Use this URL to cite or link to this record in EThOS:
Title: The reliability of statistical investigations into surgical audit data
Author: Pollock, John
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 2002
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
This thesis reviews the established methodology used in the examination of outcomes following surgery of various types. In particular we report on the statistical techniques used in audit studies to assess the relative performance of surgeons and the information within which they work. An analysis is made of a long term sequence of outcomes for patients undergoing surgery for colorectal cancer in a single hospital and we explore the reliability of the inferences on relative performance which can be made. The conclusions drawn from this study are extended by an analysis of outcomes for patients undergoing similar surgery but in several hospitals. We compare traditional statistical approaches with newer computationally intensive techniques which more accurately model the variation between surgeons and institutions. These empirical studies are then used as the basis for an extensive simulation exercise which explores the adequacy of existing statistical methods to detect differences in surgical performance when we know a priori that they do or do not exist. As part of the Bristol Inquiry into paediatric cardiac surgery at that institution we reviewed qualitative aspects of the data which were available for analysis and specifically analysed one set of data on outcomes based on the UK Cardiac Surgical Register. We conclude with a comment on the realistic aims of statistical analysis of surgical audit data and discuss the implications this has for data analysis, clinicians and policymakers.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available