APSR2026-186

Yes
Late-Breaking
Submitted
Oral Presentation
AO19-002
 
 
https://storage.unitedwebnetwork.com/files/1285/1212584-46903-APSR2026-186 YiChen_432590.pptx
Format: PPTX Only
 
Format: PDF Only
08. Lung Cancer
4

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.

Yi Chen * The First Affiliated Hospital of Chongqing Medical University Department of Respiratory and Critical Care Medicine Chongqing China
Xuan Li - The First Affiliated Hospital of Chongqing Medical University Department of Clinical Nutrition Chongqing China
YiJia Cao - University-Town Hospital of Chongqing Medical University Department of General Surgery Chongqing China
Yuan Li - The First Affiliated Hospital of Chongqing Medical University Department of Radiology, Department of Cardiothoracic Surgery Chongqing China
 
 
 
 
 
 
 
 
 
 
 
Presenting Author Details
Yi
Chen
929246728@qq.com
 
31-40
China
Original Research
An AI-driven Model (RFM-LAPr) Integrating CT radiomics and TNM Staging for the Prognostic Evaluation of Lung Adenocarcinoma
Maximum 25 words
Abstract Content
Lung adenocarcinoma (LUAD) prognosis is primarily determined by the TNM staging system, yet substantial inter-individual heterogeneity results in variable outcomes among same-stage patients. Radiomics holds great promise for optimizing cancer prognostic prediction. This study aims to identify the risk of recurrence early in the perioperative period. An AI-driven model (RFM-LNM) was developed by integrating radiomics and TNM staging.
The study cohort comprised 215 patients from Center A (training set), with 111 patients from Centers B and C serving as an external test set and 59 cases from TCIA as a public test set.
RFM-LAPr exhibited superior performance across all cohorts (testing set AUC=0.804~0.829, C-index: 0.747~0.783).Calibration curves confirmed excellent consistency between predicted and actual survival. Kaplan-Meier analysis revealed distinct prognostic stratification (Log-rank p<0.0001, HR=5.231, 95%CI=3.724~7.348) with an optimal cut-off value of 0.276.SHAP analysis highlighted RadScore, T/N staging, and differentiation as key predictive features.
RFM-LAPr refines prognostic evaluation beyond TNM staging and is supported by a freely accessible clinical web tool (https://lapr.rfmodel.com/), demonstrating high clinical utility.
 
 
 
 
 
No
Yes
https://storage.unitedwebnetwork.com/files/1285/1212584-37089-1_371665.png
JPG or JPEG or PNG format ONLY
Digital technology,Artificial Intelligence,Lung cancer
maximum 3 keywords and no abbreviations, separated by commas
 
187