Cognitive Function Characterization Using Electronic Health Records Notes

Abstract

Cognitive impairment is a defining feature of neurological disorders such as Alzheimer's disease (AD), one of the leading causes of disability and mortality in the elderly population. Assessing cognitive impairment is important for diagnostic, clinical management, and research purposes. The Folstein Mini-Mental State Examination (MMSE) is the most common screening measure of cognitive function, yet this score is not consistently available in the electronic health records. We conducted a pilot study to extract frequently used concepts characterizing cognitive function from the clinical notes of AD patients in an Aging and Dementia clinical practice. Then we developed a model to infer the severity of cognitive impairment and created a subspecialized taxonomy for concepts associated with MMSE scores. We evaluated the taxonomy and the severity prediction model and presented example use cases of this model.