NEWS


AI cancer tools risk ‘shortcut learning’


University of Warwick research warns that popular deep learning systems trained for cancer pathology may be relying on hidden shortcuts rather than genuine biological signals. Artificial intelligence tools are


increasingly being developed to predict cancer biology directly from microscope images, promising faster diagnoses, and cheaper testing. But new research from the University of Warwick, published in Nature Biomedical Engineering, suggests that many of these systems may be using visual shortcuts rather than true biology. To reach this conclusion, the


researchers analysed more than 8,000 patient samples across four major cancer types – breast, colorectal, lung and endometrial – and compared the performance of leading machine learning approaches. While the models often achieved high headline accuracy, the team found this frequently came from statistical ‘shortcuts’. When performance of AI models


was assessed within stratified patient subgroups, such as only high-grade breast cancers or only MSI-positive tumours, accuracy fell substantially, revealing that the models were dependent on shortcut signals that disappear once confounding factors are controlled. For certain prediction tasks, the


performance advantage of deep learning over human-derived clinical information was modest. AI systems achieved accuracy scores of just over 80% when predicting biomarkers, compared with around 75% using tumour grade alone – a measure already assessed by pathologists. Dawood M, Branson K, Tejpar S, Rajpoot N, Minhas FUAA. Confounding factors and biases abound when predicting molecular biomarkers from histological images. Nat Biomed Eng. Published online March 2, 2026. doi:10.1038/s41551- 026-01616-8


Mpox antibody assay validated in Rwanda


An antibody test for the infectious disease Mpox was successfully developed during the new clade 1b outbreak in Rwanda, the first time that an assay of its kind has been validated within this seting. The serum and dried-blood-spot test was able to identify those with infection and vaccine- derived antibodies – helping authorities to prioritise vaccine use. The test, an IgG ELISA assay, is described in a new paper published in The Lancet Infectious Diseases. Developed by a team from the University of Birmingham in collaboration with the Rwanda Biomedical Centre (RBC) and the University of Rwanda, the highly accurate test for Mpox antibodies was successfully trialled within the National Reference Laboratory in Kigali, Rwanda. The assay tests for antibodies to


Mpox virus that appear after infection or vaccination. By detecting this immune signature, public health authorities and researchers can beter study key factors in outbreaks of Mpox cases such as the networks of disease transmission, who needs priority for vaccination, and the how immunity changes over time. The project, called MpoxCARE, took blood samples collected and tested in Rwanda from known patients who either had received an Mpox vaccine, had previously had an Mpox infection,


or had no exposure to the disease or prior vaccination. The test was validated on whether it would be able to identify patients who had developed Mpox antibodies (immunity) after vaccination or naturally after infection. Researchers from the MpoxCARE team


developed the test using only four key antibody signatures, to ensure that the test was affordable and supplies were accessible in remote laboratories. The new diagnostic tool is a product of a longstanding relationship between the University of Birmingham and the national health implementation agency for Rwanda, Rwanda Biomedical Centre. The joint research portfolio is configured with capacity building at the core, which includes international PhD studentships and infectious disease research expertise from the NHS and NIHR to allow for the rapid development of scientific countermeasures for outbreaks of vaccine preventable disease. Clarke J, Semukunzi H, Faustini SE, et al. A combined ELISA for infection-induced and vaccine-induced mpox antibodies during the clade Ib outbreak in Rwanda: an observational, cross-sectional, clinical validation study. Lancet Infect Dis. 2026. Published online 9 March. doi:0.1016/S1473- 3099(26)00006-X


BHR Biosynex appoints UK+I head


Point-of-care diagnostic firm BHR Biosynex has appointed Adam Martin as Country Manager for the UK and Ireland. In his role, Adam will be responsible


for leading BHR Biosynex’s commercial strategy across the UK and Ireland, overseeing continued growth across point-of-care testing solutions for healthcare professionals alongside the company’s expanding portfolio of home-use, self-care and OTC healthcare products. This includes supporting the ongoing introduction of additional Biosynex Pharma brands into the UK and Ireland market. Adam brings extensive experience


in healthcare sales leadership, market development and strategic partnership building, with a strong track record of driving growth across both professional healthcare and consumer health


14 WWW.PATHOLOGYINPRACTICE.COM April 2026


channels. In his role, Adam will focus on strengthening customer and partner relationships, expanding BHR Biosynex’s footprint across healthcare, pharmacy and consumer channels, and supporting the successful introduction of new diagnostic and OTC innovations from the wider BIOSYNEX Group. On joining the company, Adam


Martin said: “I am proud to be joining such a great company at a pivotal time and to be leading such an experienced, incredible team. Point-of-care testing is being utilised across the UK and Ireland in increasingly varied locations and the addition of the OTC and self-test products compliments the offerings to both healthcare professionals and consumers.”


Dr Fayyaz Minhas, University of Warwick


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56