domingo, 9 de junio de 2019

Can Predictive Analytics Drive Implementation Research to Improve Population Health? | | Blogs | CDC

Can Predictive Analytics Drive Implementation Research to Improve Population Health? | | Blogs | CDC

Centers for Disease Control and Prevention. CDC twenty four seven. Saving Lives, Protecting People



Can Predictive Analytics Drive Implementation Research to Improve Population Health?

Posted on  by Michael Engelgau, George A. Mensah, Center for Translation Research and Implementation Science, National Heart, Lung, Blood Institute, National Institutes for Health, Bethesda, Maryland and Muin J. Khoury, Office of Public Health Genomics, Centers for Disease Control and Prevention, Atlanta, Georgia

a crowd of people incased in an upward arrow with a magnifying glass on them with DNA

To date, research investments have yielded many highly effective health interventions for disease prevention and treatment. Examples include smoking cessation, lipid and blood pressure control as well as diet and physical activity interventions. Yet, many interventions are not being optimally delivered to have public health impact. Implementation research can provide a means to determine optimal and sustainable strategies to deliver health interventions. To improve implementation research, novel tools are needed to tap into many sources of information and develop models for health outcomes at the individual, population, and system levels. Enter predictive analytics!

What is Predictive Analytics?

Predictive analytics in health is a set of analytic procedures that take existing information and forecast future probabilities of disease patterns, health behaviors, and other variables, using population- and individual-level data along with biomedical and other types of data. These data can then driveanalytic models that can influence health decision making – at both the individual and population levels. This is much different from the traditional hypothesis-driven biomedical research. Predictive analytics uses statistical algorithms, comprehensive data (e.g., geospatial, burden of disease, demography, variation in community and health care capacity and in local resources settings), and strives to understand complex interrelationships between determinants of health and the variability of health care and public health service delivery—and the likelihood of future health outcomes. Predictive analytics could help forecast potential solutions for populations, specifically vulnerable population subgroups, by simulating implementation strategies and then exploring the facilitators and challenges in specific contexts—while simultaneously considering available resources and capacity.

How Can Predictive Analytics be Used to Improve Implementation Research?

So far, predictive analytics has been used mostly as a business tool. Businesses may use current and past data to better understand their customers, products, and competitors while also identifying potential opportunities and risks. This approach is not hypothesis driven. Rather, the data drive the analytical direction seeking novel relationships. For population health, understanding how the community context can facilitate delivery of health interventions is key. Predictive analytics can simulate a wide variety of clinical-, systems-, and population-level delivery interventions and also predict outcome measures and forecast results from selected intervention delivery scenarios. Predictive analytics can help determine efficient implementation research strategies that then can be tested in delivery systems.
Our recent paper illustrates many examples of the uses of predictive analytics—from uses in individuals, populations, and health systems, and data incorporation with the goal of predicting disease risk or health events. The spectrum of data sources can range from public health surveillance and epidemiology to social media which provide a range of results that include identifying disease burdens and risk factors, high health risk states, as well as strategies to target resources at high-risk or high-burden groups. A common theme is the use of large amounts of data, and in some cases, multiple types of data—beyond traditional health-related data—and to use them in innovative ways.
Predictive analytics models can incorporate large amounts of data from many domains and simulate the complex environments where interventions are delivered. These simulations may prove to be a valuable asset because they may be able to refine and make more efficient the implementation research agenda. This becomes even more important under current scenarios of limited resources especially in developing countries.
Predictive analytics has many limitations. We need to better understand how prediction models actually impact health related decisions, individual and population health outcomes, costs, and quality of care. While we can identify health information that is enlightening, whether it triggers a health decision action can be challenging. Other technical challenges include linking of data sources, data quality, model validation and evaluation of utility, as well as provider, consumer and health system education and preparedness.
These are the early days in the use of predictive analytics for implementation research in health. For research and public health agencies alike, realizing a vision for health impact will benefit from careful exploration and evaluation of predictive analytics technologies to inform the next generation of implementation research studies to improve population health.
Posted on  by Michael Engelgau, George A. Mensah, Center for Translation Research and Implementation Science, National Heart, Lung, Blood Institute, National Institutes for Health, Bethesda, Maryland and Muin J. Khoury, Office of Public Health Genomics, Centers for Disease Control and Prevention, Atlanta, Georgia

Tags 

No hay comentarios:

Publicar un comentario