Health data scientists from PKUHSC launched the CKD LHS study in collaboration with doctors and epidemiologists from Yanzhou city.Credit: Guilan Kong et al.
× close
Health data scientists from PKUHSC launched the CKD LHS study in collaboration with doctors and epidemiologists from Yanzhou city.Credit: Guilan Kong et al.
recent publications health data science provides an in-depth exploration of an innovative approach to chronic kidney disease (CKD) management through the adoption of a learning health systems (LHS) model. This study highlights transformative changes towards more responsive and efficient medical practice, especially in the management of prevalent diseases such as CKD.
In medicine, the path from research discovery to clinical application is notoriously long, often taking nearly 20 years. The LHS framework aims to dramatically shorten this trajectory by leveraging real-time data analytics, thereby rapidly translating research insights into real-world medical interventions.
Guilan Kong, Associate Research Professor at Peking University's National Institute of Health Data Science (NIHDS), highlighted the important role of LHS in accelerating the data-to-evidence-to-practice continuum, and said this progress would be a global in the digital age, which he believes is essential to improving health outcomes.
Targeting CKD, a prevalent but poorly controlled condition in China, the research team piloted the LHS initiative in the city of Yanzhou. The district features a sophisticated Regional Health Information Platform (YRHIP), which has been in operation since 2009. This platform is essential for local healthcare. Landscape collects comprehensive patient data across a variety of healthcare institutions and has been instrumental in the development of his professional CKD surveillance system, launched in 2018.
Project launch included assembling a diverse learning community including physicians, IT experts, and data scientists to jointly assess CKD care in Yinzhou and identify and address critical care delivery gaps . This collaborative effort enabled the identification of his CKD patients through advanced computational tools, facilitating targeted interventions by primary care providers.
The researchers highlight the potential to integrate predictive analytics and clinical decision support mechanisms into YRHIP, with the aim of enhancing patient triage, streamlining referrals, and facilitating the adoption of clinical guidelines.
NIHDS Professor Luxia Zhang reflected on the pilot's promising results and suggested that a robust LHS infrastructure can greatly facilitate the adoption of evidence-based medical solutions. Although the LHS model is prevalent in more affluent settings, applying her LHS model in less economically developed regions presents unique challenges and opportunities for innovation.
Looking to the future, the research team plans to improve CKD predictive analytics and further integrate these technologies into Yinzhou's medical framework, allowing doctors to make more informed decisions. Professor Kong believes this will improve the standard of CKD treatment.
For more information:
Guilan Kong et al., “Transforming healthcare through a learning health system approach in the digital age: Chronic kidney disease management in China.” health data science (2023). DOI: 10.34133/hds.0102
Health data science provided
