Classifying patients suspected of appendicitis with regard to likelihood

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 nontherapuetic laparotomy rates.