JMIR Publications

ABSTRACT

Background:

Systemically identifying caregivers in the electronic health record (EHR) is a critical step for delivering patient-centered care, enhancing care coordination, and advancing research and population health efforts in caregiving. Despite EHRs being effective in identifying patients through standardized data fields like demographics, lab results, medications, and diagnoses, identifying caregivers through the EHR is challenging in the absence of specific caregiver fields.

Objective:

Recognizing the complexity of identifying caregiving networks of people living with dementia (PLWD), this study aimed to systematically capture caregiver information by combining EHR structured fields and unstructured notes and free text.

Methods:

Among a cohort of PLWD aged ≥60 from Kaiser Permanente Colorado (KPCO) caregiver names were identified by combining structured patient contact fields, i.e. known contacts, with name-matching and natural language processing (NLP) techniques of unstructured notes and patient portal messages containing caregiver terms.

Results:

Among the cohort of N=789 PLWD, 95% had at least one caregiver name listed in structured fields (mean=2.1). Over 95% of the cohort had caregiver terms mentioned near a known contact name in unstructured encounter notes, with 35% having a full name match in unstructured patient portal messages. The NLP model identified 7,556 “new” names in the unstructured EHR text containing caregiver terms among 99% of the cohort with high accuracy and reliability (F1=.85, precision=.89, recall=.82). 87% of the cohort had a new name identified ≥2 near a caregiver term in their notes and portal messages.

Conclusions:

Analysis revealed significant patterns in caregiver-related information distributed across structured and unstructured EHR fields, emphasizing the importance of integrating both data sources for a comprehensive understanding of caregiving networks. A framework was developed to systematically identify potential caregivers across caregiving networks using structured and unstructured EHR data. This approach has the potential to improve health services for PLWD and their caregivers.