Prediction of injury severity is an important task for articulating proper mitigation measures to reduce the loss of an accident resulting into injuries. In this study, using OSHA construction injury data, we developed a fatality prediction model using logistic regression and frequency weighted data transformation. The approach adopted here is useful for handling categorical predictors. The model is fairly fit to the data. The model could be used for prediction with the involvement of experienced domain experts. Interestingly, some of the predictors actuate an injury being fatal while other predictors inhibit it. Management should take appropriate mitigation measures to reduce the influence of the predictors contributing positively.