Abstract
In current day practice, healthcare professionals are set up with the almost impossible task to translate the daily growing amount of evidence and combine it with all clinical parameters from their patients to what is best. On top of that, value improvement in healthcare is emerging as a response to the growing healthcare costs. The complex balance between multimorbidity, polypharmacy, and potential harms and benefits of interventions, makes care nowadays prone to off label treatment and non-adherence to guidelines, potentially leading to more preventable risk and disease in patients. This sparked the interest into a care system that better integrates clinical practice and evidence: a Learning Healthcare System. A Learning Healthcare System is a continuous cycle of data collection (from routine clinical care in the EHRs), data analysis, interpretation of results, and feedback of potential improvements for patients, healthcare professionals, and policymakers, and implementation of improvements. Using the example of cardiovascular risk management, this thesis answers questions on how routine care data can be used to improve care, how data analytics can support this and how (scientific) evidence could be better implemented in daily practice.
Original language | English |
---|---|
Awarding Institution |
|
Supervisors/Advisors |
|
Award date | 23 Sept 2020 |
Publisher | |
Print ISBNs | 978-94-6402-291-9 |
DOIs | |
Publication status | Published - 23 Sept 2020 |
Keywords
- Learning Healthcare System
- routine care data
- EBM
- EHR data
- data mining
- real-time imputation
- quality of care