Frontiers in public health · 2026
Unsupervised discovery of public health subgroups associated with cognitive health vulnerability in adults: an analysis of BRFSS 2024.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Ziyue, Dookhy Joshi, Khaleghy Hossein, Maji Soumyajyoti, Yang Xuejia, Geoghegan Carmel, Chen Jia
Аннотация
BACKGROUND: Cognitive health-related vulnerability is closely associated with multidimensional public health factors, including chronic disease burden, functional limitation, healthcare access, socioeconomic vulnerability, health behaviors, and preventive service utilization. However, latent population heterogeneity embedded in routine public health survey variables remains insufficiently explored.
OBJECTIVE: This study aims to develop an unsupervised semantic stratification framework based on BRFSS 2024 data to identify adult population subgroups associated with cognitive health-related vulnerability from a public health perspective.
METHODS: Routine public health variables were selected, cleaned, imputed, and standardized, while cognitive reference variables were excluded from model training. An autoencoder was used to learn low-dimensional latent representations, followed by MiniBatchKMeans clustering to identify semantic subgroups. Each subgroup was further analyzed through public health profiling, held-out cognitive reference validation, non-redundant feature signature analysis, and intervention priority assessment.
RESULTS: Four interpretable semantic subgroups were identified: the low-burden subgroup, general health vulnerability subgroup, health behavior risk subgroup, and preventive service gap subgroup. These subgroups showed distinct patterns in public health burden, cognitive reference variables, key feature signatures, and intervention priorities.
CONCLUSION: Routine public health survey data can support the identification of latent adult subgroups associated with cognitive health-related vulnerability and provide exploratory evidence for population monitoring, priority screening, resource allocation, and stratified intervention design. This framework is not a diagnostic, prognostic, or causal inference model, and further validation using weighted, longitudinal, cross-year, and external data is needed.
OBJECTIVE: This study aims to develop an unsupervised semantic stratification framework based on BRFSS 2024 data to identify adult population subgroups associated with cognitive health-related vulnerability from a public health perspective.
METHODS: Routine public health variables were selected, cleaned, imputed, and standardized, while cognitive reference variables were excluded from model training. An autoencoder was used to learn low-dimensional latent representations, followed by MiniBatchKMeans clustering to identify semantic subgroups. Each subgroup was further analyzed through public health profiling, held-out cognitive reference validation, non-redundant feature signature analysis, and intervention priority assessment.
RESULTS: Four interpretable semantic subgroups were identified: the low-burden subgroup, general health vulnerability subgroup, health behavior risk subgroup, and preventive service gap subgroup. These subgroups showed distinct patterns in public health burden, cognitive reference variables, key feature signatures, and intervention priorities.
CONCLUSION: Routine public health survey data can support the identification of latent adult subgroups associated with cognitive health-related vulnerability and provide exploratory evidence for population monitoring, priority screening, resource allocation, and stratified intervention design. This framework is not a diagnostic, prognostic, or causal inference model, and further validation using weighted, longitudinal, cross-year, and external data is needed.