ESTRO 2022 - Abstract Book

S327

Abstract book

ESTRO 2022

rates, patients treated between 2014-2017 had improved overall survival compared with patients treated between 2010- 2013.

Conclusion There was no discernible high-risk period for early mortality and neither the CCI nor TNM stage was associated with an increased risk. To optimize risk stratification, other tools than the CCI should be used to quantify comorbidity in this setting.

MO-0391 Predicting early mortality using muscle characteristics for patients with lung cancer

A. McWilliam 1 , D. McSweeney 2 , K. Banfill 1 , M. van Herk 1 , C. Faivre-Finn 3 , A. Green 1

1 University of Manchester, Division of Cancer Science, Manchester, United Kingdom; 2 University of Manchester, Division of Cancer Science, Mancheter, United Kingdom; 3 Univesity of Manchester, Division of Cancer Science, Manchester, United Kingdom Purpose or Objective There is a need for quantitative biomarkers to guide treatment decisions in patients with lung cancer treated with radiotherapy. Decisions on treatment intent consider variables, such as age, stage and performance status, but predicting early mortality is challenging. 90-day mortality is used in surgical decision making, but no models have been developed for radiotherapy. In this work, we investigated muscle characteristics as an image-based biomarker to predict early mortality. Materials and Methods 586 patients with NSCLC lung cancer treated with 55Gy in 20 fractions were identified from a retrospective database. The muscle compartment at T12 was segmented on planning CT using an in-house AI model. Muscle area and density were