An artificial intelligence algorithm has been developed that could diagnose deep vein thrombosis (DVT) faster but as effectively as traditional radiologist-interpreted diagnostic scans, it has been announced.
Researchers at Oxford University say they hope the algorithm has the potential to reduce long waiting lists and avoid patients unnecessarily receiving drugs to treat DVT when they do not have it.
With colleagues from Imperial College London, the University of Sheffield and tech company ThinkSono, researchers trained a machine learning AI algorithm (AutoDVT) to distinguish patients who had DVT from those without.
The findings, published in the journal Digital Medicine, showed it accurately diagnosed DVT when compared to the gold standard ultrasound scan. AutoDVT also directs non-specialists in optimal ultrasound technique, so that people can receive tests in the community without having to be seen at specialist centres. The team believe their approach could potentially save health services more than £100 per examination.
This is the first study to show that machine learning AI algorithms can potentially diagnose DVT. The team is now about to start a test-accuracy blinded clinical study to compare the accuracy of AutoDVT with standard care to determine the sensitivity for picking up DVT cases.
Study lead Dr Nicola Curry, a researcher at Oxford University’s Radcliffe Department of Medicine and clinician at Oxford University Hospitals NHS Foundation Trust, said: “Traditionally, DVT diagnoses need a specialist ultrasound scan performed by a trained radiographer, and we have found that the preliminary data using the AI algorithm coupled to a hand-held ultrasound machine shows promising results.”
The research team hopes combining the AutoDVT tool with the AI algorithm will enable non-specialist healthcare professionals, such as GPs and nurses, to diagnose and treat DVT quickly.
Kainz B, Heinrich MP, Makropoulos A, Oppenheimer J, Mandegaran R, Sankar S, Deane C, Mischkewitz S, Al-Noor F, Rawdin AC, Ruttloff A, Stevenson MD, Klein-Weigel P, Curry N (2021) “Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning.” npj Digital Medicine, doi: 10.1038/s41746-021-00503-7
Disclaimer: The news stories shared on this site are used as a way to inform our members and followers of updates and relevant information happening in Haematology. The BSH does not endorse the content of news items from external sources and is not in a position to verify the findings, accuracy, or the source of any studies mentioned. Any medical or drugs information is provided as an information resource only and is not to be relied on for any diagnostic or treatment purposes.
News service provided by Englemed News http://www.englemed.co.uk/