The importance of social components of health has been emphasized both in epidemiology and public health. This paper highlights the significant impact of social components on health outcomes in a novel way. Introducing the concept of sociomarkers, which are measurable indicators of social conditions in which a patient is embedded, we employed a machine learning approach that uses both biomarkers and sociomarkers to identify asthma patients at risk of a hospital revisit after an initial visit with an accuracy of 66%. The analysis has been performed over an integrated dataset consisting of individual-level patient information such as gender, race, insurance type, and age, along with ZIP code-level sociomarkers such as poverty level, blight prevalence, and housing quality. Using this uniquely integrated database, we then compare the traditional biomarker-based risk model and the sociomarker-based risk model. A biomarker-based predictive model yields an accuracy of 65% and the sociomarker-based model predicts with an accuracy of 61%. Without knowing specific symptom-related features, the sociomarker-based model can correctly predict two out of three patients at risk. We systematically show that sociomarkers play an important role in predicting health outcomes at the individual level in pediatric asthma cases. Additionally, by merging multiple data sources with detailed neighborhood-level data, we directly measure the importance of residential conditions for predicting individual health outcomes.

Background: Adverse Childhood Experiences (ACEs), a set of negative events and processes that a person might encounter during childhood and adolescence, have been proven to be linked to increased risks of a multitude of negative health outcomes and conditions when children reach adulthood and beyond. Objective: To better understand the relationship between ACEs and their relevant risk factors with associated health outcomes and to eventually design and implement preventive interventions, access to an integrated coherent dataset is needed. Therefore, we implemented a formal ontology as a resource to allow the mental health community to facilitate data integration and knowledge modeling and to improve ACEs’ surveillance and research. Methods: We use advanced knowledge representation and semantic Web tools and techniques to implement the ontology. The current implementation of the ontology is expressed in the description logic ALCRIQ(D), a sublogic of Web Ontology Language (OWL 2). Results: The ACEs Ontology has been implemented and made available to the mental health community and the public via the BioPortal repository. Moreover, multiple use-case scenarios have been introduced to showcase and evaluate the usability of the ontology in action. The ontology was created to be used by major actors in the ACEs community with different applications, from the diagnosis of individuals and predicting potential negative outcomes that they might encounter to the prevention of ACEs in a population and designing interventions and policies. Conclusions: The ACEs Ontology provides a uniform and reusable semantic network and an integrated knowledge structure for mental health practitioners and researchers to improve ACEs’ surveillance and evaluation.

Social networks, broadly defined as interconnectedness with other people, can influence behavioral and health outcomes.^1-3 The importance of social and relational environments for cognitive development and emotional well-being is well known.^4-8 Networks of social support can attenuate psychologic stress and provide support to people experiencing neurotic symptoms.^9-12 The progress that children make when forming healthy relationships during the period from birth to 5 years can have long-lasting benefits throughout their entire lives.¹³ In early childhood development, relationships between children and caregivers are crucial and play an important role in socialization.^14-17 The social environment and relationships early in life are critical for children’s emotional, intellectual, and social development into adulthood and can considerably influence the child’s life-long adaptation strategy.^6,13,18-21 Social networks channel benefits and risks associated with social health determinants, such as health-related knowledge, attitudes, and capacity to cope with adversities associated with social disadvantage.^1,4,6,22-24

In this paper, we investigate the relationships between dwelling conditions and pediatric asthma prevalence, merging multiple data sources to unpack disproportionate pediatric asthma prevalence in Memphis, TN, USA. Using 32 097 pediatric asthma encounter data from a children's hospital, we map the patient distributions in Memphis. Connecting these data with 244 000 property quality data and census data, we show that pediatric asthma is disproportionately prevalent in the bad quality neighborhoods, even after controlling for ethnicity and poverty level. Furthermore, we show that the neighborhood inequality has a more negative effect than the overall neighborhood degeneration. Our novel data integration provides a unique opportunity to directly test the relationship between residential qualities and asthma prevalences at the macro-level, and to the best of our knowledge, this study is the first study that investigates the association between the detailed property quality and pediatric asthma with a relatively large sample size. Moreover, directly connecting health outcomes with the detailed housing quality data enables us to unpack how the inequality in living conditions yields disproportionate public health outcome distributions. To further improve public health decision making, the health issue should be approached with a more holistic view with taking into account environmental, residential, and social conditions. Integrating multiple data sources helps us not only discover the hidden links between quality of housing and childhood asthma in an urban community but also provide more efficient health surveillance guidelines to identify the population at risk. We show that neighborhood blight and inequality are closely associated with childhood asthma and other consecutive health problems, and therefore, any effective health intervention should also consider consolidation of housing policies and procedures. In addition, the detailed neighborhood level data helps us to reveal the pathways of social inequalities to health disparities and improve the public health through a properly designed surveillance system.

Background: Breast cancer is one of the most commonly diagnosed cancers among women in the United States and pain is the most common side effect of breast cancer and its treatment. Yet, the relationships between social determinants of pain and pain experience/intensity remain under-investigated. We examined the associations between social determinants of pain both at the individual level and the neighborhood level to understand how social conditions are associated with pain perception among early stage breast cancer patients. Methods: We conducted integrated statistical analysis of 1,191 women with early stage breast cancer treated at a large cancer center in Memphis, Tennessee. Combining electronic health records, patient-reported data and census data regarding residential address at the time of first diagnosis, we evaluated the relationships between social determinants and pain perception. Pain responses were self-reported by a patient as a numerical rating scale score at the patient’s initial diagnosis and follow-up clinical visits. We implemented two sets of statistical analyses of the zero-inflated Poisson model and estimated the associations between neighborhood poverty prevalence and breast cancer pain intensity. After adjustment for demographic characteristics, cancer stage, and chemotherapy, pain perception was significantly associated with poverty and blight level of the neighborhood. Results: Among women living in the highest-poverty areas, the odds of reporting pain were 2.48 times higher than those in the lowest-poverty area. Women living in the highest-blight area had 5.43 times higher odds of reporting pain than those in the lowest-blight area. Neighborhood-level social determinants were significantly associated with pain intensity among women diagnosed with early-stage breast cancer. Conclusions: Distressed neighborhood conditions are significantly associated with higher pain perception. Breast cancer patients living in socio-economically disadvantaged neighborhoods and in poor environmental conditions reported higher pain severity compared to patients from less distressed neighborhoods. Therefore, post-diagnosis pain treatment design needs to be tailored to the social determinants of the breast cancer patients.

In this study, we reveal the distinctive communication network structures and contents of online breast cancer community posts in accordance with different cancer stages. Using data collected from community.breastcancer.org, a major online breast cancer community (28,139 original posts and 663,748 replies), we traced the communication network structures and contents of replies associated with its severity. By combining network and quantitative content analyses, we deciphered the functions and utilities of health-related online communication. We found an inverse relationship between offline epidemiological prevalence and online communication activation. Despite the relatively small percentage of breast cancer patients, it was found that the more severe the condition of breast cancer, the more active online communication was. We further found that as pathological severity advances, communication networks move from informational exchange to emotional support. The capture of online social networks based on the cancer stage can help unpack the distinctive communication patterns found across different cancer severities. Our results provide insights into a possible online communication intervention design tailored to symptom severity.