Clinical symptoms have a key role to play in the early detectionand treatment of a disease. While some COVID-19 patients may remain asymptomatic, several others may go on to develop severe pneumonia.¹ Moreover, symptoms usually coexist in a patient.

Therefore, it might help to determine and understand if symptom clusters exist in COVID-19 patients that may guide treatment approach.

Sudre and colleagues used data from the COVID Symptom Study, a prospective population-based study, which collected daily reports of symptoms from millions of users of the symptom tracker app.²

A machine learning algorithm assessed the data from a training sample of 1653 users of the app in the UK and US with confirmed COVID-19. These users had logged their symptoms in March and April, 2020. The study also included an independent replication sample of 1047 participants from UK, US, and Sweden.^2,3

Six distinct clusters of symptoms were obtained. These include:

• Cluster 1: Flu-like with no fever —headache, muscle pains, loss of smell, cough, sore throat, chest pain; no fever
• Cluster 2: Flu-like with fever —headache, loss of smell, cough, sore throat, hoarseness, loss of appetite and fever
• Cluster 3: Gastrointestinal —headache, loss of smell, loss of appetite, sore throat, chest pain, diarrhea; no cough
• Cluster 4: Severe level one —headache, loss of smell, cough, fever, hoarseness, chest pain and fatigue
• Cluster 5: Severe level two —headache, loss of smell, loss of appetite, cough, fever, sore throat, hoarseness, muscle pain, chest pain, fatigue and confusion
• Cluster 6: Severe level three —headache, loss of smell, loss of appetite, cough, fever, hoarseness, sore throat, chest pain, muscle pain, shortness of breath, diarrhea, abdominal pain, fatigue, and confusion.

References

1. Cheng X, Wan H, Yuan H, et al.Symptom cluster patterns based on text clustering method of COVID-19 and its population characteristics in Sichuan province, China. Available from: https://assets.researchsquare.com/files/rs-453085/v1/edeedb2a-70ff-4849-a946-769c41c33fd9.pdf?c=1631882126. Accessed on September 20, 2021.
2. Sudre CH, Lee KA, Lochlainn MN, et al.Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app.Sci Adv. 2021 Mar; 7(12): eabd4177.
3. Wise J.Covid-19: Study reveals six clusters of symptoms that could be used as a clinical prediction tool. BMJ 2020;370:m2911.