JMIR Publications

ABSTRACT

Background:

Subjective cognitive decline (SCD) typically refers to self- or informant-reported decline in cognition despite the absence of objective impairment on standardized testing. Older adults with documented normal cognitive test performance provide a pragmatic anchor cohort for EHR-based SCD phenotyping. However, cognitive concerns are primarily recorded in unstructured notes and are inconsistently documented, making it unclear how often and in whom concerns are captured in routine care.

Objective:

To operationalize EHR-based SCD phenotyping in an objectively normal-testing cohort using a large language model(LLM)-based natural language processing approach and to examine the frequency and clinical and sociodemographic correlates of cognitive concern documentation.

Methods:

We conducted an EHR-based observational study of patients aged ≥65 years with a first normal cognitive test recorded in EHR flowsheets between January 2019 and April 2024 in a large health system. We developed and iteratively refined a two-stage LLM-based NLP pipeline to identify documented cognitive concerns in unstructured notes during the 12 months prior to the index date, and evaluated performance against manual review. We quantified the frequency of documented concerns within this normal-testing cohort and used multivariable logistic regression to assess associations with sociodemographic factors (age, marital status, insurance, neighborhood Area Deprivation Index [ADI]), sequentially adjusting for clinical comorbidities and relevant medications.

Results:

Among 15,750 older adults with normal cognitive test scores, 13.8% (n=2,175) had at least one documented cognitive concern in the prior year, captured in 1.2% of notes (7,394/605,177). On manual validation, the two-stage pipeline (Med42-v2-8B screening followed by GPT-4o confirmation) achieved sensitivity 95.7%, PPV 93.5%, specificity 98.5%, and F1-score 0.945 for cognitive concern identification. Documentation was more likely in older individuals, those with commercial (vs. Medicare) insurance, and those with neurological and psychiatric conditions. In fully adjusted models, Parkinson’s disease (adjusted odds ratio [aOR] 5.29, 95% CI 3.60-7.77), traumatic brain injury (aOR 4.63, 3.15-6.81), stroke or transient ischemic attack (aOR 3.46, 3.15-4.18), epilepsy (aOR 2.52, 1.83-3.49), depression (aOR 1.54, 1.36-1.75), and excessive alcohol use (aOR 1.48, 1.06-2.06) were among the strongest correlates of cognitive concern documentation. In contrast, obesity (aOR 0.73, 0.65-0.82), hyperlipidemia (aOR 0.59, 0.51-0.67), and residence in more deprived neighborhoods (higher ADI) were associated with lower odds of documented cognitive concerns.

Conclusions:

A two-stage LLM pipeline enabled accurate identification of documented cognitive concerns consistent with SCD among older adults with normal cognitive testing. Documentation was uncommon and selectively captured by clinical and sociodemographic factors, with implications for equity and the validity of EHR-based phenotypes.