Several NHS hospitals are preparing to use AI-powered blood tests to assess women referred for possible uterine cancer before invasive tests are carried out.
According to the Guardian, around 90,000 postmenopausal women in the UK are referred for testing by their GP each year after experiencing heavy bleeding. Approximately 10,000 women are diagnosed with uterine cancer each year, and approximately 2,700 die from uterine cancer.
How the PinPoint test works
The test was developed by Leeds-based PinPoint Data Science and uses machine learning to assess cancer risk from blood markers. Based on analysis of approximately 30 markers, patients are classified as low risk, high risk, or high risk.
Pinpoint says the test will cost around £30 and will provide clinicians with a risk score for use within existing cancer referral pathways. The score helps inform whether a patient is being monitored, referred for further investigation, or prioritized for faster evaluation.
PinPoint describes the tool as a test for multiple cancers. The company says it is used across gynecological, pulmonary, upper gastrointestinal, head and neck, and lower gastrointestinal cancer pathways.
The test was introduced following a trial involving 16,481 patients across Yorkshire who were referred through the emergency pathway with suspected cancer. The trial involved women who were referred with symptoms that raised concerns about possible uterine or gynecological cancer.
Approximately one in 10 women referred for heavy bleeding were found to have cancer, according to reported trial results.
Pinpoint said the test correctly identified 99.1% of cancers as high or high-risk, and had a negative predictive value of 99.8% for women in the lowest risk group.
Mid Yorkshire NHS Education Trust plans to use the test for six types of gynecological or upper gastrointestinal cancers. Leeds Teaching Hospitals NHS Trust plans to use it for gynecological cancers.
Current diagnostic pathway
Under the current pathway, women referred for suspected reproductive cancer usually undergo a pelvic examination, including a transvaginal ultrasound scan. This procedure involves inserting an ultrasound probe into the vagina to measure the thickness of the uterine lining, which some women find uncomfortable or painful.
If the doctor still suspects cancer, the patient may undergo further tests, such as a biopsy, hysteroscopy, or an examination of the uterus. Pinpoint said the test aims to identify women at very low risk before such procedures are performed.
The company said the test could save about one in five referred women from needing a transvaginal ultrasound. This equates to around 18,000 women a year in the UK.
Professor Sean Duffy, chief medical officer at Pinpoint Data Science and former NHS England national cancer clinical director, said the value of the test was in excluding women who were at very low risk.
Dr Jacinta Walsh, a GP at King’s Medical Practice in Normanton, West Yorkshire, said patients could need up to six GP visits before cancer was ruled out. He said the test could speed up that process and make room for other patients.
Tracey Jackson, consultant gynecologist and lead oncology at Leeds Teaching Hospitals NHS Trust, said most women seen through the current referral route do not have cancer, but the investigation can be uncomfortable and painful.
Jackson said the test could help clinicians triage patients before hospital investigations. He said low-risk patients could be removed from primary care, while high-risk patients could be prioritized for further testing.
Other NHS AI deployments
Recent NHS AI deployments include MEMORI at Kent and Canterbury Hospitals, an AI triage tool in the NHS app, and an AI-powered chest X-ray tool for suspected lung cancer pathways.
East Kent Hospitals University NHS Foundation Trust is using an AI system called MEMORI at Kent and Canterbury Hospitals to assess infection risk from routine patient data. The system analyzes information already contained in patient records, such as blood tests, blood pressure, temperature, observations, medications, and demographics.
NHS England said the NHS app’s AI triage tool will be delivered to more than 200,000 patients within 12 months and is expected to be available to all NHS app users by April 2028.
The government has also committed £20 million to roll out AI-powered chest x-ray screening tools to all NHS trusts in England by 2029. The tool is already available in around half of England’s NHS trusts and has helped assess more than four million patients being investigated for lung cancer.
Further evidence will be needed to assess how this test will impact patient outcomes, referral decisions and the diagnostic capacity of the NHS.
Cancer Research UK said the PinPoint test was promising, but further research was needed to understand its benefits for patients and the NHS. Samantha Harrison, a spokeswoman for the charity, said early detection saves lives but currently patients are not being diagnosed quickly enough.
The charity said the test could help rule out endometrial cancer in some women through a blood test without the need for further investigation.
(Photo courtesy of Adam Mills)
Reference: Takeda Pharmaceutical signs $600 million AI drug discovery agreement with Insilico
Want to learn more about AI and big data from industry leaders? Check out the AI & Big Data Expos in Amsterdam, California, and London. This comprehensive event is part of TechEx and co-located with other major technology events. Click here for more information.
AI News is brought to you by TechForge Media. Learn about other upcoming enterprise technology events and webinars.
