Comparison of hospital laboratory serum alcohol levels obtained by an enzymatic method with whole blood levels forensically determined by gas chromatography

Estimating the equivalent whole blood ethanol level from a serum or plasma determination has been addressed by numerous articles in both the clinical and forensic literature. All previous studies have either involved sample sizes insufficient for adequate statistical evaluation or have utilized gas chromatography for both serum and whole blood analysis. In this study, based on samples from 212 consecutive patients admitted to a hospital trauma center, serum was assayed for ethanol using an enzymatic oxidation method, and the results were compared to whole blood samples taken simultaneously and analyzed by headspace gas chromatography in a forensic toxicology laboratory. Contrary to previously published conclusions, it was found that the serum/whole blood alcohol ratio (SAC/BAC) is concentrationdependent, with average values ranging from around 1.12 to as high as around 1.18, depending on SAC, thus precluding a generally applicable SAC/BAC conversion factor. However, a linear regression model was found to provide adequate prediction intervals at any desired level of confidence for whole blood alcohol from serum alcohol levels up to 300 mg/dL. For example, at a confidence level of 95%, an SAC of 103 mg/dL corresponds to a BAC of at least 0.080 g/dL.