Hospital Comparison in the Swiss Inpatient Sector

Do Swiss hospitals provide the same quality to patients?



Patients need reliable quality information to make evidence-based hospital choices. However, hospitals vary in the risk of patients they treat. Thus, a 'fair'comparison requires risk-adjustment.


In this study, we show how machine learning methods can improve risk adjustment in hospital comparisons. Even after risk adjustment, we find that Swiss hospitals vary considerably in the quality they provide to patients. For example, the complication rate for patients undergoing primary hip replacement surgery are more than 230% higher in the 'worst' hospital compared to the average hospital.

This project contributes to the following SDGs

  • 3: Good health and well-being