The impact of missing trauma data on predicting massive transfusion

Abstract

Background: Missing data are inherent in clinical research and may be especially problematic for trauma studies. This study describes a sensitivity analysis to evaluate the impact of missing data on clinical risk prediction algorithms. Three blood transfusion prediction models were evaluated using an observational trauma data set with valid missing data.

Methods: The PRospective Observational Multicenter Major Trauma Transfusion (PROMMTT) study included patients requiring one or more unit of red blood cells at 10 participating US Level I trauma centers from July 2009 to October 2010. Physiologic, laboratory, and treatment data were collected prospectively up to 24 hours after hospital admission. Subjects who received 10 or more units of red blood cells within 24 hours of admission were classified as massive transfusion (MT) patients. Correct classification percentages for three MT prediction models were evaluated using complete case analysis and multiple imputation. A sensitivity analysis for missing data was conducted to determine the upper and lower bounds for correct classification percentages.

Results: PROMMTT study enrolled 1,245 subjects. MT was received by 297 patients (24%). Missing percentage ranged from 2.2% (heart rate) to 45% (respiratory rate). Proportions of complete cases used in the MT prediction models ranged from 41% to 88%. All models demonstrated similar correct classification percentages using complete case analysis and multiple imputation. In the sensitivity analysis, correct classification upper-lower bound ranges per model were 4%, 10%, and 12%. Predictive accuracy for all models using PROMMTT data was lower than reported in the original data sets.

Conclusion: Evaluating the accuracy clinical prediction models with missing data can be misleading, especially with many predictor variables and moderate levels of missingness per variable. The proposed sensitivity analysis describes the influence of missing data on risk prediction algorithms. Reporting upper-lower bounds for percent correct classification may be more informative than multiple imputation, which provided similar results to complete case analysis in this study.