Background:  In spite of numerous studies published in the past few years on the topic, the effect of smoking on Alzheimer's disease and dementia remains uncertain. Case–control studies have largely suggested that smoking lowers the risk of AD, whereas prospective studies have shown that smoking increases this risk or has no effect on the probability of developing AD. Objectives: The aim of this study is to compare the prevalence of Smoking in elderly with cognitive impairment and elderly with non-cognitive impairment. Design: A Case control study. Participants: 88 participants aged 60 years and above. They were selected from Ain Shams University Hospital from inpatient wards and outpatient clinics. The studied sample was divided into 3 groups: Group A (32 elderly patients with Alzheimer's disease), Group B (32 elderly patients with Mild cognitive impairment) and Group C (24 controls with normal cognitive function). Measurements: Comprehensive geriatric assessment, including detailed history, physical examination, and also cognitive assessment using Montreal Cognitive Assessment (MOCA) and Mini mental status examination (MMSE). Results:As regards smoking there was a highly statistical significant difference between the 3 groups as non-smokers were more prevalent in Alzheimer's disease and Mild cognitive impairment groups in comparison to control group with (p-value= 0.001). Conclusion: There was a highly significant negative association between smoking and cognitive impairment.