91直播

Skip to main content

Latest news

Download Media Kit
Download
26
August
2025
|
09:01
Europe/London

Blood test detects ovarian cancer with high accuracy, study finds

A new blood test pioneered by diagnostics company AOA Dx (AOA) can detect ovarian cancer in symptomatic women with high accuracy a by researchers from the Universities of Manchester and Colorado has found. 

Published in the American Association of Cancer Research (AACR) journal Cancer Research Communications, the study assessed AOA鈥檚 novel technology that analysed multiple groups of biological markers from a single blood sample. 

The researchers showed the test outperformed traditional biomarker tests for ovarian cancer detection in over 950 patients from Colorado and 91直播. 

This study is a major milestone and AOA is committed to pursuing regulatory approval across the US and Europe in the coming years, ahead of launching the test to the NHS. 

The technology combines two different sets of blood-markers, proteins and lipids, with   machine learning to identify the presence of ovarian cancer in women that present with vague abdominal/pelvic symptoms. 

In samples from University of Colorado the test exhibited an accuracy of 93% across all stages of ovarian cancer and 91% for early-stage disease. 

In a set from 91直播, the model continued to perform strongly, with an accuracy of 92% for all-stages of ovarian cancer and 88% for early-stage disease.

 AOA鈥檚 test performed better than single blood-based-markers which have been used for the past 30 year, which were only able to attain accuracies of less than 90%

The successful results, say AOA, will inform the final design of the test, which could produce a streamlined and cost-effective diagnostic relevant to healthcare systems globally. 

鈥淥ur platform detects ovarian cancer at early stages and with greater accuracy than current tools,鈥 said Alex Fisher COO and Co-Founder of AOA Dx. 鈥淭hese findings show its potential to aid clinicians in making faster, more informed decisions for women who need urgent clarity during a challenging diagnostic process.鈥 

鈥淏y using machine learning to combine multiple biomarker types, we鈥檝e developed a diagnostic tool that detects ovarian cancer across the molecular complexity of the disease in sub-types and stages鈥 said Dr. Abigail McElhinny, Chief Science Officer of AOA Dx. 鈥淭his platform offers a great opportunity to improve the early diagnosis of ovarian cancer potentially resulting in better patient outcomes and lower costs to the healthcare system.鈥

AOA Dx鈥檚 platform shows significant promise for ovarian cancer early detection, offering a practical solution for symptomatic women

Professor Emma Crosbie,

varian cancer is the fifth leading cause of cancer-related deaths among women, largely due to late-stage diagnosis.

Over 90% of women experience symptoms in Stage I, yet only 20% of cases are diagnosed in Stage I or II, as symptoms like bloating, abdominal pain, and digestive issues often resemble benign conditions.

Existing diagnostic methods, which rely on invasive procedures or less reliable markers, frequently fail to identify early-stage disease.

An accurate early detection test available to women when they first visit a physician with symptoms could revolutionize the detection of ovarian cancer.

Professor Emma Crosbie, Professor at The University of Manchester and Honorary Consultant in Gynecological Oncology, 91直播 University NHS Foundation Trust (MFT), said: 鈥淎OA Dx鈥檚 platform shows significant promise for ovarian cancer early detection, offering a practical solution for symptomatic women.鈥

Professor Crosbie is also National Institute for Health and Care Research (NIHR) 91直播 Biomedical Research Centre (BRC) Cancer Prevention and Early Detection Co-Theme Lead.

She added: 鈥淎OA Dx鈥檚 platform has the potential to significantly improve patient care and outcomes for women diagnosed with ovarian cancer. We are eager to continue advancing this important research through additional prospective trials to further validate and expand our understanding of how this could be integrated into existing healthcare systems.鈥

The paper Utilizing serum-derived lipidomics with protein biomarkers and machine learning for early detection of ovarian cancer in the symptomatic population published in cancer Research Communications is available DOI:

Share this page