Prognostic factors in patients receiving surgery and radiation therapy for retroperitoneal sarcoma: A machine-learning analysis

Abstract

BackgroundThe addition of radiation therapy to surgery for retroperitoneal sarcoma remains controversial. Improved patient selection may help identify optimal candidates for multimodality treatment. The aim of this analysis was to define prognostic factors among patients who receive radiation therapy and surgery to aid in patient selection for multimodal therapy. MethodsPatients who received radiation therapy and underwent curative-intent resection for retroperitoneal sarcoma between 2004 and 2016 were identified from a national cohort in the United States (National Cancer Database). A machine-based classification and regression tree model was used to generate similar groups of patients relative to overall survival based on preoperative factors. ResultsA total of 1,443 patients received radiation therapy in addition to surgery. Median age was 61 years old and 55.0% were female. Most patients (66%) received care at an academic or integrated network cancer program. With a median follow-up of 84 months, receipt of radiation therapy was not associated with improved overall survival (P = .81). Classification and regression tree analysis revealed a significant association between overall survival and American Joint Committee on Cancer stage group, age, tumor histology, and Charlson comorbidity score. Application of these parameters via machine learning stratified patients into 5 cohorts with distinct survival outcomes. In the most favorable cohort (Cohort 1: American Joint Committee on Cancer stage group ≤II, age ≤61, histology including fibrosarcoma, well differentiated liposarcoma, myxoid liposarcoma, and leiomyosarcoma), the 5-year overall survival was 81.7% and median overall survival was not reached; in the least favorable cohort (Cohort 6: American Joint Committee on Cancer stage group >II, age >68) where the 5-year survival was 41.3% and median overall survival was 45.2 months (P < .001 versus Cohort 1). ConclusionIn the absence of a defined survival benefit, patients with advanced American Joint Committee on Cancer stage group, older age, and medical comorbidities have relatively unfavorable overall survival after combined modality therapy and therefore stand the least to gain from the addition of radiation therapy to surgery. In contrast, younger patients with good performance status and retroperitoneal sarcoma histologies with a higher propensity for local recurrence may have the greatest opportunity to benefit from radiation therapy.