Scientists develop clinical tool to classify severity of COVID-19 patients

The researchers delved through the symptoms of millions of users, finding there to be six distinguished groupings of coronavirus symptoms, each with their own level of severity.

By ZACHARY KEYSER
Medical staff, wearing protective suits and face masks, work in an intensive care unit for coronavirus disease (COVID-19) patients at the Franco-Britannique hospital in Levallois-Perret near Paris as the spread of the coronavirus disease continues in France, April 15, 2020. (photo credit: REUTERS)
Medical staff, wearing protective suits and face masks, work in an intensive care unit for coronavirus disease (COVID-19) patients at the Franco-Britannique hospital in Levallois-Perret near Paris as the spread of the coronavirus disease continues in France, April 15, 2020.
(photo credit: REUTERS)
An international team of researchers have come up with a predictive method to determine if a patient infected with COVID-19 will need ventilator assistance or further medical support ahead of time, by clustering coronavirus symptoms into distinctive groupings.
The clinical tool - which has not yet been peer reviewed - was developed by Zoe Global Limited in collaboration with clinicians and scientists from the King’s College London, Massachusetts General Hospital and the Lund University Diabetes Centre, using listings posted early on in the coronavirus pandemic through the COVID Symptom Study Smartphone application.
The researchers delved through the symptoms of millions of users, finding there to be six distinguished groupings of coronavirus symptoms, each with their own level of severity.
"During the spread of the coronavirus disease 2019 (COVID-19) pandemic, the strain on healthcare systems has been felt globally and varying strategies for appropriate use of limited medical resource have been proposed," the researchers wrote in their findings. "However, heterogeneity in disease and presentation is evident, and the ability to predict required medical support 20 ahead of time is limited. In this work, we sought to develop a clinical tool based on the time series of early development of COVID-19 that could be predictive of the need for high-level care in individuals more likely to seek medical help."
The researchers then listed symptoms such as muscle pains, fever, persistent cough, diarrhea, loss of smell, headache, fatigue, etc., and based on the severity, group them together in six numbered clusters.
For example, within the less severe Cluster 1 patients would be experiencing muscle pain, cough, loss of smell and headaches - where these symptoms would also be classified as less severe - while fatigue, confusion, fever and fatigue were absent from the reporting. Whereas in Cluster 6, all the listed symptoms were present, among others, and considered severe in their own right - indicating a possible need for ventilator assistance.
The cluster classification a patient would be thrown into is also affected by body mass index (BMI), age, demographics, etc.
"Compared to Cluster 3 – 6, of which 8.6% - 19.8% required respiratory support, Cluster 1 and 2 represent milder forms of COVID-19 with 1.5% and 4.4% respectively, requiring respiratory support," the researchers explained. "These clusters showed 5 predominantly upper respiratory tract symptoms and were distinguished from each other by the absence of muscle pain in Cluster 2 compared to Cluster 1, and slightly increased reports of skipped meals and fever in Cluster 2. Cluster 1 had notably lower mean age and BMI than the clusters containing patients with higher likelihood of requiring respiratory support."
"Cluster 3 shows stronger gastrointestinal symptoms in isolation (diarrhea, skipped meals) and a relatively reduced need for respiratory support, of 3.7%. However, the associated rate of hospital visit was high compared to cluster 1 and 2. Cluster 4, 5 and 6 included participants reporting more severe COVID-19 with 8.6%, 9.9% and 19.8% of individuals within these clusters requiring respiratory support, respectively," the scientists continued. These three clusters represent distinct presentations, with Cluster 4 marked by the early presence of severe fatigue and the continuous presence of chest 5 pain and persistent cough."
"In turn, individuals in cluster 5 reported confusion, skipped meals and severe fatigue. Finally, individuals in Cluster 6 reported more marked symptoms of respiratory distress including early onset of shortness of breath accompanied by chest pain. These respiratory symptoms were combined with significant abdominal pain, diarrhea and confusion when compared with other clusters. The proportion of frail people was higher in cluster 5 and 6 than in what we consider to be the milder clusters."
Although not yet peer-reviewed, the researchers have hopes this clinical tool could be applied to real world situations to reduce the strain on healthcare systems amid the coronavirus pandemic.
They note that it not only could provide the hospitals a proper heads up when classify new COVID-19 patients, but would also allow hospitals to set up proper monitoring procedures such as respiratory and pulse oximetry monitoring for these patients if they feel the need to do so based on the initial classification - targeting higher risk individuals for increased care, making sure they receive the necessary treatment if their symptoms take a turn for the worse.
"The ability to predict medical resource requirements days before they arise has significant clinical utility in this pandemic," the researchers concluded. "If widely utilized, healthcare providers and managers could track large groups of patients and predict 15 numbers requiring hospital care and respiratory support days ahead of these needs arising, allowing for staff, bed and intensive care planning."