Since 1984, the United States Preventive Services Task Force (USPSTF) has conducted numerous systematic reviews of the evidence for hundreds of preventive services.1 In this manner, the USPSTF determines the level of scientific evidence supporting a preventive care recommendation, assigning well-supported recommendations an evidence grade of A or B. Currently, USPSTF guidelines recommend 50 preventive care services based on grade A or B evidence.2 However, the US health system has yet to maximize the benefit of these preventive care recommendations.3,4 There is underutilization of recommended preventive care services and related evidence of disparities in health outcomes.4-10 Currently, the number of recommended preventive services is more than can be consistently applied in primary care due to time constraints, and is still growing.11 To optimize social benefit, capabilities to prioritize preventive services precisely? based on estimates of anticipated gain for individuals ? are needed.3,4,11 The problem of underutilizing preventive care services represents an important type of problem that the Learning Health System (LHS) must learn to improve. For problems like this, what to do to achieve better health is known but how to do it systematically for a large population remains unknown. Taking a LHS approach to solve such problems is an idea that has gained momentum since a seminal report appeared from the Institute of Medicine.12 When implemented, the LHS has the potential to engender continuous study to bring about effective Individualized Precision Prevention (IPP), resulting in improved population health. Overall, the LHS ?learns? through a cyclical process that engages an interested community in assembly and analysis of data relevant to an important problem, which leads to discovery of new knowledge from the data.13 The learning cycle is completed by direct application of that knowledge to change practice. Changed practice generates new data, driving the next iteration of the learning cycle, with improvement occurring over successive iterations. We envision a learning cycle for improving utilization of preventive services through automated prioritization of preventive services for individuals, ultimately achieving IPP for many people.

Public Health Relevance

By following evidence-based preventive health service recommendations, the health of all people can be improved. The United States Preventive Services Task Force (USPSTF) provides such evidence-based recommendations. As the number and complexity of the USPSTF's recommendations increase, it becomes more challenging for primary care physicians to personalize and prioritize preventive services for their patients. We have built the Knowledge Grid, a scalable infrastructure platform to support curation and rapid, widespread delivery of knowledge into practice. Using the Knowledge Grid, we will make the USPSTF's evidence-based recommendations computable. Then, by complementing the Knowledge Grid with other available technology for extending the electronic health record systems that physicians already use, we will develop and study a systematic, scalable method intended to help primary care providers individualize, in a precise, efficient, and evidence-based way, the preventive health services they deliver to their patients.

Agency
National Institute of Health (NIH)
Institute
Agency for Healthcare Research and Quality (AHRQ)
Type
Exploratory/Developmental Grants (R21)
Project #
5R21HS026257-02
Application #
9733994
Study Section
Healthcare Information Technology Research (HITR)
Program Officer
Wyatt, Derrick
Project Start
2018-07-01
Project End
2020-06-30
Budget Start
2019-07-01
Budget End
2020-06-30
Support Year
2
Fiscal Year
2019
Total Cost
Indirect Cost
Name
University of Michigan Ann Arbor
Department
Other Basic Sciences
Type
Schools of Medicine
DUNS #
073133571
City
Ann Arbor
State
MI
Country
United States
Zip Code
48109