OBJECTIVES: Length of hospital stay (LOS) is a major cost component of hospital budgets. Accurate prediction of LOS has become increasingly important for health care systems, and reducing the LOS has the potential for large savings in the public hospital system. This study aimed to assess the factors associated with prolonged LOS of acute ischemic stroke taking into consideration demographic, risk factors, and clinical signs that can be assessed at the time of admission. Particular attention is paid on the impact of previous medication use on LOS. METHODS: A retrospective cohort study of all acute ischemic stroke survivors attending a hospital in Malaysia from May 1, 2008 to December 31, 2008. Long hospital stay was defined as a stay greater than or equal to the median of LOS. Data included demographic information, clinical information, risk factors, and previous medication use. SPSS version 15 was used for data analysis. RESULTS: Overall, 363 patients were studied. The median (interquartile range) of LOS was 69 (45-111) hours. The independent factors associated with prolonged LOS were a history of atrial fibrillation (P = 0.011), patients with moderate and severe Glasgow Coma Scale (P ˂ 0.001), patients with higher body temperature (P = 0.015), patients with higher fasting or random blood glucose (P = 0.004), and patients without previous use of angiotensin converting enzyme inhibitor medication (P = 0.027). CONCLUSIONS: This study provided scientific data for the factors that could hamper the discharge, particularly before clinicians can evaluate the most effective, efficient, and acceptable methods of managing patients with acute ischemic stroke. Moreover, these variables are potentially preventable or treatable at admission time and would be ideal targets to reduce the burden of illness and healthcare costs of ischemic stroke.