UNSTRUCTURED
With widespread implementation of electronic health records (EHR) came great progress in the development of learning health systems (LHS) to improve health and healthcare delivery through rapid and continuous knowledge generation and translation. To aid LHS in their goals, implementation science (IS) and its frameworks are increasingly being leveraged to ensure LHS are feasible, rapid and iterative, reliable, reproducible, equitable and sustainable. However, six key challenges limit the application of IS to EHR-driven LHS: barriers to team science, limited IS experience, data and technology limitations, time and resource constraints, appropriateness of certain IS approaches, and equity considerations. Using three case studies in diverse health settings and one IS framework, we illustrate these challenges faced by LHS and provide solutions to overcome the bottlenecks to application of IS and use of EHRs that often stymie LHS progress. We discuss lessons learned and also provide recommendations for future research and practice, including the need for more guidance on how to practically apply IS methods and a renewed call for greater generation of and access to inclusive data.