Peak blood alcohol prediction: An empirical test of two computer models

Objective: Two computer programs (Computerized Blood Alcohol Calculator and Blood Alcohol Content Estimator) were compared for reliability in predicting peak blood alcohol concentration (BAC). Method: Subjects were middle-aged volunteers (N = 40; 20 men, 20 women) who each consumed a constant amount of alcohol (40 mi of 95% alcohol or 30 g ethanol) prior to undergoing breath testing to determine peak BAC. The observed BACs were compared with the predicted BACs obtained with each of the computer programs. Results: The Computerized Blood Alcohol Calculator provided marginally better BAC predictions than did the Blood Alcohol Content Estimator. However, both computer models seriously underestimated the peak BACs for this group of subjects. Conclusions: Results are discussed with particular reference to the need for additional studies of age, gender, and body composition in predicting peak BACs for heterogeneous subject groups.