Latest discoveries

Chinese researchers develop prediction model for critical illness in COVID-19 patients

Xinhua | Updated: 2020-05-15 18:36
Members of the first group of imported COVID-19 patients diagnosed at Suifenhe port in Northeast China's Heilongjiang province who were cured and discharged from the hospital on April 21, 2020 wave goodbye to medics. [Photo by Pan Songgang/For]

GUANGZHOU -- Chinese researchers have developed a prediction model to help identify COVID-19 patients' risk of developing critical illnesses, according to the Guangzhou Institute of Respiratory Health.

The research led by Zhong Nanshan, a renowned respiratory specialist, was published in the journal JAMA Internal Medicine.

Identifying COVID-19 patients with a high risk of becoming critically ill is of great significance to the treatment plan and allocation of medical resources.

Researchers developed the model based on clinical data of 1,590 COVID-19 patients. They screened 72 clinical factors and identified 10 key risk factors that could be combined to help predict the development of critical illnesses, including chest radiography abnormality, age, hemoptysis, dyspnea, unconsciousness, and number of comorbidities.

They validated the prediction model on 710 patients and results showed that the accuracy rate reached more than 88 percent.

The prediction model has been used in several hospitals in Hubei Province including Leishenshan Hospital. The research team also developed an online risk calculator that is freely available to the public.

The research team will expand the research on big data of respiratory diseases including COVID-19 and develop more accurate and practical clinical tools, according to the institute.

Please feel free to contact us by sending your questions to or commenting on China Daily app. We will ask experts to answer them.

Editor's picks
Copyright 1995 - . All rights reserved. The content (including but not limited to text, photo, multimedia information, etc) published in this site belongs to China Daily Information Co (CDIC). Without written authorization from CDIC, such content shall not be republished or used in any form. Note: Browsers with 1024*768 or higher resolution are suggested for this site.
License for publishing multimedia online 0108263

Registration Number: 130349