AI researchers celebrate medical breakthrough: a new AI algorithm of an American research team can read infections and car -immune diseases with great accuracy in typical changes in B and T cells and thus diseases.
Maxim Zaslavsky from the US-Stanford University and its co-authors reported this in the Science Magazine “Science”. The diseases are read in the gens inspection of the receptors of the immune cells.
The background: The diagnosis of infectious diseases is currently usually looking for the cause. This often means waiting for a long time until a culture is made and evaluated. Antibody reactions also often occur alone with a delay. In the case of car -immune diseases such as type 1 diabetes, the disease is determined by the consequences of metabolism, in rheumatism with considerable uncertainty about the combination of countless signs of disease, including laboratory values (rheumatism factors).
Search for specific receptor -characteristics
However, the scientists, including experts from the Tropical Institute of the University of Basel, followed a new idea: diseases cause specific reactions of the immune system of the affected. Very special receptors are trained on B and Timmunzellen. The idea of the experts: the receptors can possibly read where the body’s own defense system is currently concerned.
“Our immune system constantly monitors our body with B and T cells that work as molecular threat sensors. The combination of the information from these two main areas of the immune system offers us a more extensive picture of the defense system response to diseases and processes that lead to car -immunity (car -immune diseases; note) or vaccin reactions, ”Zaslavsky was quoted in a broadcast of the investigation of research on research.
AI system fed with 30 million data packages
In patients with infections or autoimmune diseases, the researchers have therefore selected certain parts in the genes for the B and T-Zell receptors. These receptors are there to detect pathogens or to cause defensive reactions that are misconception in the case of autoimmune diseases against the body’s own tissue. The scientists therefore created a program with the AI software Mal-ID (“Machine Learning for Immunological Diagnosis”) that for some diseases should recognize typical changes in the receptors of the immune cells.
“In a pilot study, Mal-ID evaluated the sequence data of 16.2 million B cell receptors and 23.5 million T cell receptors. They came from blood samples of 593 people, 63 of whom were infected with SARS-COV-2 and 95 with the hi virus, “said the German medical magazine. 86 of the test subjects had suffered under a car -immune disease (erythematos lupus), 92 type 1 diabetes (also a car -immune disease). 37 test subjects were vaccinated against the flu. 217 Test test subjects formed the control group as not influenced.
Almost 100 % accuracy
The result: Mal-ID recognized both the individual diseases such as SARS-COV-2 infections, HIV infections, Lupus, type 1 diabetes as well as the earlier flu vaccination with almost 100 % sensitivity (finding the affected) and specificity (if there is no objection). A difference depending on the type of disease: the gensquencies of the receptors of the test subjects of the test subjects identified the HIV and COVID-19 infections and flu vaccination. The T cell receptors identified the erythematodes and diabetic patients.
“Because the costs of sequence guys have fallen considerably in recent years, the procedure for clinical diagnostics can become interesting. This applies in particular to car -immune diseases, which are often only diagnosed after a month to years, ”wrote the German medical magazine.
Algorithm easily adjustable
Although the researchers have so far only developed on the basis of six diseases or immunological disorders (vaccination), they assume that algorithm can be quickly adjusted to identify immunological signatures that are specific to many other diseases and suffering. This is especially true for the complex car -immune diseases, which also include joint rehostism (rheumatoid arthritis, chronic polyarthritis).
“Patients often have to fight for years before they get a diagnosis, and even then the names we give these diseases, such as generic terms that overlook the biological diversity behind complex diseases,” said Zaslavsky. “If we could use Times ID to decipher the heterogeneity behind lupus or rheumatoid arthritis, that would have a big impact.”
Source: Krone
I am an experienced and passionate journalist with a strong track record in news website reporting. I specialize in technology coverage, breaking stories on the latest developments and trends from around the world. Working for Today Times Live has given me the opportunity to write thought-provoking pieces that have caught the attention of many readers.
