Machine learning model for circulating tumor DNA detection in chronic obstructive pulmonary disease patients with lung cancer

Authors
Sun Hye Shin, Soojin Cha, Ho Yun Lee, Seung-Ho Shin, Yeon Jeong Kim, Donghyun Park, Kyung Yeon Han, You Jin Oh, Woong-Yang Park, Myung-Ju Ahn, Hojoong Kim, Hong-Hee Won, Hye Yun Park
Journal
Translational Lung Cancer Research
Related Product

COPD

Date Published
2024.01
Summary

Shin, Cha, Lee, and colleagues developed a machine learning model to predict ctDNA presence in COPD patients with lung cancer, aiming for a non-invasive diagnostic approach. Utilizing deep sequencing, chest CT analysis with Aview software, and machine learning algorithms (AUC = 0.774), they identified ctDNA mutations in 30.5% of patients. Aview was used to quantify emphysema (emphysema index, EI), showing that advanced tumor stage, higher CRP, and milder emphysema were associated with ctDNA detection. Patients with severe emphysema had lower ctDNA detection, possibly due to reduced tumor DNA shedding. This study suggests ctDNA’s diagnostic potential in milder emphysema cases, while indicating a need for complementary diagnostics in severe cases. The model’s insights could impact ctDNA-based lung cancer screening, with future work expanding to broader populations and additional validation to improve accuracy and applicability.

Contact

제품, 인재 채용, 투자 관련 또는 기타 문의사항이 있으신 경우 편하신 방법으로 연락주시기 바랍니다

문의하기