The Lung Cancer Channel is supported with funding from Johnson & Johnson (Gold).
VJOncology is an independent medical education platform. Supporters, including channel supporters, have no influence over the production of content. The levels of sponsorship listed are reflective of the amount of funding given to support the channel.
WCLC 2026 | Sybil implementation and social determinants of lung cancer risk prediction
Evan Garrad, MD, University of Illinois Chicago, Chicago, IL, discusses the implementation of the Sybil, an open access machine learning model that assesses lung cancer risk from low-dose CT scans, and presents exploratory analysis on the associations between patient and neighborhood characteristics and Sybil scores in a diverse, high-risk patient population. The analysis revealed several associations with social determinants of health, which are hypothesis-generating for future research. This interview took place at the IASLC 2026 World Conference on Lung Cancer congress in Seoul, Republic of Korea.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
Transcript
Yes, so we at UIC are fortunate to be part of the Sybil consortium. We were chosen as one of the first clinical sites to implement Sybil. So Sybil is an open access machine learning model that looks at low dose CT scans and generates a one to six year lung cancer risk with higher scores representing a higher relative risk of cancer. What we were interested in at UIC, since we have a very diverse patient population that’s high risk and really a safety net population within our hospital, we looked at our patient population and how Sybil interacts...
Yes, so we at UIC are fortunate to be part of the Sybil consortium. We were chosen as one of the first clinical sites to implement Sybil. So Sybil is an open access machine learning model that looks at low dose CT scans and generates a one to six year lung cancer risk with higher scores representing a higher relative risk of cancer. What we were interested in at UIC, since we have a very diverse patient population that’s high risk and really a safety net population within our hospital, we looked at our patient population and how Sybil interacts. What we were interested in this analysis and looking at are what are the underlying patient associations in terms of their individual characteristics and the neighborhood characteristics that they live in, and how that might be associated with Sybil scores. Sybil is a novel AI platform, and so a lot of this was exploratory analysis. We looked at multiple social determinants of health and saw several associations that I think are still, like I said, exploratory, but really hypothesis generating for the future.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
Read more...
