Natural Language Processing to Detect Cognitive Concerns in Electronic Health Records Using Deep Learning
This addresses the issue of under-recognition and under-diagnosis of cognitive concerns in healthcare, potentially aiding in earlier patient referrals, though it is incremental as it builds on existing NLP methods for medical text.
The study tackled the problem of under-detection of dementia by applying natural language processing to unstructured clinician notes in electronic health records, finding that an attention-based deep learning model outperformed a baseline model using only structured data.
Dementia is under-recognized in the community, under-diagnosed by healthcare professionals, and under-coded in claims data. Information on cognitive dysfunction, however, is often found in unstructured clinician notes within medical records but manual review by experts is time consuming and often prone to errors. Automated mining of these notes presents a potential opportunity to label patients with cognitive concerns who could benefit from an evaluation or be referred to specialist care. In order to identify patients with cognitive concerns in electronic medical records, we applied natural language processing (NLP) algorithms and compared model performance to a baseline model that used structured diagnosis codes and medication data only. An attention-based deep learning model outperformed the baseline model and other simpler models.