Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Performance and Utility of the Sybil Deep Learning Model for Lung Cancer Risk Prediction in Asian High- and Low-Risk

Yeon Wook Kim1, Jeongbin Oh2, Jinyong Park3

  • 1Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, South Korea; Department of Internal Medicine, Seoul National University Bundang Hospital Healthcare Innovation Park, Seoul, South Korea.

Chest
|May 15, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Human-in-the-loop validation of a sequential multi-LLM medical education pipeline.

NPJ digital medicine·2026
Same author

Feasibility and psychometric evaluation of large language model-generated radiology learning materials for board examination preparation: a prospective pilot study.

BMC medical education·2026
Same author

Electronic cigarette use after smoking cessation and lung cancer risk.

Nature medicine·2026
Same author

Meaningful Thresholds for Change in Quantitative CT-Derived Fibrosis Extent in Idiopathic Pulmonary Fibrosis.

American journal of respiratory and critical care medicine·2026
Same author

Clinical characteristics of post-operative N2 nodal upstaging in non-small cell lung cancer: a retrospective cohort study.

Translational lung cancer research·2026
Same author

Lung Microphysiological System Validates Novel Cell Therapy for Acute Respiratory Distress Syndrome.

Advanced biology·2025

Sybil, a deep learning model, accurately predicts lung cancer risk from CT scans in an Asian population. This tool shows promise for personalized lung cancer screening strategies, improving early detection and patient outcomes.

Area of Science:

  • Radiology and Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Sybil is a deep learning model for predicting lung cancer risk using low-dose chest CT (LDCT) scans.
  • It enables a precision-based approach to lung cancer screening (LCS).

Purpose of the Study:

  • To evaluate the performance and utility of the Sybil model in a pragmatic Asian LCS cohort.
  • Assessing Sybil's effectiveness across diverse risk profiles within this population.

Main Methods:

  • Analysis of 21,087 individuals aged 50-80 undergoing LDCT screening (2009-2021).
  • Sybil evaluated baseline LDCT scans for 1-6 year lung cancer risk prediction.
  • Model performance assessed using Area Under the Receiver Operating Characteristic Curve (AUROC), stratified by smoking history.
Keywords:
artificial intelligencelow-dose CT scanlung cancer screeningrisk prediction

Related Experiment Videos

Main Results:

  • Sybil achieved AUROCs of 0.86 for 1-year and 0.74 for 6-year invasive lung cancer predictions.
  • Performance varied across subgroups, with higher AUROCs in never-smokers (0.86 for 1-year, 0.79 for 6-year).
  • Five-year overall survival rates for lung cancer cases differed significantly by smoking history.

Conclusions:

  • Sybil demonstrated robust lung cancer risk prediction performance in a diverse Asian screening cohort.
  • The findings support Sybil's potential for developing personalized LCS strategies tailored to region-specific needs.