Challenges and Opportunities in Analysis of Medical Registry Data

• Activity Number: 112
• Type: Topic Contributed
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Christopher Ake*+
• Companies: Kaiser Permanente
• Keywords: medical registries ; comparative effectiveness ; quality control

Abstract

The continuing development of medical registries will present statisticians with distinctive opportunities. Accumulation of registry data facilitates a variety of observational research studies, but many registries can be used for quality control and improvement as well. Kaiser Permanente's total joint replacement registries (e.g., hips, knees, shoulders) display both functions. In addition to mainstay methods such as the survival analysis used in comparative effectiveness studies of different implant types, statisticians seeking to work with registries like these will benefit from knowledge of causal modeling techniques appropriate to observational data such as propensity score analyses. Understanding of statistical process control methods that optimize ongoing monitoring of infection and other adverse event rates can also be expected to gain in value. When reporting results, the variety of audiences, in this case both within Kaiser (e.g., orthopedic surgeons, nurses, infection control and quality assurance personnel) and beyond (orthopedic journals, national and international meetings, FDA, registries in other countries) places a premium on verbal and visual communication skills