A new study found that COVID-19 symptoms occur in six different “clusters,” which can help predict which patients are most at risk and need respiratory support.
For the study, the researchers used a machine learning algorithm to analyze data from more than 1,600 patients in the US and UK who had tested positive for COVID-19 and had regularly recorded their symptoms on the Zoe health app. in March and April. The researchers then tested the algorithm using it on an additional 1,047 patients in the US, UK, and Sweden, who entered their symptoms into the app throughout May.
The study identified six groups of symptoms:
Group 1 (“flulike” without fever): headache, loss of smell, muscle aches, cough, sore throat, chest pain, no fever
Group 2 (“flulike” with fever): headache, loss of smell, cough, sore throat, hoarseness, fever, loss of appetite
Group 3 (gastrointestinal): headache, loss of smell, loss of appetite, diarrhea, sore throat, chest pain, no cough
Group 4 (severe level one, fatigue): headache, loss of smell, cough, fever, hoarseness, chest pain, fatigue
Group 5 (severe level two, confusion): headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle pain
Group 6 (severe level three, abdominal and respiratory): headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, fatigue, confusion, muscle pain, shortness of breath, diarrhea , abdominal pain
Although continuous cough, fever, and loss of smell (anosmia) are generally highlighted as the three key symptoms of COVID-19, data collected from app users shows that people may experience a wide range of different symptoms. , including headaches, muscle aches, fatigue, diarrhea, confusion, loss of appetite, shortness of breath and more, “notes a statement published in the Zoe app.” Progression and results also vary significantly between people, from symptoms mild flu or a simple skin rash to serious or life-threatening illness. “
The researchers also looked at which groups of patients were most likely to need ventilators or supplemental oxygen, and found that patients in groups 6, 5, and 4 (19.8 percent, 9.9 percent, and 8.6 percent, respectively) needed the most. respiratory support. But “only 1.5 percent of people with group 1, 4.4 percent of people with group 2, and 3.3 percent of people with group 3 COVID-19 needed respiratory help,” according to a statement from the King’s College London, whose researchers, along with scientists from Massachusetts General Hospital, provided information during the development of the application for the study.
The study authors suggested that these results “could be used to monitor at-risk patients and predict medical resource requirements days before they are needed,” adding, for example, that “patients who fall into group 5 or 6 on day 5 of illness are at significant risk for hospitalization and respiratory support and can benefit from home pulse oximetry with daily phone calls from their general practice to ensure that hospital care occurs at the appropriate point in the course of his illness. “
Study co-author Claire Steves, a clinical professor at King’s College London, tells Yahoo Life: “This study helps us see the different ways that COVID can present. It alerts us to symptoms that are particularly worrisome in the first few days if someone has a positive test, such as confusion, abdominal symptoms, and severe fatigue. More importantly, if we start monitoring symptoms in the first five days, we could get help for those who are on a more severe disease path earlier, and perhaps prevent them from really getting sick. ”
Linda Anegawa, an internist with the virtual primary care platform PlushCare, tells Yahoo Life that the results of the study are “interesting because, so far, we have focused primarily on patient characteristics, which [put] people at risk of serious illness. This is the first time I have seen the actual symptoms correlate with the severity of the disease. “
She adds: “While more research is needed, identifying the six groups can now begin to help clinicians stratify the risk of patients they are seeing and allocate resources to those patients who feel more likely to be severely affected. This is critical as resources are scarce and doctors are scattered, especially in the overvoltage areas. “
Anegawa also says that being able to identify which group corresponds to their symptoms “can help patients seek care sooner if they find their symptoms place them in one of the high-risk categories.”
Dr. Matthew Exline, a pulmonary and critical care specialist at Ohio State University Wexner Medical Center, tells Yahoo Life that the research is “very helpful,” even for patients with mild symptoms of coronavirus. “Many patients, when they are told they have COVID, there is obviously a lot of anxiety. Appropriately, we focus on the worst case scenario: the dangers if you end up in a fan, things like that. ” But knowing that you’re in a low-risk group could help ease that anxiety. Doctors may say, “‘Hey, a lot of people with your type of symptoms end up not needing much. [medical] help ‘is reassuring for patients and very helpful, ”he says.
Both Exline and Anegawa point out that the study, however, has not been peer-reviewed. Anegawa also expressed some concern about trying to group patients into groups: “I have seen many patients who appear to fluctuate between multiple symptom groups or who have characteristics of multiple groups, for example, a patient with diarrhea only. How would we classify these types of individuals? It is a difficult question.
But overall, Exline says using an app for COVID-19 patients to record their daily symptoms is “a great idea,” adding: “I think it’s an incredible use of data. One of the things that really is a challenge with COVID research is [that scientists have] so many questions and there is only a finite number of people trying to answer those questions. There are difficulties in humans to make hundreds of phone calls [to collect data on patients]. By asking willing people to enter their symptoms as it happens, you can get a lot of data. “
Anegawa agrees, adding: “In this era where virtual medicine is growing rapidly, healthcare apps are a great way to help patients collect data for their telemedicine visits. In the future, I envision apps that help detect symptomatic patients, again to save time and resources. “
Read more from Yahoo Life:
Do you want to receive daily news about lifestyle and wellness in your inbox? sign up here for the Yahoo Life newsletter.
