Background: Advanced cancer patients complain of highly distressing symptom at the end-of-life, and important reasons for palliative intervention to relive symptoms. Methods: We analyzed 1282 patients who died of advanced cancer from August 2011 to August 2019 retrospectively. We divided into patients who complain of symptom include fatigue, dyspnea, nausea and vomiting, and cancer pain, or didn’t for 3 days prior to death, and analyzed predictors by multiple logistics method. The primary endpoint of this study was to identify frequency and predictors of end-of-life symptoms in advanced cancer patients. Results: As a background, the median age is 73 years old, 690 males, 592 females, 227 gastroesophageal cancers, 250 biliary pancreatic cancers, 54 hepatocellular carcinomas, 189 colorectal cancer, 251 lung cancers, 71 breast cancers, 58 urological malignancies, 60 gynecological malignancies, 47 head and neck cancer, 31 hematological malignancies, and 22 sarcomas. Number of patients who complained of dyspnea, fatigue, nausea and vomiting, and cancer pain were 235 (18.3%), 318 (24.8%), 81 (6.3%), and 322 (25.1%) at the end-of-life. In a multivariate analysis, peritoneal metastasis (ORs 1.812), with mental (ORs 0.549), palliative referral (ORs 0.680), Eastern Cancer Organization Group Performance Status (ECOG-PS) (OR0.679) and consciousness level (ORs 0.610) was independent predictors in patients with fatigue at the end-of-life. Chest cancer (Odds Ratio 2.635), lung (ORs 2.159), brain (ORs 0.431) and peritoneal metastasis (ORs 0.602), with mental (ORs 0.429), respiratory (ORs 1.960) and metabolic disorder (ORs 0.520), palliative referral (ORs 0.645) and consciousness level (ORs 0.468) was independent predictors in patients with dyspnea. Lung metastasis (ORs 0.480, peritoneal metastasis (ORs 1.812), with anti-cancer therapy (OR 2.244) and consciousness level (ORs 0.610) was independent predictors in patients with nausea and vomiting. Brain metastasis (ORs 0.435, liver metastasis (ORs 1.374), and consciousness level (ORs 0.599) was independent predictors in patients with cancer pain. Conclusions: We reported frequency and independent predictors of end-of-life symptoms in advanced cancer patients. Information on these predictors be useful to explaining about their end-of-life in advance.