The aging population has led to an increase in cognitive impairment resulting in significant costs to patients, their families, and society. A research endeavor on a large cohort to better understand the frequency and severity of cognitive impairment is urgent to respond to the health needs of this population. However, little is known about temporal trends of patient health functions (i.e., activity of daily living) and how these trends are associated with the onset of cognitive impairment in older adults. Moreover, the use of rich source of clinical narratives in electronic health records to facilitate cognitive impairment research (i.e., topic analysis) has not been well explored. A study indicated that clinicians often delay a diagnosis of cognitive impairment and miss appropriate treatment of underlying diseases and comorbid conditions which may cause safety issues for the patient and others. This study is to characterize and better understand early signals of older adult cognitive impairment by examining temporal trends of patient activity of daily living and analyzing topics of patient medical conditions described in clinical narratives using semantic topic models.