Objective:

We sought to evaluate studies that applied natural language processing (NLP) to the diagnosis, prediction, or treatment of common neurological disorders.

Background:

NLP, a branch of artificial intelligence that analyzes unstructured language, is being increasingly utilized in medicine. However, the extent to which NLP has been studied in neurological disorders remains inconsistently characterized.

Design/Methods:

This review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards and was registered with the Prospective Register of Systematic Reviews (PROSPERO; CRD42021228703). The search was conducted using MEDLINE and EMBASE on May 11, 2022. We included studies of NLP use in migraine, Parkinson disease, Alzheimer dementia, stroke and transient ischemic attack (TIA), epilepsy, or multiple sclerosis. We excluded non-English language, conference abstract, and review articles, as well as studies involving heterogeneous clinical populations or indirect clinical uses of NLP. Study characteristics were extracted and analyzed using descriptive statistics.

Results:

We identified 916 studies, of which 41 (4.5%), published between 2013 and 2022, were included in the final review. The most studied disorders were stroke and TIA (N=20 studies, 48.8%), followed by epilepsy (N=10, 24.4%), Alzheimer disease (N=6, 14.6%), and multiple sclerosis (N=5, 12.2%). We found no studies of NLP use in migraine or Parkinson disease that met our eligibility criteria. The main objective of NLP was diagnosis (N=20, 48.8%) followed by disease phenotyping (N=17, 41.5%), prognostication (N=9, 22%) and treatment (N=4, 9.8%). Eighteen (43.9%) studies used only machine learning approaches, 6 (14.6%) used only rule-based methods, and 17 (41.5%) used both. 

Conclusions:

We found several gaps in neurological NLP research, with few to no studies in certain disorders, suggesting additional areas of inquiry. We observed that NLP was most widely studied in diagnostic applications, implying a potential role for NLP in augmenting diagnostic accuracy in settings with limited access to neurological expertise.