A Risk-Adjusted O-E CUSUM with a V-Mask for Monitoring Medical Outcomes

• Activity Number: 74
• Type: Contributed
• Date/Time: Sunday, August 2, 2009 : 4:00 PM to 5:50 PM
• Sponsor: Section on Physical and Engineering Sciences
• Author(s): Rena Jie Sun*+ and John D. Kalbfleisch
• Companies: University of Michigan and University of Michigan
• Keywords: Cumulative SUM (CUSUM) ; failure time data ; Sequential tests ; Risk adjustments ; V-mask ; quality control and improvement

Abstract

Motivated by a risk-adjusted one-sided CUSUM procedure within a continuous time setting, we introduce an O-E (Observed-Expected) CUSUM along with a V-mask decision criterion to simultaneously monitor for failure time outcomes that are 'worse than expected' or 'better than expected.' Appropriate V-masks are obtained for facilities of different sizes by controlling the false alarm rate over a period of given length, and simulation studies are conducted to test the performance of the proposed method, and to compared it to the one-sided CUSUM approach. A case study is carried out for 58 liver transplant programs, using the proposed O-E CUSUM, the one-sided CUSUM, and methods currently in use for flagging centers for review. The use of CUSUM methods fro quality improvement is stressed.