Learning Health Systems最新文献

We explored the challenges and solutions for managing data within the Whole Health System (WHS), which operates as a Learning Health System and a patient-centered healthcare approach that combines conventional and complementary approaches. Addressing these challenges is critical for enhancing patient care and improving outcomes within WHS. The proposed solutions include prioritizing interoperability for seamless data exchange, incorporating patient-centered comparative clinical effectiveness research and real-world data to personalize treatment plans and validate integrative approaches, and leveraging advanced data analytics tools to incorporate patient-reported outcomes, objective metrics, robust data platforms. Implementing these measures will enable WHS to fulfill its mission as a holistic and patient-centered healthcare model, promoting greater collaboration among providers, boosting the well-being of patients and providers, and improving patient outcomes.

When researchers are embedded within healthcare systems and collaborate with practitioners and operational leaders, they may be able to rapidly identify problems and opportunities that can be addressed to improve quality and affordability. While other industries have well-developed data exploration processes (e.g., banking), healthcare is still developing its methods with widely varying data sources, huge quantities of unstructured data, uncertain precision in measurement, uncertainties about data quality, and complicated and stringent regulations and policies on data access. In recognition of these challenges, the AcademyHealth Learning Health System (LHS) Interest Group (In 2021, Learning Health Systems journal established a formal relationship with AcademyHealth, serving as the official journal of its LHS Interest Group.) released a call for papers in June 2023 to focus on challenges encountered by investigators related to the use of real-world data in embedded research.

We use the term “embedded researcher” to characterize a broad range of people well-trained in research methods using real-world data. Being located inside a health system, they often have privileged access to data and the practitioners who may be observing new situations, problems, or opportunities for improvement. Unlike colleagues only involved in internal quality improvement efforts, embedded researchers also seek to broadly share their findings and create generalizable knowledge. The sharing is less focused on the specific findings—too many things may be unique about the setting, people, and other factors to be directly generalizable. The challenges faced and techniques used to overcome them, however, may offer important lessons for other embedded researchers.

As LHSs mature and internally tackle increasingly complex problems with embedded research, the challenges presented in using real-world data for locally applied health services research are important to understand. Taken together, the papers in this Special Issue offer insights into the frontiers of embedded research as LHSs embark on their own learning journey. Accelerating the transformation of data to knowledge requires an understanding of the underlying data and techniques needed to draw useful lessons from the data. Sharing experiences across teams and settings will help others in anticipating and addressing the challenges they are likely to encounter.

The learning health system (LHS) model was proposed to provide real-time, bi-directional flow of learning using data captured in health information technology systems to deliver rapid learning in healthcare delivery. As highlighted by the landmark National Academy of Medicine report “Crossing the Quality Chasm,” the U.S. healthcare delivery industry represents complex adaptive systems, and there is an urgent need to develop innovative methods to identify efficient team structures by harnessing real-world care delivery data found in the electronic health record (EHR). We offer a discussion surrounding the complexities of team communication and how solutions may be guided by theories such as the Multiteam System (MTS) framework and the Multitheoretical Multilevel Framework of Communication Networks. To advance healthcare delivery science and promote LHSs, our team has been building a new line of research using EHR data to study MTS in the complex real world of cancer care delivery. We are developing new network metrics to study MTSs and will be analyzing the impact of EHR communication network structures on patient outcomes. As this research leads to patient care delivery interventions/tools, healthcare leaders and healthcare professionals can effectively use health IT data to implement the most evidence-based collaboration approaches in order to achieve the optimal LHS and patient outcomes.

The Adult Medical Care Coordination program (“the program”) was implemented at Mayo Clinic to promote patient self-management and improve 30-day unplanned readmission for patients with high risk for readmission after hospital discharge. This study aimed to evaluate the impact of the program compared to usual care using a pragmatic, stepped wedge cluster randomized trial (“stepped wedge trial”). However, several challenges arose including large differences between the study arms. Our goal is to describe the challenges and present lessons learned on how to overcome such challenges and generate evidence to support practice decisions. We describe the challenges encountered during the trial, the approach to addressing these challenges, and lessons learned for other learning health system researchers facing similar challenges. The trial experienced several challenges in implementation including several clinics dropping from the study and care disruptions due to COVID-19. Additionally, there were large differences in the patient population between the program and usual care arms. For example, the mean age was 76.8 for the program and 68.1 for usual care. Due to these differences, we adapted the methods using the propensity score matching approach that is traditionally applied to observational designs and adjusted for differences in observable characteristics. When conducting pragmatic research, researchers will encounter factors beyond their control that may introduce bias. The lessons learned include the need to weigh the tradeoffs of pragmatic design elements and the potential value of adaptive designs for pragmatic trials. Applying these lessons would promote the successful generation of evidence that informs practice decisions.