AI can automatically assess if patients show signs of emphysema, according to a new study published in Radiology. The findings could be a significant breakthrough in chronic obstructive pulmonary disease (COPD) research.
A scoring system first proposed by the Fleischner Society is often used to detect signs of parenchymal emphysema. This Fleischner system, however, still poses certain problems for healthcare providers––and AI could be the answer.
“Visual analysis by using a structured scoring system is time consuming, subjective and requires substantial training, making it difficult to perform in routine practice,” wrote lead author Stephen M. Humphries, PhD, department of radiology at National Jewish Health in Denver, and colleagues. “A validated automatic technique to classify emphysema patterns could be useful for risk stratification in clinical practice and lung cancer screening programs. In addition, such a technique could permit selection of participants with specific grades of emphysema (or with no emphysema) for future COPD clinical trials.”
Humphries et al. trained a deep learning algorithm to identify signs of emphysema according to the Fleischner system. Data from more than 7,000 patients who participated in the Genetic Epidemiology of COPD (COPDGene) study were used to test the algorithm. Each patient had undergone a CT examination and additional clinical tests, participated in a six-minute walking test and answered multiple standardized questionnaires. An external testing cohort of nearly 2,000 patients was also explored to confirm the team’s findings.
Overall, the algorithm as able to accurately detect signs of emphysema by evaluating patient data. AI-classified cases of emphysema were associated with “clinical measures of pulmonary insufficiency and the risk of mortality.” The AI also helped reduce the Fleischner system’s “inherent subjectivity.”
“We believe that the deep learning system presented in this article may complement quantitative densitometric assessment of emphysema severity,” the authors wrote. “Other structured scoring systems have been used for visual classification of emphysema patterns, but to our knowledge, only the Fleischner system has been validated against mortality.”
Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.