Health

Machine learning algorithm to diagnose deep vein thrombosis

A qualitative sample image of the model’s segmentation performance. Segmentation is robust throughout compression. The venous region is evaluated for full compressibility to rule out DVT. Device: Clarius L7 (2017). Credit: https: //doi.org/10.1038/s41746-021-00503-7

The team of researchers aims to diagnose deep vein thrombosis (DVT) as quickly and effectively as traditional radiologist-interpreted diagnostic scans, reduce long patient waiting lists, and avoid patients. , Is developing the use of artificial intelligence (AI) algorithms. Receive medication unnecessarily to treat DVT when they do not have it.

DVT is one of the most commonly formed blood clots in the legs, causing swelling, pain, and discomfort. If left untreated, it can cause fatal blood clots in the lungs. Thirty to fifty percent of people who develop DVT may continue to have long-term symptoms and disabilities.

Researchers at Oxford University, Imperial College, and the University of Sheffield are working with technology firm ThinkSono (led by Fouad Al-Noor and Sven Mischkewitz) to train machine learning AI algorithms (AutoDVT) to train patients and patients with DVT. I made a distinction. No DVT. The AI ​​algorithm accurately diagnosed DVT compared to gold standard ultrasound scans, and the team found that using the algorithm could save $ 150 in medical services per test.

“Traditionally, DVT diagnostics have required specialized ultrasound scans by trained radiologists, and preliminary data using AI algorithms coupled to portable ultrasound equipment has shown promising results. “Research leader Dr. Nikola Curry said. Researcher at Radcliffe School of Medicine, Oxford University and Clinician at the NHS Foundation Trust, Oxford University Hospital.

This is the first study to show it Machine learning AI algorithms have the potential to diagnose DVT, and researchers conduct blinded clinical studies of test accuracy to compare the accuracy of AutoDVT with standard care to determine the sensitivity for picking up DVT cases. I plan to start. AutoDVT is expected to enable faster and more appropriate diagnosis of approximately 8 million people worldwide who may develop venous thrombosis each year.

“AI algorithms can not only be trained to analyze ultrasound images to distinguish between the presence or absence of blood clots, but they can also use ultrasound wands to guide the user to the right place along the femoral vein. Expert users can get the right images, “said Christopher Dean, a research team member at the Oxford Hemothymology and Thrombosis Center.

The research team expects a combination of AutoDVT tools and AI algorithmAllows non-professional medical professionals such as GPs and nurses to quickly diagnose and treat DVT. In addition, it may allow non-professional image collection that can be sent to professionals to facilitate diagnosis of those who cannot be contacted.

“Currently, many patients do not have a definitive diagnosis within 24 hours of suspicious DVT, and a large number of patients can become often unnecessary anticoagulants with potential side effects. You’ll get a painful injection, “Dr. Currie said. It is also part of the Oxford Hematology Center.

The results of the study are published in the journal Digital medicine..


Engineers have discovered that imaging technology can be a treatment for deep vein thrombosis


For more information:
Kainz, B., Heinrich, MP, Makropoulos, A. et al, Non-invasive diagnosis of deep vein thrombosis from machine-learned ultrasound images. Digital medicine (2021). doi.org/10.1038/s41746-021-00503-7

Provided by
Oxford University

Quote: Machine learning algorithm for diagnosing deep vein thrombosis (September 15, 2021) from https: //medicalxpress.com/news/2021-09-machine-algorithm-deep-vein-thrombosis.html 2021 Obtained on September 15, 2014.

This document is subject to copyright. No part may be reproduced without written permission, except for fair transactions for personal investigation or research purposes. The content is provided for informational purposes only.



Machine learning algorithm to diagnose deep vein thrombosis Source link Machine learning algorithm to diagnose deep vein thrombosis

Related Articles

Back to top button