The concept of learning health systems, where the data generated through routine care is used to produce knowledge, has become increasingly popular. This paper explores one US example of a learning health system, from which the authors conclude that learning health systems are rich in potential but may face technical and social challenges in realizing their ideals.
Focused on cystic fibrosis, the system enables patients to enter their own data. This is then combined with routine clinical information, feeding a shared dashboard that can be viewed by patients and health professionals at the same time with the aim of facilitating better partnerships. The data can also be used to support improvements in care and research.
This study showed that those involved in the design of the learning system were in consensus that the goal of enabling patients and clinicians to become confident, competent, and equal partners who can share decisions was a very valuable one. But achieving that goal was challenging. Technical problems, including interoperability between different information systems and avoiding information overload, were not straightforward to resolve. Also challenging was the attempt to shift the nature of the patient-clinician relationship, particularly in the time-challenged context of busy clinics. Some concerns were also expressed about the potential for data collected by the learning system to be used for surveillance purposes.
To develop these insights, the authors interviewed individuals involved in the design, implementation, and evaluation of a learning health system for cystic fibrosis in the US.
In this new article from Implementation Science, Dixon-Woods et al. explore why learning health systems use data and analytics from patients’ electronic health records and other digital resources to identify opportunities to improve the quality of care. However, research into setting up learning systems has been limited. This study aims to address this gap, producing findings that may help others developing learning systems.