[ad_1]
With communities across the nation experiencing a wave of COVID-19 infections, physicians need effective tools that enable them to aggressively and accurately treat each patient based on specific disease presentation, history of health and medical risks.
In a research recently published online in Medical image analysis, a team of engineers demonstrated how a new algorithm developed by them was able to successfully predict whether or not a COVID-19 patient would need intensive care intervention. This AI-based approach could be a valuable tool in determining the correct course of treatment for individual patients.
The research team, led by Pingkun Yan, assistant professor of biomedical engineering at Rensselaer Polytechnic Institute, developed this method by combining computed tomography (CT) images of the chest that assess the severity of a patient’s lung infection with non-diagnostic data. imaging, such as demographics information, vital signs and laboratory blood test results. By combining these data points, the algorithm is able to predict patient outcomes, particularly whether or not a patient will need an ICU intervention.
The algorithm was tested on datasets collected from a total of 295 patients from three different hospitals: one in the United States, one in Iran and one in Italy. The researchers were able to compare the algorithm’s predictions with the type of treatment a patient actually needs.
“As a practitioner of artificial intelligence, I believe in its power,” said Yan, who is a member of the Center for Biotechnology and Interdisciplinary Studies (CBIS) in Rensselaer. “It really allows us to analyze a large amount of data and also extract features that may not be so obvious to the human eye.”
This development is the result of research supported by a recent grant from the National Institutes of Health, which was awarded to provide solutions during this global pandemic. As the team continues its work, Yan said, the researchers will integrate their new algorithm with another that Yan had previously developed to assess a patient’s risk of cardiovascular disease using CT scans of the chest.
“We know that a key factor in COVID mortality is whether a patient has underlying conditions and heart disease is a significant comorbidity,” Yan said. “How much this contributes to the progress of their disease is, at this time, quite subjective. So, we need to have a quantification of their heart condition and then determine how to keep it in this prediction.”
“This critical work, led by Professor Yan, offers a viable solution for clinicians in the midst of a global pandemic,” said Deepak Vashishth, director of CBIS. “This project highlights the capabilities of Rensselaer’s experience in the field of bioimaging combined with important partnerships with medical institutions.”
Yan is joined in Rensselaer by Ge Wang, a chair professor of biomedical engineering and a member of CBIS, as well as graduate students Hanqing Chao, Xi Fang, and Jiajin Zhang. The Rensselaer team is working in partnership with Massachusetts General Hospital. When this work is completed, Yan said, the team hopes to translate its algorithm into a method that Massachusetts General doctors can use to evaluate their patients.
“We are actually seeing that the impact could go far beyond COVID diseases. For example, patients with other lung diseases,” Yan said. “Assessing their heart disease condition, along with their lung condition, could better predict their mortality risk so we can help them manage their condition.”
Source of the story:
Materials provided by Rensselaer Polytechnic Institute. Original written by Torie Wells. Note: The content can be changed by style and length.
.
[ad_2]
Source link
