APSR2026-551

 
Late-Breaking
Submitted
Oral Presentation
AO31-003
 
 
https://storage.unitedwebnetwork.com/files/1285/1216361-46903-APSR_2026_Sybil_20261119_440603.pptx
Format: PPTX Only
 
Format: PDF Only
08. Lung Cancer
3

No more than 15 authors can be listed.
Please ensure the authors are listed in the right order.
If there are multiple affiliations, please use the "+" button next to "Select Country/Region" to add additional affiliation fields.

Kei Chuen Ma * Wong Tai Sin Hospital, Hospital Authority Department of Tuberculosis and Chest Hong Kong Hong Kong
Kwok Sang Yee - Wong Tai Sin Hospital, Hospital Authority Department of Tuberculosis and Chest Hong Kong Hong Kong
Cee Zhung Steven Tseng - Wong Tai Sin Hospital, Hospital Authority Department of Tuberculosis and Chest Hong Kong Hong Kong
 
 
 
 
 
 
 
 
 
 
 
 
Presenting Author Details
Kei Chuen
Ma
philipma1025@gmail.com
+85294302466
31-40
 
Original Research
Validation of the Sybil Deep Learning Lung Cancer Risk Prediction Model in a Hong Kong Chinese Population
Maximum 25 words
Abstract Content
Earlier detection of lung cancer through imaging can reduce preventable deaths, but implementing efficient, scalable early-detection service models is challenging. Sybil is a deep learning model originally trained using low-dose CT data from the U.S. (Mikhael PG et al, J Clin Oncol. 2023;41(12):2191-2200) National Lung Screening Trial (NLST) to predict future lung cancer risk from CT scans. While Sybil has shown promising performance in its development setting, its generalizability to Chinese populations and real-world clinical settings in Hong Kong has not been established. Local validation is essential before considering deployment to support risk stratification, clinical decision-making, or pathway redesign for earlier detection. Aim: To evaluate the real-world discriminatory performance of the Sybil deep learning model for lung cancer risk prediction in a Hong Kong Chinese population undergoing CT thorax imaging, and to describe key clinical differences between cancer and non-cancer groups in this cohort.
We performed a retrospective validation study including 458 individuals aged 43–82 years who underwent CT thorax scans between 2022 and 2024 in hospitals under the Hong Kong Hospital Authority. The cohort comprised 256 participants with histologically confirmed lung cancer and 202 individuals without evidence of lung cancer (non-cancer controls). Demographic and clinical characteristics were compared between groups, including smoking status and radiologic nodule size. Sybil-generated risk predictions were obtained from CT scans and model discrimination was assessed using the area under the receiver operating characteristic curve (AUC). Group comparisons were evaluated using standard statistical testing, with significance defined as p<0.05.
The lung cancer group had a higher prevalence of smoking compared with non-cancer controls (86% vs 24%). The mean nodule size was larger among participants with lung cancer than among controls (2.1 cm vs 1.1 cm; p<0.05). Sybil demonstrated strong discriminatory performance for lung cancer in this Hong Kong Chinese population, achieving an AUC of 0.87. These findings suggest good separation of cancer versus non-cancer cases based on CT-derived model predictions in routine clinical imaging data.
In a real-world cohort of patients undergoing CT thorax imaging within the Hong Kong public hospital system, the Sybil deep learning model showed good performance in distinguishing lung cancer from non-cancer individuals.
 
 
 
 
 
Yes
No
 
JPG or JPEG or PNG format ONLY
AI implementation, lung cancer detection
maximum 3 keywords and no abbreviations, separated by commas
 
364