Computer based clinical decision support systems (CDSSs) utilising clinical prediction rules (CPRs) as part of referral for cancer


Session type:

Tom Fahey1
1HRB Centre for Primary Care Research, Dublin, Ireland


Clinical prediction rules (CPRs) are clinical tools that quantify the contribution of the history, physical examination and diagnostic tests and then stratify patients according to the probability of having a target disorder. The outcome of interest can be diverse and range across the diagnostic, prognostic and therapeutic spectrum. The most well-known CPR is the Ottawa ankle rule, which distinguishes ankle sprain from ankle fracture. CPRs go through three distinct stages prior to full implementation in a clinical setting: (1) development of the CPR - establishing the independent and combined effect of explanatory variables that can include symptoms, signs or diagnostic tests; (2) narrow and broad validation - where the explanatory variables or clinical predictors in the derivation CPR set are assessed in separate populations; and lastly (3) impact analysis of the CPR- assessed by means of a RCT (RCT) where the impact of applying the CPR in a clinical setting is measured either by patient outcome, health professional behaviour, resource use or any combination of these outcomes. We have developed and validated a CPR for women with symptomatic breast complaints. The first part of this presentation will discuss the development and validation of CPRs in relation to the diagnosis and referral of patients with suspected cancer, with reference to breast and colorectal cancer.

We will then discuss the implementation of CPRs as part of computer based clinical decision support systems (CDSSs). CDSSs are information systems designed to improve clinical decision making. They have several critical elements: they are integrated with the electronic patient record; they have a computerised knowledge base; and provide patient-specific information delivered via a software algorithm. The potential for developing and implementing referral guidance for cancer by means of CDSSs will form the second part of this presentation, with critical reference to evidence from randomised trials.