Machine learning algorithm diagnoses deep vein thrombosis

UK and German researchers are developing an artificial intelligence (AI) algorithm with the aim of diagnosing deep vein thrombosis (DVT) more quickly and as effectively as traditional radiologist-interpreted diagnostic scans, potentially cutting down long patient waiting lists and avoiding patients unnecessarily receiving drugs to treat DVT when they don’t have it.

DVT is a type of blood clot most commonly formed in the leg, causing swelling, pain and discomfort. If left untreated, it can lead to fatal blood clots in the lungs; 30–50% of people who develop a DVT can go on to have long-term symptoms and disability. Meanwhile, many patients who do not have a definitive diagnosis within 24 hours of a suspected DVT end up receiving painful injections of what can often be an unnecessary anticoagulant, with potential side effects.

The researchers collaborated with tech company ThinkSono to train a machine learning AI algorithm, dubbed AutoDVT, to distinguish patients with DVT from those without DVT. The results of their study, published in npj Digital Medicine, show the AI algorithm accurately diagnosed DVT when compared to the gold standard ultrasound scan, and the team worked out that using the algorithm could potentially save health services $150 per examination.

“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 handheld ultrasound machine shows promising results,” said study lead Dr Nicola Curry, a researcher at Oxford’s Radcliffe Department of Medicine and clinician at Oxford University Hospitals NHS Foundation Trust.

Having shown that machine learning AI algorithms can potentially diagnose DVT, the researchers are now due to start a test-accuracy blinded clinical study, comparing the accuracy and sensitivity of AutoDVT with standard care. The hope will be that AutoDVT will get the right diagnosis faster to the nearly 8 million people worldwide who potentially have a venous blood clot each year.

“The AI algorithm can not only be trained to analyse ultrasound images to discriminate the presence versus the absence of a blood clot, it can also direct the user using the ultrasound wand to the right locations along the femoral vein, so that even a non-specialist user can acquire the right images,” said team member Christopher Deane, from the Oxford Haemophilia and Thrombosis Centre.

The researchers hope that the AutoDVT tool and AI algorithm will allow non-specialist healthcare professionals, like GPs and nurses, to quickly diagnose and treat DVT. It may additionally allow the collection of images by non-specialists, which could be sent to an expert facilitating diagnosis of those unable to get to a specialist.

“We are delighted by the results in this study and are excited to work further with Oxford University Hospital and other partner hospitals to trial the software and bring it to patients worldwide,” said ThinkSono CEO Fouad Al Noor.

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletter and bimonthly magazine.