Background: Social support plays a crucial role for patients with aggressive hematologic malignancies as they navigate their illness course. We examined associations of social support with overall survival and health care utilization in this population. Methods: We conducted a cross sectional secondary analysis using data from a prospective longitudinal cohort study of 251 hospitalized patients with aggressive hematologic malignancies at Massachusetts General Hospital from 2014 through 2017. We utilized Natural Language Processing (NLP) to identify extent of patients’ social support (limited versus adequate as defined by NLP-aided chart review of the Electronic Health Record (EHR)). We used multivariable regression models to examine associations of social support with: 1) overall survival; 2) death or readmission within 90 days of discharge from index hospitalization; 3) time to readmission within 90 days; and 4) index hospitalization length of stay. Results: Patients had a median age of 64 (range: 19-93) years, and most were white (89.6%), male (68.9%), and married (65.3%). A plurality of patients had leukemia (42.2%) followed by lymphoma (37.9%) and myelodysplastic syndrome/myeloproliferative neoplasm (19.9%). Using NLP, we identified that 8.8% (22/251) of patients had limited social support. In multivariable analyses, limited social support was associated with worse overall survival (HR = 2.00, p = 0.042) and higher likelihood of death or readmission within 90 days of discharge (OR = 3.11, P = 0.043), but not with time to readmission within 90 days, or index hospital length of stay. Conclusions: In this cohort of hospitalized patients with aggressive hematologic malignancies, we found associations of limited social support with lower overall survival and higher likelihood of death or readmission within 90 days of hospital discharge. These findings underscore the utility of NLP for evaluating extent of social support and the need for larger studies evaluating social support in patients with aggressive hematologic malignancies.