Four distinct subtypes of long-term COVID defined in a machine learning study
Using machine learning to track symptom clusters in around 35,000 COVID patients, the researchers identified four distinct types of long-term COVID. The findings suggest that long-term COVID is a diverse disease with a wide variety of clinical manifestations.
The new research looked at two large cohorts of patients, all with at least one persistent symptom that lasted between 30 and 180 days after a SARS-CoV-2 infection. A machine learning algorithm sorted through the mass of data, covering around 137 different persistent symptoms.
In a new study published in Natural medicinethe researchers describe “four subphenotypes dominated by new conditions of the cardiac and renal systems (Subphenotype 1); problems of the respiratory system, sleep and anxiety (Subphenotype 2); musculoskeletal and nervous systems (Subphenotype 3); and digestive and respiratory systems (Subphenotype 4)”.
The first subtype was found to be the most common, accounting for 34% of long-term COVID patients in the data set. This subtype included patients with heart and kidney problems, anemia, and circulatory disorders.
This manifestation of prolonged COVID was more frequent in older patients (with a mean age of 65 years) and in those with severe COVID. Interestingly, this long-term COVID subtype was most prominent in those infected during the first wave of the disease during the first half of 2020.
The second subtype identified, almost as common as the first, accounted for 33% of all cases. This appearance of prolonged COVID was dominated by persistent respiratory symptoms, chest pain, anxiety, headache, and insomnia.
Unlike the first subtype, this second type of long-term COVID was associated with milder acute illness. It also appeared more common in patients infected later in the pandemic (between November 2020 and November 2021).
The third subtype (23% of patients) was mainly related to musculoskeletal and nervous system disorders, including nerve pain and headache. This subtype was seen more frequently in patients with pre-existing autoimmune conditions, such as rheumatoid arthritis and asthma.
The last subtype was the rarest, only seen in 10% of patients. It was dominated by gastrointestinal disturbances, including stomach pain, nausea, and intestinal problems. This latter subtype was associated with milder acute disease.
Rainu Kaushal, from the Department of Population Health Sciences at Weill Cornell Medicine and a co-senior author of the new study, said that better understanding the variety of clinical manifestations of long-term COVID not only helps clinicians treat patients effective, but guides researchers working to develop new treatments for this chronic condition.
“Understanding the epidemiology of long-term COVID allows clinicians to help patients understand their symptoms and prognoses and facilitates multi-specialty treatment for patients,” Kaushal said. “Electronic health records offer a window into this condition, allowing us to better characterize prolonged COVID symptoms, informing other types of research, including pivotal discoveries and clinical trials.”
The study is not the first to try to divide long-term COVID into different subtypes. A large UK study published in 2022 suggested that the condition can be divided into three groups of symptoms (cognitive, respiratory, and everything in between).
However, these new findings offer the most robust and comprehensive categorization of long COVID subtypes to date. And the next step for the research team will be to better identify the risk factors for each long subtype of COVID and determine whether some treatments are more effective for certain subtypes than others.
The new study was published in Natural medicine.
Font: Weill Cornell Medicine