Crown infection: symptoms vary significantly by age group


Early coronavirus symptoms usually vary with age group. This is proven by a new study.

© Imago

According to a British study, the early symptoms of coronavirus differ significantly depending on the age group. This knowledge is made possible by a new model of artificial intelligence.

London / Kassel – The symptoms of a coronary infection are varied, in addition to the typical colds such as cough, sore throat and runny nose, abdominal pain or shortness of breath may also indicate coronavirus, among others. However, especially in the coming colder seasons, it would be practical to see quickly if it is the flu or in fact Corona *.

Researchers at King’s College London have now answered that question. In a new study, the team tried to train an artificial intelligence (AI) to determine the possibility of Covid-19 infection based on the first symptoms.

The study, published in The Lancet Digital Health, also found differences in early symptoms in different age groups: For example, symptoms in the first three days between the ages of 16 and 39 differ significantly from those in those over 60 and over 80. years -Years.

University: King’s College London
Establishment: 1829
Number of students: 27,629 (Kiosk: 2016)
Entry rate: 13 percent (since 2014)

Artificial intelligence model looks at first signs of coronary heart disease

In previous research approaches, many artificial intelligence models only considered the symptoms at the peak of a disease, the scientists explained. At the beginning of the coronary infection, however, some symptoms could be better indicators than in the later course of the disease. A press release said the new results could be used to tailor recommendations for home isolation and early-stage testing.

Data from the Covid Symptom Study application were used for the study. This was developed by Zoe, a health science company. Zoe partnered with King’s College London and Massachusetts General Hospital in Boston to develop. Users of the app can provide information about their Covid 19 symptoms and share the results of PCR tests with the research team.

For their study, the team looked at the statements of 182,991 patients for about 18 symptoms in the first three days after the onset of symptoms. The data became available between the end of April and mid-October 2020. The artificial intelligence was trained with this data, which then analyzed the data of 15,049 other test subjects between October and the end of November 2020.

Study: Loss of smell and chest pain are the most common coronary symptoms

The relevant symptoms for early detection of a Covid 19 infection were therefore loss of smell, chest pain, persistent cough, stomach pain, blisters on the legs, overworked eyes and unusual muscle pain.

In all sexes, the most common symptoms were loss of smell and chest pain. Although fever is one of the known symptoms of coronary heart disease, it often did not make sense for the first three days. A recent Harvard University study found that people can be coronavirus *.

Early coronavirus symptoms vary with age group

However, the symptoms of coronavirus infection differed in different age groups. While persistent cough was a clear sign of illness in people between the ages of 40 and 59, in younger people the loss of smell indicates Sars-Cov-2 infection and Covid-19 infectious disease.

According to Artificial Intelligence, diarrhea, sore throat or muscle aches were the first signs in people over 80 years of age. However, coronavirus * symptoms also differ between vaccinated and unvaccinated individuals.

New artificial intelligence model detects coronary infections based on symptoms more often than other models

Artificial intelligence, developed by King’s College London, does not always diagnose Covid disease 19, but it is even more accurate than other algorithms that diagnose or predict coron infection. The sensitivity, ie the value at which the positives in the crown were also correctly predicted, was 73 percent. Lying down, the specialization, i.e. the probability that the negatives for the rim are also predicted to be correct negatives, was 72 percent.

The authors of the study now hope that the model will be well received. Liane dos Santos Canas, the study’s lead author, also hopes that knowing the different symptoms can help people get tested as early as possible to minimize the risk of transmission. (Nail Akkoyun) * is an offer from IPPEN.MEDIA.


Source link