Search

Manganese (Mn) is an essential metal with a biphasic relationship with health outcomes. High-level exposure to Mn is associated with manganism, but few data explore the effects of chronic, lower-level Mn on cognitive function in adults. We sought to determine the relationship between blood/urinary manganese levels and cognitive function in elderly individuals using 2011–2014 data from the National Health and Nutrition Examination Survey (NHANES). Weighted multivariate regression models were used to determine correlations, adjusting for several covariates. Blood Mn was inversely associated with the Consortium to Establish a Registry for Alzheimer’s Disease (CERAD) immediate learning of new verbal information (p-value = 0.04), but lost significance after adjusting for medical history (p-value = 0.09). In addition, blood Mn was inversely associated with Animal Fluency scores after adjusting for all covariates. Urinary Mn was inversely associated with CERAD immediate learning after adjusting for all covariates (p-value = 0.01) and inversely associated with the Digit Symbol Substitution Test scores (p-value = 0.0002), but lost significance after adjusting for medical history (p-value = 0.13). Upon stratifying by race/ethnicity, other Races and Non-Hispanic (NH)-Blacks had significantly higher blood Mn levels when compared to NH-Whites. Collectively, these findings suggest that increased blood and urinary Mn levels are associated with poorer cognitive function in an elderly US population.

Big data and artificial intelligence are currently two of the most important and trending pieces for innovation and predictive analytics in healthcare, leading the digital healthcare transformation. Keralty organization is already working on developing an intelligent big data analytic platform based on machine learning and data integration principles. We discuss how this platform is the new pillar for the organization to improve population health management, value-based care, and new upcoming challenges in healthcare. The benefits of using this new data platform for community and population health include better healthcare outcomes, improvement of clinical operations, reducing costs of care, and generation of accurate medical information. Several machine learning algorithms implemented by the authors can use the large standardized datasets integrated into the platform to improve the effectiveness of public health interventions, improving diagnosis, and clinical decision support. The data integrated into the platform come from Electronic Health Records (EHR), Hospital Information Systems (HIS), Radiology Information Systems (RIS), and Laboratory Information Systems (LIS), as well as data generated by public health platforms, mobile data, social media, and clinical web portals. This massive volume of data is integrated using big data techniques for storage, retrieval, processing, and transformation. This paper presents the design of a digital health platform in a healthcare organization in Colombia to integrate operational, clinical, and business data repositories with advanced analytics to improve the decision-making process for population health management.