Researchers at Case Western Reserve University have developed an integrated clinical and CT-based AI nomogram (CIAIN) to predict which COVID-19 patients need a ventilator. CIANE can more precisely identify patients at an earlier disease presentation who may need intubation and invasive mechanical ventilation. The novel approach would decrease disease progression and mortality.
The study included a chart review of 869 SARS-CoV-2 positive patients who were diagnosed in January 2020 from Renmin Hospital of Wuhan University, Hubei General Hospital, and University Hospitals, Cleveland. Baseline clinical characteristics and chest CT scans were acquired for all patients. The selected patients were in the mild stage of the disease and without any respiratory assistance.
How does it work?
A chest CT scan is uploaded as a digitized image where CIAIN can detect and analyze distinctive features that are not visible to the naked eye. An algorithm can then determine whether the patient is at an increased risk of respiratory distress and may require a ventilator.
The prognostic approach assists medical staff in determining which patients need early supportive interventions to slow down disease progression. Despite increasing vaccination rates, early identification of ventilator candidates is imperative, given the worldwide shortage in ventilators with the recent emergence of the Delta variant.
Reference:
Hiremath A, Bera K, Yuan L, Vaidya P, Alilou M, Furin J, Armitage K, Gilkeson R, Ji M, Fu P, Gupta A, Lu C, Madabushi A. Integrated Clinical and CT based Artificial Intelligence nomogram for predicting severity and need for ventilator support in COVID-19 patients: A multi-site study. IEEE J Biomed Health Inform. 2021 Aug 13;PP. doi: 10.1109/JBHI.2021.3103389. Epub ahead of print. PMID: 34388099.
Image by PIRO4D from Pixabay