Loneliness, social isolation, and effects on cognitive decline in patients with dementia: A retrospective cohort study using natural language processing

Myers, James A. C.; Stafford, Tom; Koychev, Ivan; Perneczky, Robert ; Bandmann, Oliver und Vaci, Nemanja (2025): Loneliness, social isolation, and effects on cognitive decline in patients with dementia: A retrospective cohort study using natural language processing. In: Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, Bd. 17, Nr. 3, e70149

Abstract

INTRODUCTION

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 analyed using mixed-effects models.

RESULTS

Lonely patients (n = 382), compared to controls (n = 3912), showed an average MoCA score that was 0.83 points lower at diagnosis (P = 0.008) and throughout the disease. Socially isolated patients (n = 523) experienced a 0.21 MoCA point per year faster rate of cognitive decline in the 6 months before diagnosis (P = 0.029), but were comparable to controls before this period. This led to average MoCA scores that were 0.69 MoCA points lower at diagnosis (P = 0.011).

DISCUSSION

Lower cognitive levels in lonely and socially isolated patients suggest that these factors may contribute to dementia progression.

Highlights

- Developed Natural Language Processing model to detect social isolation and loneliness in electronic health records.

- Patients with loneliness reports have lower Montreal Cognitive Assessment (MoCA) scores than other patients.

- Social isolation was related to the faster decline in MoCA scores before diagnosis.

- Social isolation and loneliness are promising targets for slowing cognitive decline.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin > Munich Cluster for Systems Neurology (SyNergy)
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 2352-8729
• Sprache: Englisch
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - 390857198