Estimating the likely true changes in rheumatic fever incidence using two data sources

Abstract

Acute rheumatic fever (ARF) continues to produce a significant burden of disease in New Zealand (NZ) Māori and Pacific peoples. Serious limitations in national surveillance data mean that accurate case totals cannot be generated. Given the changing epidemiology of ARF in NZ and the major national rheumatic fever prevention programme (2012-2017), we updated our previous likely true case number estimates using capture-recapture analyses. Aims were to estimate the likely true incidence of ARF in NZ and comment on the changing ability to detect cases. Data were obtained from national hospitalisation and notification databases. The Chapman Estimate partially adjusted for bias. An estimated 2342 likely true new cases arose from 1997 to 2015, giving a mean annual incidence of 2·9 per 100 000 (95% CI 2·5-3·5). Compared with the pre-intervention (2009-2011) baseline incidence (3·4 per 100 000, 95% CI 2·9-4·0), the likely true 2015 incidence declined 44%. Large gaps in data completeness are slowly closing. During the period 2012-2015, 723 cases were identified; 83·8% of notifications were matched to hospitalisation data, and 87·2% of hospitalisations matched to notifications. Despite this improvement, clinicians need to remain aware of the need to notify atypical patients. A possible unintended consequence of the national ARF prevention programme is increased misdiagnosis.

Keywords: Health equity; incidence; public health; rheumatic fever; surveillance system.

Fig. 1.

Selecting cases for the initial notification dataset and the initial hospitalisation dataset 1997–2015.

Fig. 2.

Overlap between initial case datasets, 1997–2015.

Fig. 3.

ARF hospitalisations and notifications, 1997–2015.