Investigating AI's potential in risk-stratifying lung cancer screenings for extending screening intervals and reducing workload: A retrospective analysis of a tertiary hospital cohort
- 1University of California, San Francisco
Abstract
Objective: We aimed to 1) evaluate whether AI algorithms could identify a very low-risk sub-population Lung-RADS 1/2 cases suitable for a safe switch to biennial screening, and 2) externally validate Sybil, an imaging-based deep learning lung cancer risk prediction tool. Materials and methods: We gathered all lung cancer screenings (LCSs) from a tertiary safety-net hospital (n=3120, up to September 2024), manually extracted relevant clinical data, and analyzed Sybil's performance across various subgroups, with a specific focus on Lung-RADS 1 and 2 cases. We simulated LCS interval extension using Sybil and the Brock model risk scores calibrated on a subset of the National Lung Screening Trial (NLST). Confidence intervals were obtained through bootstrapping. Results: The median follow-up was 2.3 years (interquartile range 1.5-3.1), with a total 6-year cancer incidence rate of 2.3% (72/3120). Lung-RADS 1 and 2 cases comprised 90.5% of our scans. Sybil's overall area under the curve (AUC) ranged from 0.819 to 0.912; while its 2-year AUC for Lung-RADS 1 and 2 cases was 0.746. In the screening interval extension simulation, calibrating for a 30% shift to biennial screening translated into 33.8% of negative screens in our data being safely extended using Sybil, with no delayed cancers. The Brock model demonstrated an AUC of 0.513 on our data, with a sensitivity of 18.2% using the 1.5% threshold. Conclusion: Sybil has the potential to safely extend LCS intervals for low-risk individuals, reducing radiology workload and opening spots for life-saving new screenings.
Related
- The Influence of Trauma Screenings on Scheduling Assessment of Children Referred to Community Based Mental Health Services
- Investigating a Potential Link Between Metabolic-Neurotrophic Coupling in Breast Tumor Innervation in Bioengineered Models
- Investigating potential molecular mechanisms linking 6PPD-quinone exposure to Intervertebral Disc Degeneration: A network toxicology, molecular docking, and molecular dynamics simulation study
- Development and validation of a nomogram for stratifying severe Mycoplasma pneumoniae pneumonia risk in children early
- Investigating the potential effect of topiramate on anorexia nervosa and binge eating behaviour using drug-target Mendelian randomization
BibTeX
@misc{nowroozi2026investigating,
title = {{Investigating AI's potential in risk-stratifying lung cancer screenings for extending screening intervals and reducing workload: A retrospective analysis of a tertiary hospital cohort}},
author = {A. Nowroozi and M. Bondarenko and S. S. Brar and B. Haas and J. Brown and A. Rustagi and B. Graham and M. Hudson and G. Su and A. Yala and J. H. Sohn},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.26367146},
url = {https://www.medrxiv.org/content/10.64898/2026.11.03.26367146v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Investigating AI's potential in risk-stratifying lung cancer screenings for extending screening intervals and reducing workload: A retrospective analysis of a tertiary hospital cohort
AU - A. Nowroozi
AU - M. Bondarenko
AU - S. S. Brar
AU - B. Haas
AU - J. Brown
AU - A. Rustagi
AU - B. Graham
AU - M. Hudson
AU - G. Su
AU - A. Yala
AU - J. H. Sohn
PY - 2026
DA - 2026/11/03
PB - medRxiv
DO - 10.64898/2026.11.03.26367146
UR - https://www.medrxiv.org/content/10.64898/2026.11.03.26367146v1
AB - Objective: We aimed to 1) evaluate whether AI algorithms could identify a very low-risk sub-population Lung-RADS 1/2 cases suitable for a safe switch to biennial screening, and 2) externally validate Sybil, an imaging-based deep learning lung cancer risk prediction tool. Materials and methods: We gathered all lung cancer screenings (LCSs) from a tertiary safety-net hospital (n=3120, up to September 2024), manually extracted relevant clinical data, and analyzed Sybil's performance across various subgroups, with a specific focus on Lung-RADS 1 and 2 cases. We simulated LCS interval extension using Sybil and the Brock model risk scores calibrated on a subset of the National Lung Screening Trial (NLST). Confidence intervals were obtained through bootstrapping. Results: The median follow-up was 2.3 years (interquartile range 1.5-3.1), with a total 6-year cancer incidence rate of 2.3% (72/3120). Lung-RADS 1 and 2 cases comprised 90.5% of our scans. Sybil's overall area under the curve (AUC) ranged from 0.819 to 0.912; while its 2-year AUC for Lung-RADS 1 and 2 cases was 0.746. In the screening interval extension simulation, calibrating for a 30% shift to biennial screening translated into 33.8% of negative screens in our data being safely extended using Sybil, with no delayed cancers. The Brock model demonstrated an AUC of 0.513 on our data, with a sensitivity of 18.2% using the 1.5% threshold. Conclusion: Sybil has the potential to safely extend LCS intervals for low-risk individuals, reducing radiology workload and opening spots for life-saving new screenings.
ER -