based on the top 100 models in the AIC ranking. Model-averaging minimized model uncertainty, decreased the overall prediction variance, and provided an approach to evaluating the importance of individual variables. There were 17 variables investigated: four vehicle, four demographic, and nine morphomic. More than 130,000 logistic models were investigated in total. The models were characterized into four scenarios to assess individual variable contribution to injury risk. Scenario 1 used vehicle variables; Scenario 2, vehicle and demographic variables; Scenario 3, vehicle and morphomic variables; and Scenario 4 used all variables. AIC was used to rank the models and to address over-fitting. In each scenario, the results based on the top three models and the averages of the top 100 models were presented. The AIC and the area under the receiver operating characteristic curve (AUC) were reported in each model. The models were re-fitted after removing each variable one at a time. The increases of AIC and the decreases of AUC were then assessed to measure the contribution and importance of the individual variables in each model. The importance of the individual variables was also determined by their weighted frequencies of appearance in the top 100 selected models. Overall, the AUC was 0.58 in Scenario 1, 0.78 in Scenario 2, 0.76 in Scenario 3 and 0.82 in Scenario 4. The results showed that morphomic variables are as accurate at predicting injury risk as demographic variables. The results of this study emphasize the importance of including morphomic variables when assessing injury risk. The results also highlight the need for morphomic data in the development of human mathematical models when assessing restraint performance in frontal crashes, since morphomic variables are more “tangible” measurements compared to demographic variables such as age and gender.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Prediction of thoracic injury severity in frontal impacts by selected anatomical morphomic variables through model-averaged logistic regression approach


    Contributors:

    Published in:

    Publication date :

    2013-08-23


    Size :

    9 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Injury mechanisms and severity in narrow offset frontal impacts

    Pintar, Frank A. / Yoganandan, Narayan / Maiman, Dennis J. | Tema Archive | 2008


    Injury Mechanisms and Severity in Narrow Offset Frontal Impacts

    Pintar, F.A. / Yoganandan, N. / Maiman, D.J. et al. | British Library Conference Proceedings | 2008


    A logistic regression analysis of lower limb injury risk in frontal collision

    Thomas,P. / Bradford,M. / Vehicle Safety Research Centre Loughborough,GB | Automotive engineering | 1995


    Towards an Accident Severity Prediction System with Logistic Regression

    Mensouri, Houssam / Azmani, Abdellah / Azmani, Monir | Springer Verlag | 2023