By a News Reporter-Staff News Editor at Insurance Weekly News -- Investigators publish new report on Risk Management. According to news reporting originating from Ann Arbor, Michigan , by VerticalNews correspondents, research stated, "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." Our news editors obtained a quote from the research from the University of Michigan , "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." According to the news editors, the research concluded: "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." For more information on this research see: Prediction of thoracic injury severity in frontal impacts by selected anatomical morphomic variables through model-averaged logistic regression approach. Accident Analysis and Prevention , 2013;60():172-180. Accident Analysis and Prevention can be contacted at: Pergamon-Elsevier Science Ltd , The Boulevard, Langford Lane , Kidlington, Oxford OX5 1GB, England . ( Elsevier - www.elsevier.com ; Accident Analysis and Prevention - www.elsevier.com/wps/product/cws_home/336 ) The news editors report that additional information may be obtained by contacting P. Zhang , University of Michigan , Dept. of Biostat , Ann Arbor, MI 48109, United States . Additional authors for this research include C. Parenteau , L. Wang , S. Holcombe, C. Kohoyda-Inglis , J. Sullivan and S. Wang. Keywords for this news article include: Michigan , Ann Arbor , United States , Risk Management, North and Central America Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC
Most Popular Stories
- Apple, HP, Intel May Take a Hit from Slowdown in Smartphone Sales Growth
- FDIC Files Lawsuit on Behalf of Banks Allegedly Hurt by Libor Scandal
- Some California Cities Seeking Water Independence
- Motley Crue's Nikki Sixx Marries Model Courtney Bingham
- Chinese e-Commerce Giant Alibaba Gears for IPO in U.S.
- Will Missing Malaysian Jet Prompt Aviation System Change?
- Jack Daniel's Resists Changes to Tenn. Whiskey Law