Health systems worldwide struggle to provide the optimal treatment amid the rapid pace of scientific progress and frequent structural changes. Learning health systems (LHS) that continuously analyze their data to generate evidence and to enable informed decisions have been proposed as a possible solution. This paper investigates the involvement of laboratory medicine in LHS and evaluates relevant systems according to their scope, enabling technologies, architecture for evidence generation, data-action latency, and social aspects. While laboratory medicine provides a central source of information in many large-scale LHS, there are also systems with a particular focus on laboratories. For example, external quality assessments are performed by sending samples with known quantities to laboratories worldwide to verify their analytical methods. This data are also analyzed for other purposes, such as post-market surveillance of devices. These schemes have operated successfully over several decades. Newer, innovative tools harvest the possibilities of wearable devices and increased connectivity. LHS in laboratory medicine need to be recognized and incorporated into systems of systems to generate better evidence. Further research on the roles of other stakeholders will identify opportunities and obstacles for building and maintaining successful LHS.