Enhancing case definitions for surveillance of human monkeypox in the Democratic Republic of Congo

Abstract

Background: Human monkeypox (MPX) occurs at appreciable rates in the Democratic Republic of Congo (DRC). Infection with varicella zoster virus (VZV) has a similar presentation to that of MPX, and in areas where MPX is endemic these two illnesses are commonly mistaken. This study evaluated the diagnostic utility of two surveillance case definitions for MPX and specific clinical characteristics associated with laboratory-confirmed MPX cases.

Methodology/principal findings: Data from a cohort of suspect MPX cases (identified by surveillance over the course of a 42 month period during 2009-2014) from DRC were used; real-time PCR diagnostic test results were used to establish MPX and VZV diagnoses. A total of 333 laboratory-confirmed MPX cases, 383 laboratory-confirmed VZV cases, and 36 cases that were determined to not be either MPX or VZV were included in the analyses. Significant (p<0.05) differences between laboratory-confirmed MPX and VZV cases were noted for several signs/symptoms including key rash characteristics. Both surveillance case definitions had high sensitivity and low specificities for individuals that had suspected MPX virus infections. Using 12 signs/symptoms with high sensitivity and/or specificity values, a receiver operator characteristic analysis showed that models for MPX cases that had the presence of 'fever before rash' plus at least 7 or 8 of the 12 signs/symptoms demonstrated a more balanced performance between sensitivity and specificity.

Conclusions: Laboratory-confirmed MPX and VZV cases presented with many of the same signs and symptoms, and the analysis here emphasized the utility of including 12 specific signs/symptoms when investigating MPX cases. In order to document and detect endemic human MPX cases, a surveillance case definition with more specificity is needed for accurate case detection. In the absence of a more specific case definition, continued emphasis on confirmatory laboratory-based diagnostics is warranted.

Fig 1. Flow chart of the cases selected for each analysis.

Fig 2. A receiver operating characteristic analysis showing the area under the curve for the model using the symptom ‘fever before rash’ and various summed frequencies of 12 signs/symptoms.