It probably worked: a Bayesian approach to evaluating the introduction of activity-based hospital payment in Israel

Background In 2013-2014, Israel accelerated adoption of activity-based payments to hospitals. While the effects of such payments on patient length of stay (LoS) have been examined in several countries, there have been few analyses of incentive effects in the Israeli context of capped reimbursements and stretched resources. Methods We examined administrative data from the Israel Ministry of Health for 14 procedures from 2005 to 2016 in all not-for-profit hospitals (97% of the acute care beds). Survival analyses using a Weibull distribution allowed us to examine the non-negative and right-skewed data. We opted for a Bayesian approach to estimate relative change in LoS. Results LoS declined in 7 of 14 procedures analyzed, notably, in 6 out of 7 urological procedures. In these procedures, reduction in LoS ranged between 11% and 20%. The estimation results for the control variables are mixed and do not indicate a clear pattern of association with LoS. Conclusions The decrease in LoS freed resources to treat other patients, which may have resulted in reduced waiting times. It may have been more feasible to reduce LoS for urological procedures since these had relatively long LoS. Policymakers should pay attention to the effects of decreases in LoS on quality of care. Stretched hospital resources, capped reimbursements, retrospective subsidies and underpriced procedures may have limited hospitals' ability to reduce LoS for other procedures where no decrease occurred (e.g., general surgery).