Sign in Subscribe
Artificial intelligence

Artificial Intelligence Enhances COVID-19 Diagnosis with New Research Findings

Strategic Insights

— 1 min read

Researchers at the George Emil Palade University of Medicine in Targu Mures, Romania, have developed a new approach to diagnose COVID-19 using artificial intelligence (AI) algorithms. The study aimed to analyze the correlation between lung lesions identified on CT scans and biological inflammatory markers assessed to establish the survival rate among patients. The research found strong and very strong correlations between the derived inflammatory markers, interleukin-6, and the CT severity scores obtained by the AI algorithm.

Key Takeaways:

  • The study included 120 patients diagnosed with moderate to severe COVID-19 pneumonia who were admitted to the intensive care unit and the internal medicine department between September 2020 and October 2021.
  • Each patient underwent a chest CT scan, which was analyzed by two radiologists and an AI post-processing software.
  • The study found strong and very strong correlations between the derived inflammatory markers, interleukin-6, and the CT severity scores obtained by the AI algorithm (r=0.851, p < 0.01).
  • The research concluded that when combined with inflammatory markers, AI provides a reliable and objective method for evaluating COVID-19 pneumonia, enhancing the accuracy of diagnosis.
  • The study notes that the increased workloads during the COVID-19 pandemic led to the development of various AI tools to enable quicker diagnoses and quantitative evaluations of the lesions.
  • The research was conducted by a team of researchers including Anca Meda Vasiesiu, Ioana Halmaciu, Andrei Manea, Andrei Dragomir, Ioana Tripon, Vlad Vunvulea, Cristian Boeriu, Andrea Rus, and Minodora Dobreanu.

Statistics:

  • 120 patients were included in the study.
  • The patients were admitted to the intensive care unit and the internal medicine department between September 2020 and October 2021.
  • The study found that the correlations between the derived inflammatory markers, interleukin-6, and the CT severity scores obtained by the AI algorithm were strong and very strong (r=0.851, p < 0.01).

Sources:

  • The Journal of Critical Care Medicine, 2025;11(3):247-256.
  • NewsRx. Researchers at George Emil Palade University of Medicine Target Artificial Intelligence (Artificial intelligence algorithms based approach in evaluating COVID-19 patients and management). Medical Letter on the CDC & FDA. August 24, 2025; p 165.

Read more