Marcelo Bellucci
08/03/2020 - 10:16
- Clarín.com
- Society
Using data collected by an epidemiological research application, a team of scientists was able to identify the six types of coronavirus that are currently circulating and what are the most recurring symptoms that patients experience. This finding could serve for the clinical management of Covid-19 and help doctors predict who is most at risk and who needs hospital care in a second wave of infections.
The COVID Symptom Study app - developed in collaboration by King's College London and Guy's and St Thomas Hospital - was launched in mid-March in the UK and extended to the US and Sweden. It asks participants to record their health and any new potential symptoms of Covid-19 on a daily basis. With more than 4 million users, this represents one of the largest and most comprehensive studios of its kind.
To find out whether the particular symptoms manifest together and how it relates to disease progression, the scientists used a machine learning algorithm to analyze data from a subset of around 1,600 users who had coronaviruses and had regularly recorded their ailments. .
"Being able to collect large data sets through the app and apply machine learning to them is having a profound impact on our understanding of the scope and impact of Covid-19 and human health in general," said Sebastien Ourselin, professor of health care engineering at King's College London and lead author of the study.
Although continuous cough, fever, and loss of smell (anosmia) rank as the three most frequent symptoms, the data collected shows that people can experience a wide variety such as headaches, muscle aches, fatigue, diarrhea, confusion, loss of appetite, skin irritation, and shortness of breath.
Most reported headache and loss of smell as the most common, with various additional combinations progressively manifesting. Some of these, such as confusion, abdominal pain, and shortness of breath, are not widely known.
"These findings have important implications for the care and follow-up of people who are most vulnerable to severe COVID-19," explains geriatric consultant Dr. Claire Steves, one of the experts working on the study.
Subsequent analysis of the data revealed the six distinct "types" of Covid-19, each of which is distinguished by a particular group of signals.
1. Similar to the flu, no fever: headache, loss of smell, muscle aches, cough, sore throat, chest pain, no fever.
2. Similar to the flu, with fever: headache, loss of smell, cough, sore throat, hoarseness, fever, loss of appetite.
3. Gastrointestinal Covid-19: headache, loss of smell, loss of appetite, diarrhea, sore throat, chest pain, no cough.
4. Covid-19 level one severe, with fatigue: headache, loss of smell, cough, fever, hoarseness, chest pain, fatigue.
5. Covid-19 severe level two, with confusion: headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle pain.
6. Covid-19 severe level three, with abdominal pain and respiratory distress: headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle pain, lack breath, diarrhea, abdominal pain.
“By knowing who these people are on the fifth day, there would be time to provide support and early interventions, such as monitoring oxygen and blood sugar levels, and making sure they are adequately hydrated. A simple consultation that could be done at home, avoiding hospitalizations and saving lives, "says Steves.
The team crossed these data to find out whether people experiencing particular groups of symptoms were more likely to need respiratory support in the form of ventilation or additional oxygen.
In addition, they developed a model that combines information on age, sex, body mass index, and pre-existing conditions along with collected symptoms, to predict which of the six groups is most likely to relapse. And how likely are you to require hospitalization and respiratory support.
Since most people who require respiratory assistance come to the hospital about 13 days after their first symptoms, these additional eight days represent a significant "early warning" about who is most likely to need more intensive care.
GS