JMIR Publications

ABSTRACT

Background:

Alzheimer's disease and related dementias (ADRD) are complex disorders with overlapping symptoms and pathologies. Comprehensive records of symptoms in electronic health records (EHR) are critical not only for accurate diagnosis, but also for supporting ongoing research studies and clinical trials. However, these symptoms are frequently obscured within unstructured clinical notes in EHR, making manual extraction both time-consuming and labor-intensive.

Objective:

We aimed to automate symptom extraction from clinical notes of patients with ADRD using fine-tuned large language models (LLM).

Methods:

We fine-tuned LLMs to extract ADRD symptoms across seven domains: Memory, Executive Function, Motor, Language, Visuospatial, Neuropsychiatric, and Sleep. We assessed the algorithm’s performance by calculating the area under the receiver operating characteristic curve (AUROC) for each domain. The extracted symptoms were then validated in two analyses: (1) predicting ADRD diagnosis using the counts of extracted symptoms and (2) examining the association between ADRD symptoms and MRI-derived brain volumes.

Results:

Symptom extraction across the seven domains achieved high accuracy with AUROCs ranging from 0.97 to 0.99. Using the counts of extracted symptoms to predict ADRD diagnosis yielded an AUROC of 0.83, 95% CI [0.77, 0.89]. Symptom associations with brain volumes revealed that smaller hippocampal volume was linked to memory impairments (p = 0.006, odds ratio = 0.62, 95% CI = [0.46, 0.84]), and reduced pallidum size was associated with motor impairments (p = 0.036, odds ratio = 0.73, 95% CI = [0.58, 0.9]).

Conclusions:

These results highlight the accuracy and reliability of our high-throughput ADRD phenotyping algorithm. By enabling automated symptom extraction, our approach has the potential to assist with differential diagnosis, as well as facilitate clinical trials and research studies of dementia.