To determine the factors that are related to short-term survival and to develop a model that can be used to estimate prognosis in terminal lung cancer patients. Longitudinal cohort study of hospice lung cancer patients followed from date of admission to hospice until death. Community-based nonprofit home hospice service. Three hundred ten consecutive lung cancer patients admitted to hospice, with a separate validation sample of 78 consecutive hospice lung cancer patients. The relationships between survival and admission demographic characteristics, information from the history and physical examination, assessments of performance and nutrition, particular symptoms, and the presence of a living will were evaluated. Mean survival was 51 days, with a median survival of 27 days. Shorter survival was independently associated with those who had no living will on admission to hospice (p = 0.008), those who had tissue types other than squamous cell or adenocarcinoma (p = 0.008), those who had liver metastases (p = 0.04), those who were tachycardic (p < 0.001), those who required assistance or were dependent in their toileting (p < 0.001) and feeding (p = 0.001), those who had dry mouths (p = 0.01), and those who had severe or incapacitating pain (p < 0.05). A model estimating survival time based on the number of these significant variables present is reported (r = 0.53 in the original sample; r = 0.38 in the validation sample). Multiple factors, including tissue type, the presence of metastases, assessments of functional status, specific symptoms, and the presence of a living will, were related to short-term survival in terminal lung cancer patients admitted to hospice. A model utilizing these specific factors allows useful estimates of short-term survival for these patients.