Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster Display session

87P - Prognostic models of recurrence free survival in non-small cell lung cancer


31 Mar 2023


Poster Display session


Kieran Palmer


Journal of Thoracic Oncology (2023) 18 (4S): S89-S100.


K.R. Palmer1, A. Houston2, H. Macpherson3, W. Wang4, F. Quartly3, M. Grant3, K.R. Patel3, A. Ghose3, S. Williams2, L. Lim Farah3, J. Conibear3, K. Giaslakiotis3, K. Lau3, W. Ricketts3, A. Januszewski3

Author affiliations

  • 1 London/GB
  • 2 St Bartholomew's Hospital - Barts Health NHS Trust, London/GB
  • 3 St. Bartholomew's Hospital - Barts Health NHS Trust, London/GB
  • 4 Queen Mary University of London, London/GB


Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 87P


Accurate prediction of recurrence-free survival (RFS) in patients undergoing radical surgery for early-stage non-small cell lung cancer (NSCLC) is necessary to improve outcomes. We aimed to develop pre- and post-operative prognostic models based on a range of clinicopathological factors using machine learning.


Retrospective data was collected from patients treated with radical surgery from 2015 to 2021, and 66 clinicopathological features were extracted. Three regularised Cox models were trialled (Ridge, LASSO and Elastic Net) and features were selected using a ‘maximum relevancy-minimum redundancy’ approach. Model development and validation were performed using nested cross-validation. Performance was assessed using the Concordance Index (C-index), Cumulative Dynamic Area Under the Receiver Operating Characteristic Curve (AUROC) and Dynamic Brier Score.


392 patients were included; 145 (37%) patients developed recurrence or died from all causes, and median RFS was 74 months. The Elastic Net model – trained using systemic inflammatory response index [SIRI], eosinophil count, pre-operative nodal stage, weight loss, performance status and maximum standardized uptake value (SUVmax) – and the Ridge model – using performance status, weight loss, SIRI, eosinophil count, lymphovascular invasion, visceral pleural invasion, and pathological stage – proved optimal for pre- and post-operative prognosis, respectively (table).

Table: 87P

Prognostic performance of pre- and post-surgical models

ModelRegularisationN FeaturesC-IndexMean AUROCMean Brier Score
Pre-surgicalElastic Net60.70 ± 0.030.72 ± 0.020.18 ± 0.05
Post-surgicalRidge70.75 ± 0.040.79 ± 0.020.16 ± 0.04

Both models had better performance at predicting earlier recurrence or death with a pre-surgical and post-surgical 1-year AUROC of 0.73 ± 0.03 and 0.83 ± 0.08 respectively.


Our prognostic models demonstrate robust prediction of RFS in early-stage NSCLC, and may identify patients who will benefit from peri-operative anti-cancer therapy and/or closer post-operative surveillance. Future work is required to validate these models externally and prospectively.

Legal entity responsible for the study

The authors.


Has not received any funding.


All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.