A Learning Healthcare System is defined, by the Institute of Medicine (IoM) (Institute of Medicine 2015), as a system in which,
“science, informatics, incentives, and culture are aligned for continuous improvement and innovation, with best practices seamlessly embedded in the delivery process and new knowledge captured as an integral by-product of the delivery experience.”
The term has been promoted by the IoM, whose many publications on the topic have provided a backbone to the literature (Institute of Medicine 2015). Professor Friedman describes a cycle with processes that are common to all Learning Health Systems (Friedman 2014):
Figure 2. The Learning Health System Cycle. Reproduced from Friedman 2014
According to Professor Friedman, any Learning Healthcare System has three components (Friedman 2015):
1. Afferent (Blue) side:
o Assemble the data from various sources
o Analyse the data by various means
o Interpret the findings
2. Efferent (Red) side:
o Feeding findings back into the system in various formats
o Changing practice
3. Scale: Can be institutional, national, international
A Learning Healthcare System is a sociotechnical system (Wallace 2015). The blue/afferent side is made possible by recent technical innovations, but red/efferent side is an enormous interdisciplinary challenge incorporating, behavioural psychology, communication science, implementation science, behavioural economics, policy science and organisational theory (Friedman 2015).
Such systems can be based on any of the cyclical improvement approaches, such as Plan, Do, Study, Act, but they explicitly use technical and social approaches to learn and improve with every patient who is treated. In this review, we focus on behaviour change techniques as an effective mechanism to ensure that knowledge generated by Learning Healthcare Systems is fed back into the system to achieve change (the red side of the cycle).
There is no single Learning Healthcare System. Rather there are many manifestations, at different scales. It could be a department that tracks its patient’s outcomes in order to learn and improve its practice. It could be a provider that builds predictive models, from elements of its EHR, which allow it to forecast demand and reallocate resources more effectively. It could be a national distributed network drawing tens of millions of patient records from multiple providers, to assess the effectiveness of particular treatment.
This website contains links to many Learning Health System Projects around the world. Each demonstrates one or more of six key use cases that meet the definition of a Learning Healthcare System and they represent areas in which significant progress has been made:
- Intelligent Automation
- Comparative Effectiveness Research
- Positive Deviance
- Predictive Modelling
- Clinical Decision Support
Electronic Health Records provide a data source and a user interface to many Learning Healthcare Systems, but on their own, they do not represent the entire sociotechnical cycle outlined in Figure 2.
Many healthcare systems have been using electronic products to improve their services for a considerable time. These have included (Cotton, R., et al. 2014):
- Information Websites
- Mobile Apps
- Service Directories
- Online Appointment Booking
- Social Media Presence
These and other systems may be valuable and are likely to be rolled out more widely in the years to come, but they are outwith the scope of this report, except where they form part of a Learning Healthcare System.
Learning Healthcare Systems have major, workforce, organisational, regulatory and economic implications for society. These are discussed in the section entitled Implications. The development of these systems is neither inevitable nor likely to be universally welcomed. Further work is required to ensure that they realise their potential to improve healthcare and this is discussed in the section entitled Themes for the Future.
Toward a science of learning systems: a research agenda for the high-functioning Learning Health System