Seventy-nine stroke patients who underwent a vocationally oriented, comprehensive, inpatient stroke rehabilitation program were followed up to evaluate their return to work. At follow-up, 49% had returned to work a mean of 3.1 months after rehabilitation discharge. Factors associated with success and with failure of vocational rehabilitation were then identified, and a predictive model was developed. There were positive associations between return to work and Barthel Index on admission (p = 0.0002) and discharge (p = 0.0015). Negative associations were found between return to work and aphasia (p = 0.0009), rehabilitation length of stay (p less than 0.0001), and prior alcohol consumption (p = 0.03). A step-wise multiple regression model explained 42% of the variance in return to work. Those most likely to return to work were not aphasic; they had shorter rehabilitation lengths of stay and higher Barthel Index scores on discharge; and they were lighter consumers of alcoholic beverages before their strokes. In conclusion, a set of factors predictive of return to work in younger stroke patients was identified, including, most notably, a strong negative association with aphasia and an intriguing negative association with prior alcohol consumption.