The new study identifies 6 ‘groups’ of COVID-19 symptoms, which may help to ‘predict’ severe cases.


A new study has found that COVID-19 symptoms fall into six different “groups”, which can help predict which patients are at risk and need respiratory support.

For the study, researchers used a machine learning algorithm to analyze the data of more than 1,600 patients in the US and UK who tested positive for COVID-19, and regularly followed Zoe in March and April. Had logged his symptoms on the health app. The researchers then tested the algorithm on an additional 1,047 patients from the US, UK and Sweden who recorded their symptoms on the app in May.

The study identified six groups of symptoms:

Cluster 1 (“with fever” flowers): headache, lack of smell, muscle aches, cough, sore throat, chest pain, no fever

Cluster 2 (“Fluid” with fever): Headache, smell, cough, sore throat, hoarseness, fever, loss of appetite.

Cluster 3 (gastrointestinal): headache, lack of smell, loss of appetite, diarrhea, sore throat, chest pain, no cough

Cluster 4 (severe level one, fatigue): headache, smell, cough, fever, hoarseness, chest pain, tiredness

Cluster 5 (severe level two, confusion): headache, lack of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle aches

Cluster 6 (severe level three, stomach and respiratory): headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle aches, shortness of breath, diarrhea , stomach pain

“Although persistent cough, fever, and lack of smell (anosmia) are commonly highlighted as the three major symptoms of COVID-19, data collected from app users suggests that people may experience headaches, muscle cramps, One can experience a wide range of different symptoms including pain, fatigue., Diarrhea, confusion, loss of appetite, shortness of breath and more, “notes a statement published on the Zoe App.” Progress and results also among people Significantly different, ranging from mild to mild symptoms or simple rashes to severe or severe illness. “

Researchers also observed that groups of patients were more likely to require ventilators or supplemental oxygen and found that patients in clusters 6, 5 and 4 (19.8 percent, 9.9 percent and 8.6 percent, respectively) had the highest respiratory support. Was required. According to a statement from King’s College of London, “Only 1.5 percent of people with cluster 1, 4.4 percent of people with cluster 2, and 3.3 percent of people with cluster 3 COVID-19 are required to breathe,” whose researchers, along with Scientists at the Massachusetts General Hospital provided input during the development of the app for the study.

The study authors suggested that these results could be used to “monitor at-risk patients and predict medical resource needs before they are necessary,” for example, as “those patients who have 5 of the disease. Clusters a day fall into 5 or 6. There is a significant risk of hospitalization and breathing assistance and daily pulse oximetry may benefit from their normal practice to ensure that during their illness in hospital Have a proper presence. “

Claire Steve, co-author of the study, Clinical Senior Lecturer at King’s College London, tells Yahoo Life: “This study helps us look at the different ways COVID can present. It alerts us to symptoms that worry especially in the first few days if someone tests positive – such as confusion, abdominal symptoms, and severe fatigue. More importantly, if we started monitoring the symptoms in the first five days, we could help those who are on the path to a more serious illness earlier, and perhaps prevent them from actually getting sick. Huh. “

Linda Engeva, an internist at the virtual primary care platform Plushcare, tells Yahoo Life that the results of the study are “interesting because, until now, we’ve focused mostly on patient characteristics, which [put] People at risk of serious illness. This is the first example where I have noticed that the actual symptoms are related to the severity of the disease. “

She says: “While further research is needed, now identifying six groups can help doctors reduce the risk of patients they are seeing and allocate resources for patients who have severe Form is more likely to be affected. This is important because resources are scarce and doctors are thin, especially in surge areas.

Engenawa also says that being able to identify which cluster matches your symptoms “can help patients get care earlier if they feel their symptoms put them in high-risk categories” .

Dr., a Pulmonary and Critical Care Specialist at The Ohio State University Wexner Medical Center. Matthew Xline told Yahoo Life that the research is “very helpful”, including patients with mild coronavirus symptoms. “Many patients, when they are told they have COVID, obviously have a lot of anxiety. Appropriately, we focus on what the worst case is – the dangers if you end up on a ventilator Things like this happen. “But knowing that you’re in a low-risk cluster can help reduce that anxiety. Doctors say, “‘Hey, a lot of people with your symptoms don’t need much [medical] Help ‘is reassuring to patients and is very helpful, “he says.

Both Exline and Engenova state that the study, however, has not been peer reviewed. Engenova also expressed some concern about trying to group patients into groups: “I have seen many patients who fluctuate between multiple symptom groups or who have characteristics of multiple groups – e.g. , A patient with diarrhea only. How would we classify such people? This is a tricky question. “

But overall, Xline says that using an app COVID-19 patients can log their daily symptoms “is a great idea,” adding: “I think it’s a terrible use of data. COVID One of the things that is really a challenge with research is [that scientists have] There are so many questions and a limited number of people trying to answer those questions. Hundreds of phone calls cause difficulty for humans [to collect data on patients]. This is happening as you ask interested people to record their symptoms, you can get a lot more data. “

Anegawa agrees: “In an era where virtual medicine is growing rapidly, health apps are a great way to help patients gather data for their telemedicine visits. In the future, I envision apps that help screen patients with symptoms, to save time and resources. “

Read more from Yahoo Life:

Daily lifestyle and wellness news delivered to your inbox? Register here For Yahoo Life’s newspaper.

Leave a Reply

Your email address will not be published.