A retrospective evaluation of point of care ultrasound for acute cholecystitis in a tertiary academic hospital setting

Background: In 2008 the Council of Emergency Medicine Residency Directors delineated consensus recommendations for training in biliary ultrasound for the "detection of biliary pathology". Objectives: While studies have looked at the accuracy of emergency provider performed clinical ultrasound (ECUS), we sought to evaluated if ECUS could be diagnostic for acute cholecystitis and thus obviate the need for follow-up imaging. Method: We reviewed all ECUS performed between 2012 and 2017 that had a matching radiology performed ultrasound (RADUS) and a discharge diagnosis. 332 studies were identified. The sensitivity and specificity of both ECUS and RADUS were compared to the patient's discharge diagnosis. The agreement between the ECUS and RADUS was assessed using an unweighted Cohen's Kappa. The time from patient arrival to diagnosis by ECUS and RADUS was also compared. Results: Using discharge diagnosis as the gold standard ECUS was 67% (56-78%) sensitive, 88% (84-92%) specific, NPV 90% (87-95%), PPV 60% (50-71%), +LR 5.6 (3.9-8.2), -LR 0.37 (0.27-0.52) for acute cholecystitis. RADUS was 76% (66-87%) sensitive, 97% (95-99%) specific, NPV 95% (092-97%), PPV 86% (76-95%), +LR 25.6 (12.8-51.4), and -LR 0.24 (0.15-0.38). ECUS was able to detect gallstones with 93% (89-96%) sensitivity and 94% (90-98%) specificity leading to a NPV 90% (85-95%), PPV of 95% (92-98%), +LR 14.5 (7.7-27.4), -LR 0.08 (0.05-0.13). The unweighted kappa between ECUS and RADUS was 0.57. The median time between obtaining ECUS vs. RADUS diagnosis was 124 min. Conclusions: ECUS can be beneficial in ruling out acute cholecystitis, but lacks the test characteristics to be diagnostic for acute cholecystitis.