LEVERAGING NATURAL LANGUAGE PROCESSING TO IDENTIFY CAREGIVER AVAILABILITY FOR PATIENTS WITH ALZHEIMER'S DISEASE

Abstract

Abstract Identifying caregiver availability for patients with Alzheimer’s disease and related dementia (ADRD) can inform healthcare systems and hospital administrations on appropriate discharge planning. However, caregiver availability data is not systematically collected in the healthcare system. Our objective was to use medical notes (from physicians, nurses, or social workers) to assess caregiver availability and types of caregivers for hospitalized patients with ADRD. We used 2016-2019 telephone-encounter notes from a single institution. Rule-based natural language processing (NLP) was used to develop an algorithm to identify whether the patient (1) resides at home; (2) resides at an institution; (3) has a formal caregiver; and (4) has an informal caregiver. We evaluated the data at the note level and used chart abstraction as the “gold standard.” We examined the validity of the algorithm for both training (n=749) and test sets (n=227). Our results indicated a high level of accuracy and reliability for identifying an informal caregiver (F1=0.942; accuracy=0.947, sensitivity=0.970, and specificity=0.928). Identifying whether the patient lived at an institution was the least reliable measure (F1=0.638, accuracy=0.899, sensitivity=0.512, specificity=0.978). The most common causes of misclassifications were: (1) incomplete or misspelled names of the facilities; (2) past/uncertain/undecided situations; (3) lack of specificity; (4) use of uncommon abbreviations; and (5) irregular use of templates. Our NLP algorithm was able to identify whether the patient lived at home vs. an institution and whether the patient had a formal or informal caregiver. There is merit in continuing the NLP approach to identify more granular, caregiver-related information (e.g., hours available).