-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
- Cosmetic Ingredient
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
London, UK and Potsdam, Germany, September 16, 2021/PRNewswire/ - A research team is developing applications of artificial intelligence (AI) algorithms, whose purpose is to interpret diagnostic scans faster and more quickly like traditional radiologists.
Effectively diagnose deep thrombosis (DVT), which may reduce the list of patients waiting for treatment for a long time and prevent patients from unnecessarily receiving medication when they do not have deep thrombosis
.
ThinkSono AutoDVT App on a smartphone
DVT is a blood clot that most commonly forms in the legs and can cause swelling, pain, and discomfort-if left untreated, it can cause fatal blood clots in the lungs
.
30-50% of DVT patients may have long-term symptoms and disabilities
Researchers from the University of Oxford, Imperial College and University of Sheffield collaborated with technology company ThinkSono (led by Fouad Al-Noor and Sven Mischkewitz) to train machine learning AI algorithms (AutoDVT) to distinguish DVT patients from non-DVT patients
.
Compared with the gold standard ultrasound scan, the AI algorithm can accurately diagnose DVT.
Dr.
Nicola Curry, a researcher at the Radcliffe Department of Medicine at the University of Oxford and a clinician at the NHS Foundation Trust Fund of Oxford University Hospital, said: “Traditionally, the diagnosis of DVT requires a professional ultrasound scan by a trained radiologist.
We found that, Preliminary data using AI algorithms combined with handheld ultrasound machines have shown encouraging results
.
"
This is the first study to show that machine learning AI algorithms have the potential to diagnose DVT.
Researchers will start a blinded clinical study to test the accuracy of AutoDVT and compare the accuracy of AutoDVT with standard care to determine the sensitivity of identifying DVT cases
.
For nearly 8 million people around the world who may suffer from venous blood clots each year, AutoDVT is expected to be able to get the correct diagnosis faster
Christopher Deane, a research team member of the Oxford Centre for Hemophilia and Thrombosis, said: “The artificial intelligence algorithm can not only be trained to analyze ultrasound images to distinguish whether there is a blood clot, but it can also guide users using ultrasound sticks to the femoral vein.
Correct location so that even non-expert users can get the correct image
.
The research team hopes that the combination of AutoDVT tools and AI algorithms will enable non-expert medical professionals such as general practitioners and nurses to quickly diagnose and treat DVT
.
In addition, it can also allow non-experts to collect images and send them to experts so that patients who have no access to experts can get a diagnosis
"Currently, many patients have not made a final diagnosis within 24 hours of suspected DVT.
So many patients end up receiving painful injections, which may usually be unnecessary anticoagulants and have potential side effects," the same Oxford Dr.
Curry, a member of the Blood Disease Center, said
.
ThinkSono CEO Fouad Al Noor said: "We are pleased with the results of this study and are pleased to further cooperate with Oxford University Hospital and other partner hospitals to test the software and bring it to patients around the world
.
"
The research results were published in the journal "Digital Medicine", a natural collaboration journal
The URL of the ThinkSono website is:
ThinkSono for more information: Fouad Al Noor, hello@thinksono.
Note: This research paper is available here: https:// DOI number: https://doi.
Source: ThinkSono Ltd
