About this Research Topic
In the past decade, there has been an increasing recognition of the powerful role of Social Determinants of Health (SDOH) in shaping people’s health across a broad variety of health outcomes. The World Health Organization defines SDOH as the conditions in which people are born, grow, live, work, and age. These factors include social circumstances and environmental exposure such as education, employment, food, housing, social support, and psychosocial factors. There is a growing body of evidence demonstrating the significant impact of SDOH on a wide range of health outcomes. It has been estimated that SDOH could be responsible for up to 40% of all preventable deaths in the United States, whereas better medical care is responsible for a much smaller proportion, 10–15%, of preventable deaths. All the evidence suggests that efforts to improve health need to look beyond the healthcare system as the key driver of health and start to address the social and environmental factors that influence health outcomes.
In today’s data-rich world, rapid adoption of novel data systems has made large amounts of real-word data available for research, including data related to SDOH. For example, large networks of electronic health record (EHR) systems, such as those in the national Patient-Centered Clinical Research Network (PCORnet), are emerging in the United States. Many SDOH factors are documented in EHRs, including socio-economic status, education, housing, employment, and many more. However, most information on SDOH is embedded in free-text clinical notes, novel clinical natural language processing methods are needed to unlock the enormous amount of SDOH in these notes. Another example is the wide availability of environmental data. Many environmental factors, such as air pollution, are associated with negative health outcomes. However, given the complexity of the environmental data, novel analytic methods, such as machine learning and deep learning techniques, are desired over traditional statistical models. The goal of this Research Topic is to provide a forum for cutting-edge research on the development or applications of novel methods for measuring and analyzing SDOH in health outcomes research.
We are interested in Original Research as well as high-quality Review and Opinion papers that offer innovative perspectives in, but not limited to, the following areas:
(1) Novel methods for measuring and collecting social determinants of health (SDOH)
• Novel methods: natural language processing (NLP), machine learning etc
• Novel data sources: EHRs, social media, census and surveys etc
• Development of novel measures and tools (informatics tools, item banks)
(2) Novel analyses of SDOH data for public health and health outcomes research
• Artificial intelligence (AI)
• Machine learning and deep learning
• New or improvements in analytic methods
(3) Health disparities associated with SDOH
• Patient-reported outcomes and quality of life
• Analyses of disparities in SDOH (e.g., racial) and how they impact health outcomes
• SDOH in vulnerable populations (e.g, sexual and gender minorities, rural residents, etc)
In today’s data-rich world, rapid adoption of novel data systems has made large amounts of real-word data available for research, including data related to SDOH. For example, large networks of electronic health record (EHR) systems, such as those in the national Patient-Centered Clinical Research Network (PCORnet), are emerging in the United States. Many SDOH factors are documented in EHRs, including socio-economic status, education, housing, employment, and many more. However, most information on SDOH is embedded in free-text clinical notes, novel clinical natural language processing methods are needed to unlock the enormous amount of SDOH in these notes. Another example is the wide availability of environmental data. Many environmental factors, such as air pollution, are associated with negative health outcomes. However, given the complexity of the environmental data, novel analytic methods, such as machine learning and deep learning techniques, are desired over traditional statistical models. The goal of this Research Topic is to provide a forum for cutting-edge research on the development or applications of novel methods for measuring and analyzing SDOH in health outcomes research.
We are interested in Original Research as well as high-quality Review and Opinion papers that offer innovative perspectives in, but not limited to, the following areas:
(1) Novel methods for measuring and collecting social determinants of health (SDOH)
• Novel methods: natural language processing (NLP), machine learning etc
• Novel data sources: EHRs, social media, census and surveys etc
• Development of novel measures and tools (informatics tools, item banks)
(2) Novel analyses of SDOH data for public health and health outcomes research
• Artificial intelligence (AI)
• Machine learning and deep learning
• New or improvements in analytic methods
(3) Health disparities associated with SDOH
• Patient-reported outcomes and quality of life
• Analyses of disparities in SDOH (e.g., racial) and how they impact health outcomes
• SDOH in vulnerable populations (e.g, sexual and gender minorities, rural residents, etc)
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
