- Researchers at King’s College London deal with corona symptoms
- Artificial intelligence trained: AI should be early Corona-Symptome recognize and classify
- Success: Method shows higher accuracy than previous ones Diagnostic algorithms
- The results are revealing: Age plays a decisive role in symptoms
It has long been known and also feared: The Symptoms of a corona infection partly differ extremely. This is why infections are often detected much too late. While some with typical Flu symptoms, like coughing, fever or runny nose, fighting, others lose their sense of taste or smell or complain of gastrointestinal complaints. Researchers at King’s College in London have now examined this phenomenon in more detail and have come to new results in a recent study.
Early corona symptoms in particular differ significantly depending on the age of the sick
The one in the trade journal „The Lancet Digital Health“ The study that has been published clearly shows that there are significant differences in the symptoms of the disease, especially in the first three days of the corona infection. The researchers have one Artificial Intelligence (AI) trained to determine the likelihood of Covid-19 infection based on early symptoms.
The results are surprising: For example, the symptoms in the first three days in 16 to 39 year olds differ significantly from those in over 60 or over 80 year olds. For the study, the team of scientists examined the information from 182,991 participants on 18 different symptoms in the first three days after the onset of symptoms. The participants made their data available between the end of April and mid-October 2020. The AI was trained with this data.
The researchers then tested it Diagnostic model the AI on the data of 15,049 participants who reported their symptoms via the app between mid-October and the end of November 2020. For the study, the team analyzed data from the Covid Symptom Study app, in which participants * can enter their symptoms and their PCR test results.
Symptoms have different relevance for the early detection of corona
The results of the KI study show that some symptoms are more relevant to early detection than others: loss of smell, chest pain, persistent cough, abdominal pain, blisters on the feet, tired eyes and unusual muscle pain are relevant symptoms Early disease, the most common being loss of smell and chest pain.
Although fever is one of the known symptoms of Corona, it was often not meaningful in the first three days after the onset of symptoms. But what was important: Depending on the age, certain symptoms lose their relevance. It was shown that protracted coughs in people between 40 and 59 years of age compared to younger age groups as a symptom more telling than a sign of a Corona disease war.
And in people over 60, the loss of smell became less important compared to younger age groups – in people over 80, according to the AI, it even became completely irrelevant. The sick over 80 years of age complained more often of diarrhea, sore throats or muscle pain compared to younger people.
There are also differences in symptoms between men and women
There were also differences in categories other than age group: Loss of smell and chest and abdominal pain were the most important symptoms of an incipient corona infection across all sexes. In men, however, shortness of breath, tiredness and chills were more typical than in women. And even if these data were all obtained from the wild type of the virus and the alpha variant, according to the researchers, they are also for the Delta-Variant such differences can be expected in different population groups.
In contrast to other algorithms, the AI that researchers trained in the latest study is significantly more accurate. The team of scientists hopes that the results will contribute to the early Treatment of corona infections but also to get people to take tests at an early stage.