Emory AI COVID Study Finds Serious Lung Damage in Patients

An Emory University-led study, published on June 10, has found that patients with severe COVID-19 suffer from serious lung deformities. The study, conducted by Emory University's AI.Health institute, involved an international collaboration with researchers from North America, Europe, and Asia.

Key Findings

The study analyzed CT scans from 3,443 patients across multiple institutions, creating 3D AI models of lungs from three groups: healthy individuals, patients with mild COVID-19, and severe COVID-19 cases requiring ventilators. The AI analysis identified significant lung shape differences in areas between the lungs across all severity levels of the disease.

Specific Observations

Differences were particularly notable on the basal surfaces of the lungs when comparing healthy individuals to severe COVID-19 patients. Researchers suggest that these deformations could impair lung function, affecting quality of life and potentially increasing overall mortality.

Experts have long known that COVID-19 can cause pneumonia, severe lung damage, and blood infections, potentially resulting in lung scarring and chronic breathing issues. While some patients recover fully, others may suffer permanent damage.

The Role of AI in Lung Analysis

The AI technology used in the study employed a 3D residual convolutional network to segment and analyze lung images. This method allowed researchers to map lung deformations in detail, highlighting specific areas of damage. By comparing lung images from healthy individuals and COVID-19 patients, the AI provided a comprehensive understanding of the damage caused by severe COVID-19.

Expert Insights

“Although the acute phase of COVID-19 has largely been mitigated, the persistence and impact of long COVID remain a concern. Our AI analysis identified specific areas of lung damage that could have enduring consequences,” said Anant Madabhushi, PhD, executive director of Emory AI.Health and principal investigator of the study. “While we have not yet examined long COVID patients explicitly, it’s crucial to investigate whether these individuals exhibit residual lung deformation, which could provide valuable insights into the long-term effects of this disease,” he added.

Amogh Hiremath, AI scientist at Picture Health and first author of the study, emphasized the importance of early understanding: “COVID-19 can cause serious complications such as pneumonia, severe lung damage, and blood infections, which can lead to lasting lung problems like scarring and chronic breathing issues. While some people recover fully, others may suffer permanent lung damage. Understanding how COVID-19 affects the lungs during its early onset can help us better understand and treat the disease.”

Study Limitations and Future Research

The study is retrospective in nature, and the clinical practicality of the AI used needs validation by following patients until discharge. Future research will explore lung shape differences among COVID-19 patients as a biomarker in the context of long COVID.

The Broader Implications

AI could revolutionize biotech, but collecting data to bring it to scale remains a significant challenge. As the immediate threat of COVID-19 subsides, investigating the virus’s lasting impacts remains essential. This study is a step towards understanding the long-term effects of severe COVID-19 on lung function and overall health.