Stefano Cavalieri1, Luigi Mariani2, Vincent Vander Poorten3, Laure Van Breda3, Maria C Cau4, Salvatore Lo Vullo2, Salvatore Alfieri5, Carlo Resteghini5, Cristiana Bergamini5, Ester Orlandi6, Giuseppina Calareso7, Paul Clement8, Esther Hauben9, Francesca Platini5, Paolo Bossi5, Lisa Licitra10, Laura D Locati5. 1. Head and Neck Medical Oncology Department, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy. Electronic address: stefano.cavalieri@istitutotumori.mi.it. 2. Clinical Epidemiology and Trial Organization Unit, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy. 3. Otorhinolaryngology, Head and Neck Surgery, University Hospitals Leuven and Department of Oncology, Section Head and Neck Oncology, KU Leuven, Leuven, Belgium. 4. Medical Oncology Unit, Azienda Ospedaliera Brotzu, Cagliari, Italy. 5. Head and Neck Medical Oncology Department, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy. 6. Radiotherapy 1-2 Unit, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy. 7. Radiology Unit, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy. 8. Department of Oncology, KU Leuven, Leuven Cancer Institute, Leuven, Belgium. 9. Department of Pathology, KU Leuven, Leuven Cancer Institute, Leuven, Belgium. 10. Head and Neck Medical Oncology Department, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Italy; Department of Oncology and Hemato-Oncology, University of Milan, Italy.
Abstract
BACKGROUND: Distant metastases in adenoid cystic carcinoma (ACC) are common. There is no consensus on the management of metastatic disease because no therapeutic approach has demonstrated improvement in overall survival (OS) and because of prolonged life expectancy. The aim of this study is to build and validate a prognostic nomogram for metastatic ACC patients. METHODS: The study end-point was OS, measured from the date of first metastatic presentation to death/last follow-up. A retrospective analysis including metastatic ACC patients was performed to build the prognostic nomogram at the INT (Milan, Italy). The model was validated on an independent cohort of patients with similar characteristics treated at Leuven (Belgium). Outcome data and covariates were modelled by resorting to a random forest method. This machine-learning approach was used to guide and benchmark the subsequent use of more conventional modelling methods. Cox model performance was assessed in terms of discrimination (Harrell's c-index). RESULTS: Two hundred ninety-eight patients with metastatic ACC (testing set 259 INT, validation set 39 Leuven) were studied. Akaike Information Criterion-based backward selection yielded a 5-factor model showing a bias-corrected c-index of 0.730. Five independent prognostic factors were found: gender, disease-free interval and presence of lung, liver or bone metastases. Nomogram discrimination in the validation series was c = 0.701. CONCLUSION: This retrospective analysis allowed the building of an externally validated prognostic nomogram. This tool might help clinicians to discriminate patients requiring prompt management from who can benefit from a 'watchful waiting'. In addition, the nomogram might be useful to stratify patients in clinical trials.
BACKGROUND: Distant metastases in adenoid cystic carcinoma (ACC) are common. There is no consensus on the management of metastatic disease because no therapeutic approach has demonstrated improvement in overall survival (OS) and because of prolonged life expectancy. The aim of this study is to build and validate a prognostic nomogram for metastatic ACC patients. METHODS: The study end-point was OS, measured from the date of first metastatic presentation to death/last follow-up. A retrospective analysis including metastatic ACC patients was performed to build the prognostic nomogram at the INT (Milan, Italy). The model was validated on an independent cohort of patients with similar characteristics treated at Leuven (Belgium). Outcome data and covariates were modelled by resorting to a random forest method. This machine-learning approach was used to guide and benchmark the subsequent use of more conventional modelling methods. Cox model performance was assessed in terms of discrimination (Harrell's c-index). RESULTS: Two hundred ninety-eight patients with metastatic ACC (testing set 259 INT, validation set 39 Leuven) were studied. Akaike Information Criterion-based backward selection yielded a 5-factor model showing a bias-corrected c-index of 0.730. Five independent prognostic factors were found: gender, disease-free interval and presence of lung, liver or bone metastases. Nomogram discrimination in the validation series was c = 0.701. CONCLUSION: This retrospective analysis allowed the building of an externally validated prognostic nomogram. This tool might help clinicians to discriminate patients requiring prompt management from who can benefit from a 'watchful waiting'. In addition, the nomogram might be useful to stratify patients in clinical trials.