Benchmarking and reducing length of stay in Dutch hospitals

Background: To assess the development of and variation in lengths of stay in Dutch hospitals and to determine the potential reduction in hospital days if all Dutch hospitals would have an average length of stay equal to that of benchmark hospitals. Methods: The potential reduction was calculated using data obtained from 69 hospitals that participated in the National Medical Registration (LMR). For each hospital, the average length of stay was adjusted for differences in type of admission (clinical or day-care admission) and case mix (age, diagnosis and procedure). We calculated the number of hospital days that theoretically could be saved by (i) counting unnecessary clinical admissions as day cases whenever possible, and (ii) treating all remaining clinical patients with a length of stay equal to the benchmark (15(th) percentile length of stay hospital). Results: The average (mean) length of stay in Dutch hospitals decreased from 14 days in 1980 to 7 days in 2006. In 2006 more than 80% of all hospitals reached an average length of stay shorter than the 15th percentile hospital in the year 2000. In 2006 the mean length of stay ranged from 5.1 to 8.7 days. If the average length of stay of the 15th percentile hospital in 2006 is identified as the standard that other hospitals can achieve, a 14% reduction of hospital days can be attained. This percentage varied substantially across medical specialties. Extrapolating the potential reduction of hospital days of the 69 hospitals to all 98 Dutch hospitals yielded a total savings of 1.8 million hospital days (2006). The average length of stay in Dutch hospitals if all hospitals were able to treat their patients as the 15th percentile hospital would be 6 days and the number of day cases would increase by 13%. Conclusion: Hospitals in the Netherlands vary substantially in case mix adjusted length of stay. Benchmarking - using the method presented - shows the potential for efficiency improvement which can be realized by decreasing inputs (e. g. available beds for inpatient care). Future research should focus on the effect of length of stay reduction programs on outputs such as quality of care.