Lotte Nygård1, Ivan R Vogelius2, Barbara M Fischer3, Andreas Kjær3, Seppo W Langer2, Marianne C Aznar2, Gitte F Persson2, Søren M Bentzen4. 1. Department of Oncology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark. Electronic address: lotte.nygaard@regionh.dk. 2. Department of Oncology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark. 3. Department of Clinical Physiology, Nuclear Medicine and PET and Cluster for Molecular Imaging, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark. 4. Division of Biostatistics and Bioinformatics, University of Maryland Greenebaum Cancer Center, Baltimore, Maryland; Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, Maryland.
Abstract
INTRODUCTION: The aim of the study was to build a model of first failure site- and lesion-specific failure probability after definitive chemoradiotherapy for inoperable NSCLC. METHODS: We retrospectively analyzed 251 patients receiving definitive chemoradiotherapy for NSCLC at a single institution between 2009 and 2015. All patients were scanned by fludeoxyglucose positron emission tomography/computed tomography for radiotherapy planning. Clinical patient data and fludeoxyglucose positron emission tomography standardized uptake values from primary tumor and nodal lesions were analyzed by using multivariate cause-specific Cox regression. In patients experiencing locoregional failure, multivariable logistic regression was applied to assess risk of each lesion being the first site of failure. The two models were used in combination to predict probability of lesion failure accounting for competing events. RESULTS: Adenocarcinoma had a lower hazard ratio (HR) of locoregional failure than squamous cell carcinoma (HR = 0.45, 95% confidence interval [CI]: 0.26-0.76, p = 0.003). Distant failures were more common in the adenocarcinoma group (HR = 2.21, 95% CI: 1.41-3.48, p < 0.001). Multivariable logistic regression of individual lesions at the time of first failure showed that primary tumors were more likely to fail than lymph nodes (OR = 12.8, 95% CI: 5.10-32.17, p < 0.001). Increasing peak standardized uptake value was significantly associated with lesion failure (OR = 1.26 per unit increase, 95% CI: 1.12-1.40, p < 0.001). The electronic model is available at http://bit.ly/LungModelFDG. CONCLUSIONS: We developed a failure site-specific competing risk model based on patient- and lesion-level characteristics. Failure patterns differed between adenocarcinoma and squamous cell carcinoma, illustrating the limitation of aggregating them into NSCLC. Failure site-specific models add complementary information to conventional prognostic models.
INTRODUCTION: The aim of the study was to build a model of first failure site- and lesion-specific failure probability after definitive chemoradiotherapy for inoperable NSCLC. METHODS: We retrospectively analyzed 251 patients receiving definitive chemoradiotherapy for NSCLC at a single institution between 2009 and 2015. All patients were scanned by fludeoxyglucose positron emission tomography/computed tomography for radiotherapy planning. Clinical patient data and fludeoxyglucose positron emission tomography standardized uptake values from primary tumor and nodal lesions were analyzed by using multivariate cause-specific Cox regression. In patients experiencing locoregional failure, multivariable logistic regression was applied to assess risk of each lesion being the first site of failure. The two models were used in combination to predict probability of lesion failure accounting for competing events. RESULTS:Adenocarcinoma had a lower hazard ratio (HR) of locoregional failure than squamous cell carcinoma (HR = 0.45, 95% confidence interval [CI]: 0.26-0.76, p = 0.003). Distant failures were more common in the adenocarcinoma group (HR = 2.21, 95% CI: 1.41-3.48, p < 0.001). Multivariable logistic regression of individual lesions at the time of first failure showed that primary tumors were more likely to fail than lymph nodes (OR = 12.8, 95% CI: 5.10-32.17, p < 0.001). Increasing peak standardized uptake value was significantly associated with lesion failure (OR = 1.26 per unit increase, 95% CI: 1.12-1.40, p < 0.001). The electronic model is available at http://bit.ly/LungModelFDG. CONCLUSIONS: We developed a failure site-specific competing risk model based on patient- and lesion-level characteristics. Failure patterns differed between adenocarcinoma and squamous cell carcinoma, illustrating the limitation of aggregating them into NSCLC. Failure site-specific models add complementary information to conventional prognostic models.
Authors: Tine N Christensen; Seppo W Langer; Gitte Persson; Klaus Richter Larsen; Annemarie G Amtoft; Sune H Keller; Andreas Kjaer; Barbara Malene Fischer Journal: Diagnostics (Basel) Date: 2021-02-11