The UK healthcare system is making a significant step forward in cancer diagnostics. Two National Health Service (NHS) trusts are beginning to implement the innovative PinPoint AI blood test for women with suspected uterine cancer. The results of a large-scale study are impressive: in a group of 3,313 participants, the machine learning model demonstrated 99% accuracy in detecting and ruling out gynecological cancers.
Every year in England, around 90,000 patients are referred for examination due to heavy postmenopausal bleeding. Approximately 10,000 of them receive a diagnosis of uterine (or endometrial) cancer. 2,700 women die from this disease annually. The standard diagnostic procedure includes transvaginal ultrasound to measure endometrial thickness, and if suspicions remain, a biopsy and hysteroscopy. Many patients find these procedures painful and invasive.
The key problem: 20% of referred women do not have cancer confirmed, yet they are forced to undergo all stages of examination. The developers of PinPoint claim that the test will allow the disease to be ruled out at the initial referral stage, sparing around 18,000 women per year from unnecessary invasive procedures.
How It Works and Implementation
The PinPoint algorithm analyzes 30 biomarkers in a blood sample and, based on the data obtained, determines the risk level: low, elevated, or high. The technology was developed by PinPoint Data Science, a company from Leeds specializing in statistical analysis of medical data.
The implementation was preceded by large-scale trials involving 16,481 patients. General practitioners from 170 clinics in Yorkshire referred them for checks on nine types of cancer. All participants provided samples for analysis, including 3,313 women with bleeding and suspected uterine cancer. PinPoint Data Science's Chief Medical Officer, Sean Duffy, called the 99% accuracy "outstanding by any clinical standards," emphasizing that the test reliably rules out cancer in women with low risk.
The Mid Yorkshire NHS Teaching Trust plans to use the test for six types of gynecological cancer and upper gastrointestinal cancers, while the Leeds Teaching Hospitals NHS Trust will implement it for gynecological cancers.
Reaction from the Medical Community
General practitioner Jacinta Walsh from West Yorkshire noted that currently, ruling out cancer requires up to six doctor visits. PinPoint will speed up the process and free up time for other patients. Consultant gynecologist Tracy Jackson from the Leeds Trust emphasized that the new technology will enable more efficient triage: women with actual cancer will see a doctor faster, receive a diagnosis, and begin treatment.
Cancer Research UK called the test results "promising," but the organization's representative, Samantha Harrison, pointed out the need for further research to assess the benefits for patients and the healthcare system.
This event continues the trend of integrating AI into oncology. Previously, researchers reported successfully training AI to detect pancreatic cancer long before symptoms appear. However, in my opinion, it is the direction of non-invasive diagnostics based on blood analysis that has the greatest potential for widespread adoption. PinPoint could become a screening standard, reducing diagnostic time and easing the burden on the healthcare system, which is critically important for the early detection of cancer.