期刊名称：International Journal of Population Data Science
电子版ISSN：2399-4908
出版年度：2020
卷号：5
期号：1
页码：1-16
DOI：10.23889/ijpds.v5i1.1114
出版社：Swansea University
摘要：Introduction The under-reporting of Aboriginal and Torres Strait Islander people on routinely collected health datasets has important implications for understanding the health of this population. By pooling available information on individuals’ Aboriginal or Torres Strait Islander status from probabilistically linked datasets, methods have been developed to adjust for this under-reporting. Objectives To explore different algorithms that enhance reporting of Aboriginal status in birth data to define a cohort of Aboriginal women, examine any differences between women recorded as Aboriginal and those assigned enhanced Aboriginal status, and assess the effects of using different reported populations to estimate within-group comparisons for Aboriginal people. Methods Three algorithms, with different levels of inclusiveness, were used to establish different study populations all of which aimed to include all singleton babies born to Aboriginal or Torres Strait Islander women residing in New South Wales, Australia between 2010 and 2014 and their mothers. The demographics of the four study populations were described and compared using frequencies and percentages. In order to assess the impact on research outcomes and conclusions of using study populations derived from different algorithms, estimates of the associations between smoking during pregnancy and selected perinatal outcomes were compared using rates and relative risks. Results Women included in the study population through enhanced reporting were older, less disadvantaged and more commonly resided in urban areas than those recorded as Aboriginal in the birth data. Although rates of smoking and some perinatal outcomes differed between the different study populations, the relative risks of each outcome comparing smoking and non-smoking Aboriginal mothers were very similar when estimated from each of the study populations.
其他摘要：Introduction The under-ascertainment of Aboriginal and Torres Strait Islander status on routinely collected health datasets has important implications for understanding the health of this population. By pooling available information on individuals’ Aboriginal or Torres Strait Islander status from probabilistically linked datasets, methods have been developed to adjust for this under-recording. Objectives To explore different algorithms that enhance reporting of Aboriginal status in birth data to define a cohort of Aboriginal women, examine any differences between women recorded as Aboriginal and those assigned enhanced Aboriginal status, and assess the effects of using different reported populations to estimate within-group comparisons for Aboriginal people. Methods Three algorithms, with different levels of inclusiveness, were used to establish different study populations all of which aimed to include all singleton babies born to Aboriginal or Torres Strait Islander women residing in New South Wales, Australia between 2010 and 2014 and their mothers. The demographics of the four study populations were described and compared using frequencies and percentages. In order to assess the impact on research outcomes and conclusions of using study populations derived from different algorithms, estimates of the associations between smoking during pregnancy and selected perinatal outcomes were compared using rates and relative risks. Results Women included in the study population through enhanced reporting were older, less disadvantaged and more commonly resided in urban areas than those recorded as Aboriginal in the birth data. Although rates of smoking and some perinatal outcomes differed between the different study populations, the relative risks of each outcome comparing smoking and non-smoking Aboriginal mothers were very similar when estimated from each of the study populations. Conclusion This work provides evidence that estimates of within-group relative risks are reliable regardless of the assumptions made for establishing the study population through the enhanced reporting of indigenous peoples.
