Validation of survival prognostic models for non-small-cell lung cancer in stage- and age-specific groups

Published prognostic models for small-cell lung cancer (SCLC) have either combined limited- and extensive-stage patients or have not included standard anatomic staging information to assess the relative value of the knowledge of specific sites and number of sites of metastases in predicting survival in extensive-stage disease. We studied 136 extensive-stage patients in whom traditional staging procedures were performed and in whom other previously demonstrated significant pretreatment variables were determined. Using the Cox proportional hazards model, when all data were included, three variables were significant: performance status (PS) (P = .0001), number of sites of metastases (P = .0010), and age (P = .0029). A prognostic algorithm was developed using these variables, which divided the patients into three distinct groups. When the anatomic staging data were omitted, the serum albumin (P = .0313) was the only variable in addition to PS (P = .0001) and age (P = .0064) that was significant. An alternative algorithm using these three variables was nearly as predictive as the original. Therefore, in extensive-stage patients, reasonable pretreatment prognostic information can be obtained without using the number or specific sites of metastases as variables once the presence of distant metastases has been demonstrated.

Download Full-text

Prognostic models to predict survival in patients with advanced non-small cell lung cancer treated with first-line chemo- or targeted therapy

Oncotarget ◽

10.18632/oncotarget.8309 ◽

2016 ◽

Vol 7 (18) ◽

pp. 26916-26924 ◽

Cited By ~ 21

Author(s):

Rossana Berardi ◽

Silvia Rinaldi ◽

Matteo Santoni ◽

Thomas Newsom-Davis ◽

Michela Tiberi ◽

...

Keyword(s):

Lung Cancer ◽

Targeted Therapy ◽

Small Cell Lung Cancer ◽

Cell Lung Cancer ◽

Small Cell ◽

Prognostic Models ◽

Small Cell Lung ◽

First Line

Download Full-text

Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform

European Radiology ◽

10.1007/s00330-020-06957-9 ◽

2020 ◽

Vol 30 (11) ◽

pp. 6241-6250 ◽

Cited By ~ 5

Author(s):

Isabella Fornacon-Wood ◽

Hitesh Mistry ◽

Christoph J. Ackermann ◽

Fiona Blackhall ◽

Andrew McPartlin ◽

...

Keyword(s):

Lung Cancer ◽

Small Cell Lung Cancer ◽

Cell Lung Cancer ◽

Prognostic Value ◽

Cox Regression ◽

Intraclass Correlation ◽

Small Cell ◽

Prognostic Models ◽

Small Cell Lung ◽

Statistical Reliability

Abstract Objective To investigate the effects of Image Biomarker Standardisation Initiative (IBSI) compliance, harmonisation of calculation settings and platform version on the statistical reliability of radiomic features and their corresponding ability to predict clinical outcome. Methods The statistical reliability of radiomic features was assessed retrospectively in three clinical datasets (patient numbers: 108 head and neck cancer, 37 small-cell lung cancer, 47 non-small-cell lung cancer). Features were calculated using four platforms (PyRadiomics, LIFEx, CERR and IBEX). PyRadiomics, LIFEx and CERR are IBSI-compliant, whereas IBEX is not. The effects of IBSI compliance, user-defined calculation settings and platform version were assessed by calculating intraclass correlation coefficients and confidence intervals. The influence of platform choice on the relationship between radiomic biomarkers and survival was evaluated using univariable cox regression in the largest dataset. Results The reliability of radiomic features calculated by the different software platforms was only excellent (ICC > 0.9) for 4/17 radiomic features when comparing all four platforms. Reliability improved to ICC > 0.9 for 15/17 radiomic features when analysis was restricted to the three IBSI-compliant platforms. Failure to harmonise calculation settings resulted in poor reliability, even across the IBSI-compliant platforms. Software platform version also had a marked effect on feature reliability in CERR and LIFEx. Features identified as having significant relationship to survival varied between platforms, as did the direction of hazard ratios. Conclusion IBSI compliance, user-defined calculation settings and choice of platform version all influence the statistical reliability and corresponding performance of prognostic models in radiomics. Key Points • Reliability of radiomic features varies between feature calculation platforms and with choice of software version. • Image Biomarker Standardisation Initiative (IBSI) compliance improves reliability of radiomic features across platforms, but only when calculation settings are harmonised. • IBSI compliance, user-defined calculation settings and choice of platform version collectively affect the prognostic value of features.

Download Full-text