Martinez-Zayas G, Almeida FA, Simoff MJ, Yarmus L, Molina S, Young B, Feller-Kopman D, Sagar AS, Gildea T, Debiane LG, Grosu HB, Casal RF, Arain MH, Eapen GA, Jimenez CA, Noor LZ, Baghaie S, Song J, Li L, and Ost DE. A Prediction Model to Help with Oncologic Mediastinal Evaluation for Radiation: HOMER. Am J Respir Crit Care Med 2019.
American journal of respiratory and critical care medicine
RATIONALE: When stereotactic ablative radiotherapy (SABR) is an option for non-small cell lung cancer (NSCLC) patients, distinguishing between N0, N1 and N2 or N3 (N2|3) disease is important.
OBJECTIVES: To develop a prediction model for estimating the probability of N0, N1, and N2|3 disease.
METHODS: Consecutive patients with clinical-radiographic stage T1-3/N0-3/M0 NSCLC that underwent endobronchial ultrasound-guided staging from a single center were included. Multivariate ordinal logistic regression analysis was used to predict the presence of N0, N1 or N2|3 disease. Temporal validation used consecutive patients from three years later at the same center. External validation used three other hospitals.
RESULTS: In the model development cohort (n=633), younger age, central location, adenocarcinoma and higher PET-CT nodal stage were associated with a higher probability of having advanced nodal disease. Area under the receiver operating characteristic curves (AUC) were 0.84 and 0.86 for predicting N1 or higher (vs. N0) disease and N2|3 (vs. N0|1) disease respectively. Model fit was acceptable (Hosmer-Lemeshow p=0.960; Brier score 0.36). In the temporal validation cohort (n=473) AUCs were 0.86 and 0.88. Model fit was acceptable (Hosmer-Lemeshow p=0.172; Brier score 0.30). In the external validation cohort (n=722), AUCs were 0.86 and 0.88, but required calibration (Hosmer-Lemeshow p
CONCLUSIONS: This prediction model can estimate the probability of N0, N1 and N2|3 disease in NSCLC patients. The model has the potential to facilitate decision-making in NSCLC patients when SABR is an option.
ePub ahead of print