Integrating Natural Language Processing to Assess Effect of Loneliness and Social isolation on Cognitive Decline in Dementia: A Retrospective Cohort Analysis
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
The study aimed to compare cognitive trajectories between patients with reports of social isolation and loneliness and those without.
METHODS
Reports of social isolation, loneliness, and Montreal Cognitive Assessment (MoCA) scores were extracted from dementia patients’ medical records using Natural Language Processing models and analysed using mixed-effects models.
RESULTS
Lonely patients (n = 382) showed lower MoCA scores throughout the disease (B = - 0.83, t = −2.64, p = 0.008). Socially isolated patients (n = 523) experienced faster cognitive decline six months before diagnosis (B = −0.21, t = −2.18, p = 0.029), but were comparable to controls (n = 3912) before this period. This led to lower MoCA scores at diagnosis (B = −0.69, t = −2.53, p = 0.011) and in later stages.
DISCUSSION
Lower cognitive levels in lonely and socially isolated patients suggest that these factors may contribute to dementia progression.
