Optimal hepatobiliary scintigraphy for gallbladder dyskinesia

Abstract

Background: The accuracy of hepatobiliary scintigraphy to assess gallbladder function remains controversial. National supply shortages of pharmaceutical-grade cholecystokinin led to the use of an oral fatty meal to stimulate gallbladder contraction during hepatobiliary scintigraphy. The goal of this study was to compare the predictive indices of cholecystokinin and fatty meal ingestion for stimulation of gallbladder contraction.

Methods: Patients evaluated with hepatobiliary iminodiacetic acid scan from 2014 to 2017 were reviewed and grouped based on testing stimulant (fatty meal versus cholecystokinin). Patients who later underwent cholecystectomy were selected for analysis. Hepatobiliary iminodiacetic acid results were correlated with surgical pathology and postoperative resolution of symptoms. Two-way statistical analysis was performed.

Results: A total of 359 patients underwent hepatobiliary iminodiacetic acid scan followed by cholecystectomy for biliary dyskinesia. Patients who received fatty meal stimulant (n = 86) were compared to those that received cholecystokinin (n = 273). Mean gallbladder ejection fraction during hepatobiliary iminodiacetic acid was 38% and 44% for the cholecystokinin and fatty meal groups, respectively, P = .073. Predictive metrics were not statistically different between groups with regard to pathology, symptomatic improvement, or accuracy. Symptomatic resolution (cholecystokinin-hepatobiliary iminodiacetic acid 78%, fatty meal-hepatobiliary iminodiacetic acid 68%; P = 0.058) and specificity (cholecystokinin-hepatobiliary iminodiacetic acid 26%, fatty meal-hepatobiliary iminodiacetic acid 44%, P = 0.417) were comparable in both testing groups.

Conclusion: Stimulation of gallbladder contraction with a fatty meal during hepatobiliary iminodiacetic acid testing is a more affordable and reliable alternative to cholecystokinin for patients undergoing evaluation for gallbladder dysmotility.

Fig 1

Gallbladder EF% distribution with mean and 1 standard deviation represented. A logistic regression analysis was performed which indicated no significant difference in mean [SD] GBEF between CCK (38% [27]) and Ensure (44% [27]) after adjusting for age, gender, race, and diabetes, P = .073. Abbreviations: EF, ejection fraction; SD, standard deviation.