METHODS: We examined the UNOS database and identified patients with oral and oropharyngeal malignancy who underwent LT between 1988 and 2016. Patients greater than 18 years of age were included. Kaplan-Meier survival analysis and log-rank tests were performed. RESULTS: In the UNOS database, survival data regarding 142,488 patients was available and the cause of death was identified in 14,533 LT recipients.83 patients had oral and oropharyngeal ma- lignancy. 23 patients had cancer of the tongue and floor of the mouth. Mean age 55 years (SD 6 8), mean BMI 26 (SD 6 4), males were 74%, white 83%. 49 patients had tonsillar and oropharyngeal cancer. Mean age 54 years (SD 6 7), mean BMI 25 (SD 6 4), males were 86%, white 80%. 11 patients had oral and palate cancer. Mean age 56 years (SD 6 6), mean BMI 26 (SD 6 5), males were 55%, white 100%. Compared to all LT indications, those who developed oral and oropharyngeal malig- nancy were more likely to have alcoholic liver disease (P , 0.001). The mean patient survival time in the study population ranged between 5 and 7.5 years. However, patient survival was significantly lower among patients who developed oral and oropharyngeal malignancy compared to other LT recipients (Log-rank test, P , 0.001) (Figure 1). CONCLUSION: Analysis of the UNOS database showed that oral and oropharyngeal malignancy is more common among male recipients with a history of alcoholic liver disease. Better outcomes should be expected if such patients were diagnosed earlier, prolonging their life expectancy. Having a history of heavy alcohol use should raise awareness among dentists, gastroenterologists and transplant physicians regarding the increased risk of oral cancers after LT. 984 Non-Invasive Predictors of Moderate-Large Esophageal Varices in Compensated Cirrhotic Patients Irsan Hasan, MD, PhD 1 , Andri S. Sulaiman, MD, PhD 1 , Chyntia O. Jasirwan, MD, PhD 1 , Imelda M. Loho, MD 2 , Steven Zulkifly, MD 1 , Jordan Sardjan, MD 1 , Anugrah D. Handayu 1 . 1 Universitas Indonesia, Dr. Cipto Mangunkusumo National General Hospital, Central Jakarta, Jakarta Raya, Indonesia; 2 Dharmais Hospital, Indonesian National Cancer Center, West Jakarta, Jakarta Raya, Indonesia. INTRODUCTION: Esophageal variceal hemorrhage (EVH) is a severe complication of liver cir- rhosis with a high mortality rate. Esophagogastroduodenoscopy (EGD) screening to detect esopha- geal varices (EV) is currently recommended for all newly diagnosed cirrhotic patients. However, many patients who undergo EGD do not have varices, especially in compensated cirrhotic patients. Furthermore, EGD is an expensive and invasive procedure. The aim of the study is to identify a non- invasive and low-cost scoring system that could predict the presence of moderate–large EV in compensated cirrhotic patients. METHODS: A cross-sectional study was conducted in newly diagnosed patients with non-Child- Pugh (CP) C liver cirrhosis, without a history of variceal bleeding. Demographic, clinical, bio- chemical, and ultrasonographic parameters will be recorded. Presence and degree of esophageal varices will be determined during EGD. In order to identify independent predictors for the presence of esophageal varices, univariate and multivariate logistic regression will be analyzed. RESULTS: EV was found in 47 from 80 patients (58.8%) that were enrolled in this study. Of 47 patients, moderate-large varices was detected in 20/34 (58.8%) and 12/13 (92.3%) patients with CP-A and CP-B class, respectively. In univariate analysis, low platelet count (#100 000/mL), increased bipolar spleen diameter ($135 mm), and platelet count/bipolar spleen diameter ratio # 847 were associated with the presence of moderate-large EV. Only platelet count/bipolar spleen diameter ratio was associated in multivariate analysis. The AUC, sensitivity and specificity of platelet count/bipolar spleen diameter ratio # 847 is 0.77, 90.6% and 58.3%, respectively. CONCLUSION: Low platelet count is commonly found in liver cirrhotic patients and easily obtained in resource-limited setting. The enlarged spleen is often observed in patients with liver cirrhosis and associated with a higher risk of complications. The ratio of low platelet count/spleen bipolar diameter has been used to predict the presence of EV in cirrhotic patients, however, the previous studies included the patients with compensated and decompensated cirrhosis. For the implementation in daily clinical practice with resource-limited setting, a patient with compensated liver cirrhosis and platelet count/bipolar spleen diameter ratio # 847 is highly recommended to undergo EGD screening procedure. 985 Racial Difference in the Clinical Features of Non-Alcoholic Fatty Liver Disease He Qiu, MD, MBA 1 , Michelle Shi, MD 1 , May Kyaw, BS 1 , Gwyneth Sultan 1 , Tai-Ping Lee, MD 2 . 1 Hofstra / Northwell School of Medicine, Manhasset, NY; 2 Hofstra / Northwell School of Medicine, Sandra Atlas Bass Center for Liver Diseases, Manhasset, NY. [985] Table 1. Demographics and Clinical Data of Patient with NAFLD in Difference Race [983] The American Journal of GASTROENTEROLOGY VOLUME 00 | SUPPLEMENT | MONTH 2019 www.amjgastro.com Abstracts S572 Copyright © 2019 by The American College of Gastroenterology. Unauthorized reproduction of this article is prohibited.