Feasibility of case-control and test-negative designs to evaluate dengue vaccine effectiveness in Malaysia

BACKGROUND: The world's first dengue vaccine [Dengvaxia; Sanofi Pasteur] was licensed in 2015 and others are in development. Real-world evaluations of dengue vaccines will therefore soon be needed. We assessed feasibility of case control (CC) and test-negative (TN) design studies for dengue vaccine effectiveness by measuring associations between socio-demographic risk factors, and hospitalized dengue outcomes, in Malaysia.

METHODS: Following ethical approval, we conducted hospital-based dengue surveillance for one year in three referral hospitals. Suspected cases aged 9-25 years underwent dengue virological confirmation by RT-PCR and/or NS1 Ag ELISA at a central laboratory. Two age- and geography-matched hospitalized non-dengue case-controls were recruited for a traditional CC study. Suspected cases testing negative were test-negative controls. Socio-demographic, risk factor and routine laboratory data were collected. Logistic regression models were used to estimate associations between confirmed dengue and risk factors.

RESULTS: We recruited 327 subjects; 155 were suspected of dengue. The planned sample size was not met. 124 (80%) of suspected cases were dengue-confirmed; seven were assessed as severe. Three had missing RT-PCR results; the study recruited 28 test-negative controls. Only 172 matched controls could be recruited; 90 cases were matched with ≥1 controls. Characteristics of cases and controls were mostly similar. By CC design, two variables were significant risk factors for hospitalized dengue: recent household dengue contact (OR: 54, 95% CI: 7.3-397) and recent neighbourhood insecticidal fogging (OR: 2.1; 95% CI: 1.3-3.6). In the TN design, no risk factors were identified. In comparison with gold-standard diagnostics, routine tests performed poorly.

CONCLUSIONS: The CC design may be more appropriate than the TN design for hospitalized dengue vaccine effectiveness studies. Selection bias in case control selection could be minimized by protocol changes more easily than increasing TN design control numbers, because early-stage dengue diagnosis in endemic countries is highly specific. MREC study approval: (39)KKM/NIHSEC/P16-1334.