RESUMEN

Uncovering the world's ethnic inequalities is hampered by a lack of ethnicity-annotated datasets. Name-ethnicity classifiers (NECs) can help, as they are able to infer people's ethnicities from their names. However, since the latest generation of NECs rely on machine learning and artificial intelligence (AI), they may suffer from the same racist and sexist biases found in many AIs. Therefore, this paper offers an algorithmic fairness audit of three NECs. It finds that the UK-Census-trained EthnicityEstimator displays large accuracy biases with regards to ethnicity, but relatively less among gender and age groups. In contrast, the Twitter-trained NamePrism and the Wikipedia-trained Ethnicolr are more balanced among ethnicity, but less among gender and age. We relate these biases to global power structures manifested in naming conventions and NECs' input distribution of names. To improve on the uncovered biases, we program a novel NEC, N2E, using fairness-aware AI techniques. We make N2E freely available at www.name-to-ethnicity.com. Supplementary Information: The online version contains supplementary material available at 10.1007/s00146-022-01619-4.

RESUMEN

Precision (or personalized) medicine holds great promise in the treatment of breast cancer. The success of personalized medicine is contingent upon inclusivity and representation for minority groups in clinical trials. In this article, we focus on the roadblocks for the African American demographic, including the barriers to access and enrollment in breast oncology trials, the prevailing classification of race and ethnicity, and the need to refine monolithic categorization by employing genetic ancestry mapping tools for a more accurate determination of race or ethnicity.

Asunto(s)

RESUMEN

BACKGROUND: Race and ethnicity classification systems have considerable implications for public health, including the potential to reveal or mask inequities. Given increasing "super-diversity" and multiple racial/ethnic identities in many global settings, especially among younger generations, different ethnicity classification systems can underrepresent population heterogeneity and can misallocate and render invisible Indigenous people and ethnic minorities. We investigated three ethnicity classification methods and their relationship to sample size, socio-demographics and sexual health indicators. METHODS: We examined data from New Zealand's HIV behavioural surveillance programme for men who have sex with men (MSM) in 2006, 2008, 2011, and 2014. Participation was voluntary, anonymous and self-completed; recruitment was via community venues and online. Ethnicity allowed for multiple responses; we investigated three methods of dealing with these: Prioritisation, Single/Combination, and Total Response. Major ethnic groups included Asian, European, indigenous Maori, and Pacific. For each classification method, statistically significant associations with ethnicity for demographic and eight sexual health indicators were assessed using multivariable logistic regression. RESULTS: Overall, 10,525 MSM provided ethnicity data. Classification methods produced different sample sizes, and there were ethnic disparities for every sexual health indicator. In multivariable analysis, when compared with European MSM, ethnic differences were inconsistent across classification systems for two of the eight sexual health outcomes: Maori MSM were less likely to report regular partner condomless anal intercourse using Prioritisation or Total Response but not Single/Combination, and Pacific MSM were more likely to report an STI diagnosis when using Total Response but not Prioritisation or Single/Combination. CONCLUSIONS: Different classification approaches alter sample sizes and identification of health inequities. Future research should strive for equal explanatory power of Indigenous and ethnic minority groups and examine additional measures such as socially-assigned ethnicity and experiences of discrimination and racism. These findings have broad implications for surveillance and research that is used to inform public health responses.

Asunto(s)

RESUMEN

OBJECTIVE: We investigate surname affinities among areas of modern-day China, by constructing a spatial network, and making community detection. It reports a geographical genealogy of the Chinese population that is result of population origins, historical migrations, and societal evolutions. MATERIALS AND METHODS: We acquire data from the census records supplied by China's National Citizen Identity Information System, including the surname and regional information of 1.28 billion registered Chinese citizens. We propose a multilayer minimum spanning tree (MMST) to construct a spatial network based on the matrix of isonymic distances, which is often used to characterize the dissimilarity of surname structure among areas. We use the fast unfolding algorithm to detect network communities. RESULTS: We obtain a 10-layer MMST network of 362 prefecture nodes and 3,610 edges derived from the matrix of the Euclidean distances among these areas. These prefectures are divided into eight groups in the spatial network via community detection. We measure the partition by comparing the inter-distances and intra-distances of the communities and obtain meaningful regional ethnicity classification. DISCUSSION: The visualization of the resulting communities on the map indicates that the prefectures in the same community are usually geographically adjacent. The formation of this partition is influenced by geographical factors, historic migrations, trade and economic factors, as well as isolation of culture and language. The MMST algorithm proves to be effective in geo-genealogy and ethnicity classification for it retains essential information about surname affinity and highlights the geographical consanguinity of the population.

Asunto(s)