AI Spotlight · Healthcare

An AI Blood Test Could Spare 18,000 Women Invasive Cancer Checks

A £30 blood test built on machine learning is entering NHS hospitals to help rule out womb cancer before women undergo uncomfortable ultrasound scans and biopsies. Here is how it works and what the trial found.

Several NHS hospitals are preparing to roll out an AI-powered blood test to help assess women referred for possible womb cancer before they undergo invasive checks, according to AI News, citing reporting from The Guardian. Around 90,000 postmenopausal women in England are referred by GPs each year after experiencing heavy bleeding, and roughly 10,000 are diagnosed with womb cancer annually, with around 2,700 dying from the disease.

The tool at the center of this rollout is the PinPoint test, developed by Leeds-based PinPoint Data Science. It uses machine learning to assess cancer risk from around 30 blood markers, sorting patients into low, elevated, or high risk categories that clinicians can act on within existing referral pathways.

This issue covers how the test works, what the 16,481-patient Yorkshire trial actually found, and how it fits alongside the NHS's fast-growing portfolio of AI diagnostic tools.

* * *

The technology

A £30 blood test that scores cancer risk in one draw

PinPoint's test costs around £30 and gives clinicians a single risk score built from an analysis of roughly 30 blood markers [1]. That score slots directly into existing cancer referral pathways, helping determine whether a patient should be monitored, sent for further investigation, or prioritised for faster assessment. Crucially, the test does not replace clinical judgment; it is designed as a decision-support layer that runs before more invasive procedures are considered [2].

PinPoint describes the tool as a multi-cancer test rather than a womb-cancer-specific one. The company said it has already been used across gynaecological, lung, upper gastrointestinal, head and neck, and lower gastrointestinal cancer pathways, and it is UKCA-marked for use as a Multi-Cancer Early Detection blood test in symptomatic NHS patients [3].

* * *

The evidence

What the 16,481-patient Yorkshire trial found

The test is being introduced after a trial involving 16,481 patients referred through urgent suspected cancer pathways across Yorkshire, including women referred with symptoms raising concern about possible womb or gynaecological cancer [4]. The accuracy figures reported from that trial are notably high for a screening-style tool: PinPoint said the test correctly identified 99.1 percent of cancers as elevated or high risk, and delivered a negative predictive value of 99.8 percent for women placed in the lowest-risk group.

In practical terms, that negative predictive value is the number that matters most for reducing unnecessary invasive procedures. It means that when the test places a woman in the lowest-risk group, doctors can be highly confident she does not have cancer, which is precisely the population PinPoint is trying to divert away from scans and biopsies they likely do not need.

Mid Yorkshire NHS Teaching Trust plans to use the test across six types of gynaecological or upper gastrointestinal cancer, while Leeds Teaching Hospitals NHS Trust plans to use it specifically for gynaecological cancer, building on years of prior evaluation work with the West Yorkshire Cancer Alliance [5].

The patient experience

Why avoiding a transvaginal ultrasound actually matters

Under the current pathway, women referred for suspected reproductive system cancers usually undergo a pelvic examination that includes a transvaginal ultrasound scan, a procedure involving inserting a probe into the vagina to measure the thickness of the womb lining. Many women find it uncomfortable or painful, and if concern persists, patients can then be referred for further checks including a biopsy and hysteroscopy, an examination of the inside of the womb.

Professor Sean Duffy, chief medical officer at PinPoint Data Science and a former NHS England national clinical director for cancer, said the test's value lies specifically in ruling out women at very low risk before those invasive steps happen. Dr Jacinta Walsh, a GP at King's Medical Practice in Normanton, West Yorkshire, added that patients can currently require up to six GP visits before cancer is ruled out, and said the test could shorten that process significantly while freeing up capacity for other patients.

Jackson said the test could help clinicians triage patients before hospital-based investigations even begin, ruling out low-risk patients in primary care while prioritising higher-risk patients for faster follow-up. That triage function is the core promise across nearly all of PinPoint's published evaluation work to date [6].

* * *

The bigger picture

PinPoint joins a fast-growing list of NHS AI deployments

This launch is part of a broader wave of AI tools moving into frontline NHS care, not an isolated pilot. East Kent Hospitals University NHS Foundation Trust is already using an AI system called MEMORI at Kent and Canterbury Hospital to assess infection risk from routine patient data, drawing on blood tests, blood pressure, temperature, observations, medications, and demographics already sitting in patient records.

Taken together, these deployments point to a pattern: rather than one flagship AI product, the NHS is quietly layering narrow, well-validated machine learning tools into specific points across the diagnostic pathway, from infection risk scoring to imaging review to blood-based cancer triage.

* * *

The caveat

Promising, but more evidence is still needed

Not every reaction to the rollout has been unreserved. Cancer Research UK described the PinPoint test as promising but said more research is needed to understand its benefits for both patients and the NHS as a whole. Samantha Harrison, a spokesperson for the charity, said early detection saves lives, but patients are not currently being diagnosed quickly enough, and framed the test's real opportunity as ruling out endometrial cancer in some women through a blood test alone, without further investigation.

Further evidence will be needed to assess how the test affects patient outcomes, referral decisions, and NHS diagnostic capacity at scale. That caution matters because the test's real-world value depends not just on its accuracy in a trial population, but on whether GPs and hospital trusts actually change referral behaviour once it becomes part of routine practice.

* * *

Until next time,

AI Spotlight

Practical AI, translated into real work, once a week.