BMC Cancer (Sep 2023)

Online decision tools for personalized survival prediction and treatment optimization in elderly patients with lung squamous cell carcinoma: a retrospective cohort study

  • Chen-ye Shao,
  • Jing Luo,
  • Sheng Ju,
  • Chu-ling Li,
  • Cheng Ding,
  • Jun Chen,
  • Xiao-long Liu,
  • Jun Zhao,
  • Li-qin Yang

DOI
https://doi.org/10.1186/s12885-023-11309-z
Journal volume & issue
Vol. 23, no. 1
pp. 1 – 10

Abstract

Read online

Abstract Background Despite major advances in cancer therapeutics, the therapeutic options of Lung Squamous Cell Carcinoma (LSCC)-specific remain limited. Furthermore, the current staging system is imperfect for defining a prognosis and guiding treatment due to its simplicity and heterogeneity. We sought to develop prognostic decision tools for individualized survival prediction and treatment optimization in elderly patients with LSCC. Methods Clinical data of 4564 patients (stageIB-IIIB) diagnosed from 2010 to 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database for prognostic nomograms development. The proposed models were externally validated using a separate group consisting of 1299 patients (stage IB-IIIB) diagnosed from 2012–2015 in China. The prognostic performance was measured using the concordance index (C-index), calibration curves, the average time-dependent area under the receiver operator characteristic curves (AUC), and decision curve analysis. Results Eleven candidate prognostic variables were identified by the univariable and multivariable Cox regression analysis. The calibration curves showed satisfactory agreement between the actual and nomogram-estimated Lung Cancer-Specific Survival (LCSS) rates. By calculating the c-indices and average AUC, our nomograms presented a higher prognostic accuracy than the current staging system. Clinical usefulness was revealed by the decision curve analysis. User-friendly online decision tools integrating proposed nomograms were created to estimate survival for patients with different treatment regimens. Conclusions The decision tools for individualized survival prediction and treatment optimization might facilitate clinicians with decision-making, medical teaching, and experimental design. Online tools are expected to be integrated into clinical practice by using the freely available website ( https://loyal-brand-611803.framer.app/ ).

Keywords