Cancer decision support tools overview
Questions about the tools?
Contact us if you have questions about the tools
Cancer decision support tools are designed to support GPs in assessing patients with potential cancer symptoms. The tools do not replace clinical judgement, but give more information that can be used to inform patient management decisions. They tend to be underpinned by algorithms that calculate the risk of a patient having an undiagnosed cancer based on various data inputs. Several algorithms have now been developed.
Some algorithms are based on symptoms alone, whilst others also take into account other factors such as patient age and gender. There’s interest in how the tools in which these algorithms are incorporated can prompt and remind GPs about potential cancer risk that they can draw on in their management of patients
RATs are designed to be used in symptomatic populations presenting to primary care. There are currently tools available for 14 different cancer types, which provide risk estimates for patients with single symptoms, pairs of symptoms and repeat attendances with the same symptom. They are traditionally in table format, but have also been incorporated into electronic format.
QCancer have developed risk models which can be used in both symptomatic and asymptomatic populations. The QCancer tool for symptomatic populations provides absolute risk of all cancers combined, as well as a breakdown of risk for 12 different cancer types individually, based on both risk factors (such as age, gender and family history) and symptoms.
Non-web based decision support tools were initially in operation, such as the desk easel and mouse mat versions of the RAT tool. However, electronic versions, known as electronic cancer decision support tools (eCDS), are now more common. As well as functioning as standalone online risk calculators, the software can also be integrated into GP computer systems.
Using either the RAT or QCancer algorithms, eCDS tools calculate the risk that a patient may have cancer based on inputted factors such as symptoms, medical history and demographic data.
General functionalities that may be included within an eCDS tool:
- An automated prompt that draws on the information in a patient’s medical record and sends an alert if the calculated score exceeds a set threshold
- A symptom checker that provides a cancer risk score based on symptoms entered onto the system
- A risk stratification list draws on medical data within patient records and produces a list of all patients within that practice exceeding a set threshold of risk.
Macmillan have developed an integrated cancer decision support tool in collaboration with BMJ Informatica. The tool makes use of both eRAT and QCancer software.
Other major GP providers are developing integrated versions e.g. EMIS working with QCancer
At the moment there aren’t any published peer-reviewed randomised controlled trials on the use of CDS tools in practice.
The ECASS trial, a phase II randomised controlled trial evaluating use of a computer aid for assessing stomach symptoms in patients with suspected oesophageal cancer is currently in progress.
There are also a number of evaluation and several feasibility studies.
CRUK's evaluation of eCDS tool
Cancer Research UK coordinated an independent evaluation of the 2013 Macmillian pilot of the eCDS tool, which used the BMJ Informatica platform.
During Macmillan’s pilot GPs from over 400 practices across England had access to the software between March and November 2013.
The GPs were divided into two groups, with one group being presented with results from the Risk Assessment Tool and the other results from QCancer.
Cancer Research UK analysed the data collected and one of the Department of Health’s Policy Research Units also gathered feedback from interviews with patients and GPs, to get qualitative feedback on the use of the eCDS tool.
What are the effects of using the eCDS tool?
Overall, the pilot evaluation suggests that the eCDS can:
- raise GPs’ awareness of cancer symptoms
- alert and remind GPs when patients are potentially at risk
- influence the decisions GPs make about how to care for patients
In nearly a fifth (19%) of cases where GPs provided feedback, they reported that had they not used the symptom checker, they would not have referred/investigated the patient.
GPs also expressed some concerns:
- they didn’t always agree with or understand how to interpret the risk scores produced for their patients
- the risk scores produced rely on data recorded in a patient’s medical records – which may not necessarily be 100% accurate. This could flag patients who aren’t actually at risk or miss others who are
- they could end up with ‘prompt fatigue’ because of how regularly the programmes prompt them alongside existing computer prompts
- in a 10-minute consultation it was sometimes difficult to use the symptom checker function properly
- some GPs felt they weren’t focusing on interacting and talking to their patients as they would be looking at their computers more
Limitations of the evaluation
- participation and feedback from the GPs was optional. This means that the data on how the eCDS was used isn’t comprehensive and may not be representative.
- it wasn’t possible to get data on measures such as whether referred patients went on to be diagnosed with cancer, or the stage at which patients were diagnosed during the pilot. It’s therefore not possible to demonstrate that use of the eCDS lead to earlier diagnoses or improved outcomes for patients.
- the evaluation findings are therefore principally able to provide insights into how the eCDS influences GP’s decision making and GP and patient views and experiences of using the programmes, including how they could be improved.
Accelerate Coordinate Evaluate (ACE)
The NHS led ACE programme, which Cancer Research UK is involved in, is also exploring the impact of using eCDS tools on diagnostic decision making for cancer diagnosis.
We’re now on twitter.
The University of Manchester are currently conducting a survey into healthcare professionals' and public attitudes towards sun exposure and vitamin D.