A new model accurately predicts the risk of disease progression in COVID-19 patients, researchers from China revealed. The team of researchers led by Dr. Enqiang Qin from the Fifth Medical Center of Chinese PLA General Hospital, Beijing used the data collected from over 200 COVID-19 patients to develop it.

The new risk prediction model can help clinicians identify an optimal therapeutic strategy for any particular patient.

“We aimed to clarify the high-risk factors with multivariate analysis and establish a prediction of disease progression, so as to help clinicians to better choose a therapeutic strategy,” said the researchers in the paper published in Clinical Infectious Diseases.

The study participants were COVID-19 patients, including those whose clinical conditions deteriorated during the observation period. The average age was recorded to be 44 years and 14.9% of them were over 60 years old. 56.2% of them were men and about 21.6% were diagnosed with at least one underlying comorbidity. The average duration of their hospital stay was nearly 17.5 days.

The research team conducted multivariable analyses that revealed the following factors associated with an increased risk of disease progression:

  • Comorbidity
  • Age >60
  • Lymphocyte count of 1 billion per liter or lower
  • Lactate dehydrogenase level between 250 and 500 U/L
  • LDH >500 U/L

Using the above-mentioned factors, the research team developed the CALL scoring model which assigned points for each of them. This scoring model was found to be 91% accurate for differentiating patients whose illness progressed and those who didn’t.

“Using the CALL score model, clinicians can improve the therapeutic effect and reduce the mortality of COVID-19 with more accurate and reasonable resolutions on medical resources,” the study authors concluded.

Earlier in March, the experts at the NYU School of Medicine developed a tool using artificial intelligence that predicted which COVID-19 patients would go on to develop severe respiratory disease.

“Our goal was to design and deploy a decision-support tool using AI capabilities - mostly predictive analytics - to flag future clinical coronavirus severity. We hope that the tool, when fully developed, will be useful to physicians as they assess which moderately ill patients really need beds, and who can safely go home, with hospital resources stretched thin," Science Daily quoted  Anasse Bari, Ph.D., a clinical assistant professor in Computer Science at the Courant Institute.

A group of doctors working with patients infected with the novel coronavirus COVID-19 wear face shields at the Intensive Care Unit of the Hospital de Clinicas in Porto Alegre, Brazil A group of doctors working with patients infected with the novel coronavirus COVID-19 wear face shields at the Intensive Care Unit of the Hospital de Clinicas in Porto Alegre, Brazil Photo: AFP / Silvio AVILA