2023-11-23 11:32:27
Create a news article using this content 23 november 2023
In regions where high-tech laboratory tests are not available, good Covid-19 diagnoses can be made by an AI program, researchers from Radboud university medical center and international colleagues write in Scientific Reports. The AI program uses an X-ray and blood tests that can be read on the spot. Variants of the program may eventually also be used to diagnose tuberculosis.
Covid is diagnosed in the Netherlands and many other countries via a cotton swab in the nose, throat or both. A PCR test is then used to analyze whether fragments of the virus are present in the cotton wool. Yes? Covid. No? No Covid. The problem is that the high-tech PCR test (polymerase chain reaction) is not available everywhere in the world. Other techniques are then needed to diagnose an infection with the virus.
X-ray
In Scientific Reports, Keelin Murphy and Bram van Ginneken from Radboud university medical center and international colleagues describe an AI program that could be a good alternative to the antigen rapid test. The program combines an X-ray of the lungs with Point Of Care (POC) blood tests. The diagnostic value of the X-ray itself is too low, because the majority of infected people only have mild symptoms and no pneumonia can be detected. But combined with the results of one or more blood tests, it does become a reliable test.
Point Of Care
Point Of Care tests immediately indicate the result of what you want to measure. You don’t have to go to a laboratory specifically for this. One POC test (white blood cell counts WBC) maps the number of different white blood cells, with an increase in the number indicating an infection or inflammation. The other POC test measures C-reactive protein (CRP). If it has a higher value than normal, this is also an indication of inflammation. If the X-ray data are combined with WBC, possibly supplemented with CRP, a diagnosis is created that is more sensitive than an antigen rapid test in the tested African regions.
Four locations in Africa
The test took place at four different locations in Africa where there is a lack of people and resources to make Covid diagnoses with PCR. Good X-rays of the lungs can be taken at these locations, which can also be immediately checked for tuberculosis with software such as CAD4TB, as Thirona and Delft Imaging show. The POC tests can also be used there. In total, more than 3,500 people participated in the study and a PCR test was carried out as a check. Not only could the ‘low-threshold’ X-ray and blood tests be easily performed on site, but compared to the antigen rapid test, the X-ray-blood test combination, assessed by an AI program, was more sensitive than the antigen test. More sensitive means that the test determines more correct positive diagnoses.
Practical application with perspective
“This is the first study to validate AI methods for COVID-19 detection in an African setting,” the researchers write. “It shows that screening for COVID-19 using AI and point-of-care blood tests is feasible and may be more sensitive than antigen tests.” Looking ahead, they note that AI programs that combine an X-ray with POC blood tests may also eventually be suitable for tuberculosis diagnoses in medically less well-resourced regions.
-
Publication in Scientific Reports: COVID-19 screening in low resource settings using artificial intelligence for chest radiographs and point-of-care blood tests – Keelin Murphy, Josephine Muhairwe, Steven Schalekamp, Bram van Ginneken, Irene Ayakaka, Kamele Mashaete, Bulemba Katende, Alastair van Heerde, Shannon Bosman, Thandanani Madonsela, Lucia Gonzalez Fernandez, Aita Signorell, Moniek Bresser, Klaus Reither & Tracy R. Glass
]
#program #delivers #high #number #good #Covid19 #diagnoses #lowincome #countries #Interesting #alternative #African #regions #shortage #doctors