Several NHS hospitals are set to implement an AI-powered blood test designed to evaluate women referred for potential womb cancer before invasive examinations take place. According to The Guardian, approximately 90,000 postmenopausal women in England are referred by GPs annually after experiencing heavy bleeding, with about 10,000 diagnosed with womb cancer each year.
How the PinPoint test functions
The PinPoint test, developed by Leeds-based PinPoint Data Science, utilizes machine learning to evaluate cancer risk based on blood markers. The test analyzes around 30 markers to classify patients as low, elevated, or high risk. PinPoint reports that the test costs approximately £30 and provides clinicians with a risk score to guide cancer referral pathways.
This score helps determine whether a patient should be monitored, referred for further investigation, or prioritized for rapid assessment. PinPoint describes the tool as a multi-cancer test, having been used across various cancer pathways including gynaecological and lung cancers.
Trial results and implications
The introduction of the test follows a trial involving 16,481 patients referred through urgent suspected cancer pathways in Yorkshire. The trial included women with symptoms that raised concerns about potential womb or gynaecological cancer. Reported results indicated that about 10% of women referred due to heavy bleeding were found to have cancer.
PinPoint stated that the test accurately identified 99.1% of cancers as elevated or high risk, achieving a negative predictive value of 99.8% for women classified in the lowest-risk group. The Mid Yorkshire NHS Teaching Trust plans to utilize the test for six types of gynaecological or upper gastrointestinal cancers, while Leeds Teaching Hospitals NHS Trust intends to focus on gynaecological cancer.
Current diagnostic practices
Under existing protocols, women suspected of reproductive system cancers typically undergo a pelvic examination that includes a transvaginal ultrasound scan. This procedure can be uncomfortable or painful for some women. If cancer remains a concern, further checks such as a biopsy or hysteroscopy may be necessary.
PinPoint asserts that its test is designed to identify women at very low risk before these invasive procedures are performed, potentially sparing about one in five referred women from needing a transvaginal ultrasound scan, which translates to around 18,000 women annually in England.
Professor Sean Duffy, chief medical officer at PinPoint Data Science, emphasized the test's value in ruling out women at very low risk. Dr. Jacinta Walsh, a GP at King’s Medical Practice, noted that patients often require up to six GP visits before cancer is ruled out, and the test could expedite this process, allowing more capacity for other patients.
Consultant gynaecologist Tracy Jackson from Leeds Teaching Hospitals NHS Trust highlighted that most women referred through the current route do not have cancer, and the investigations can be distressing. She believes the test could help clinicians triage patients effectively, ruling out low-risk patients in primary care while prioritizing higher-risk patients for further checks.
Other NHS AI initiatives
The NHS has been exploring various AI deployments, including MEMORI at Kent and Canterbury Hospital, an AI triage tool in the NHS App, and AI-powered chest X-ray tools for suspected lung cancer pathways. East Kent Hospitals University NHS Foundation Trust is using MEMORI to assess infection risks based on routine patient data.
NHS England anticipates that the AI triage tool in the NHS App will reach over 200,000 patients within a year, with plans for broader availability by April 2028. The government has also pledged £20 million to expand AI-powered chest X-ray tools to all NHS trusts in England by 2029.
Further research is necessary to evaluate the test's impact on patient outcomes, referral decisions, and NHS diagnostic capacity. Cancer Research UK has described the PinPoint test as promising but emphasizes the need for additional studies to fully understand its benefits.
🤖 This article was rewritten by Feed and Figures' editorial AI from a report originally published by AI News. Facts and quotes are preserved from the original; the rewrite focuses on clarity and structure. For the unedited original, see the source link below.
