These are exciting times. More than ever before, patients, the public and healthcare professionals need access to information to make informed choices and ensure high quality care.
The team at HDI understands the NHS and how it works or sometimes does not. We are experts in finding and joining up complex healthcare data and we use this to gain insight and an understanding of how care is delivered.
We develop software tools to help present information in an accessible way and we work with a range of customers in the NHS, local government, charities and industry to help them understand and access healthcare information.
"Making healthcare information work for people"
HDI has been awarded a Cancer Research UK Pioneer Award for research to improve the early diagnosis of cancer using machine learning and computer-based inference algorithms. We will analyse very large linked and unlinked datasets to ask:
1) Is it possible to identify patterns in medication given prior to the diagnosis of cancer and other data to derive an “index of suspicion” that a patient is at increased likelihood of developing subsequent cancer?
- for different types of cancer; our suspicion is that the index may be most valuable for patients with cancers that present with vague symptoms – e.g. pancreatic, ovarian, stomach or brain cancer.
- for different stages of presentation of the same cancer: for example, can we use the index to help identify common cancers at an earlier stage when they would have a better prognosis?
2) Using the index of suspicion derived in 1), can we risk-stratify patients in the unlinked prescription data to identify those who might be most at risk of developing a particular cancer?
By detecting and clustering patterns in prescriptions and other data such as combinations of medication and comorbidities, we expect to be able to identify typical patients or coincident treatments. This will allow us to build human-readable predictive models for outcomes such as future cancer diagnosis grouped by cancer site and stage of presentation of the potential cancer. Odds’ ratios, flowcharts that users can understand, numerical predictions of risk scores and the likely error rates will also be produced from these models.
When applied to the whole population this approach may allow the risk-stratification of patients with an increased likelihood of presenting with cancer and help GPs to prioritise which patients to refer for further investigation or place on active follow-up.
‘Index of Suspicion’ in the news:
Researchers are compiling an anonymous dataset of primary care prescription data – totalling 80m prescriptions a month – to identify patterns that could help GPs catch cancer earlier. Scientists will use GP data to look for trends in medications given to patients before they were diagnosed with cancer – allowing them to flag up any new patients who exhibit similar tell-tale signs and may need referring for further tests.
Cancer Research UK-funded scientists are examining of finding patterns in medication given to patients before they develop cancer could improve early diagnosis. Looking for patterns in prescriptions and other data could help guide GP referrals, especially in patients with non-specific symptoms that don’t obviously indicate cancer.
Britain has one of the lowest cancer survival rates in Western Europe This is partly attributed to family doctors diagnosing the illness too late Trial launched to examine 960m prescriptions handed out by GPs each year Patients could be diagnosed with cancer more quickly if GPs examined their past prescriptions, scientists claim.
COMPUTER SAYS CANCER Researchers are going through millions of NHS records to find links COMPUTERS could spot cancer early by looking for patterns in patients’ prescription and medical history, scientists say. Researchers from Health Data Insight are trawling through millions of NHS records to try to identify these links.
Below are a selection of our projects. Click on an image to read details of the project.
HDI is a social enterprise that has been set up to act as a trusted and reliable Information Broker. We aim to do three things:
Improve access to data and information to all existing and potential users, providers and commissioners of healthcare services.
Provide Valuable Resource
Help patients and the public to understand the value of their own and other healthcare data by providing guidance and interpretation that supports informed choice and access across healthcare providers.
Improve Care Pathways
Support commissioners and providers in the delivery of improved care pathways and outcomes to ensure the community receives the best care.