Classifying patients suspected of appendicitis with regard to likelihood

Abstract

Background: We sought to develop a clinical predictive model for acute appendicitis and contrast it with current clinical practice.

Methods: A prospective observational study of patients presenting with signs or symptoms consistent with acute appendicitis. Random-partition modeling was used to develop an appendicitis likelihood model (ALM).

Results: Four hundred thirty-nine patients were enrolled, 101 with appendicitis, and 338 with other diagnoses. The ALM classified patients as "low likelihood" if they had a white blood cell count <9,500 and either no right lower-quadrant tenderness or a neutrophil count <54%. Patients were classified as "high likelihood" if they had a white blood cell count >13,000 with rebound tenderness or both voluntary guarding and neutrophil count >82%. The ALM outperformed actual clinical practice with regard to "missed" appendicitis, negative laparotomies, and total number of imaging studies.

Conclusion: The ALM may permit more judicious use of advanced radiographic imaging with lower nontherapeutic laparotomy rates.