The neighbourhood method for measuring differences in maternal mortality, infant mortality and other rare demographic events

Abstract

In the absence of reliable systems for registering rare types of vital events large surveys are required to measure changes in their rates. However some events such as maternal deaths are widely known about in the community. This study examined the utility of asking respondents about events in their neighbourhood as an efficient method for measuring relative rates of rare health events such as maternal and infant deaths. A survey was conducted in the health and demographic surveillance system (HDSS) in Matlab, Bangladesh, which includes two areas with different health care regimes. Adult women were asked about any maternal deaths; multiple births; infant deaths, live births and some other events they knew of in a small specified area around their home. Agreement between HDSS records and survey responses was moderate or better (kappa≥0.44) for all the events and greatest for maternal deaths (kappa = 0.77) with 84% being reported. Most events were more likely to be reported if they were recent (p<0.05). Infant mortality rate in one area was 0.56 times that in the other which was well reflected by the ratio of survey results (0.53). Simulations were used to study the ability of the method to detect differences in maternal mortality ratio. These suggested that a sample size around 5000 would give 80% power to detect a 50% decrease from a baseline of 183 which compared well with an estimated sample size around 10 times larger using the direct sisterhood method. The findings suggest that the Neighbourhood Method has potential for monitoring relative differences between areas or changes over time in the rates of rare demographic events, requiring considerably smaller sample sizes than traditional methods. This raises the possibility for interventions to demonstrate real effects on outcomes such as maternal deaths where previously this was only feasible by indirect methods.

Figure 1. Results of simulations.

(A) Ratios of observed neighbourhood indices for a comparison area and the reference area (I _comp/I _ref) compared with ratios of true MMRs (MMR_comp/MMR_ref) for a sample size of 20,000 per area. Each point represents the results of one simulation. In each case the MMR in the reference area was 183 per 100,000 live births. Ratios of neighbourhood indices which were significantly different (p<0.05) are shown in blue (filled circles); non-significant results are shown in orange (open circles). 1:1 line is also shown. (B) Detectable differences – the lines show ratios of MMR_comp/MMR_ref which could be detected with 80% power at the 5% significance level for a given sample size when MMR_ref = 183. The equivalent curves using a direct sisterhood survey with reference period 3 years assuming 2 sisters per respondent, GFR = 83 and perfect information from survey responses are also shown.