Publication date: Jul 03, 2025
Parkinson’s disease (PD), a progressive neurodegenerative disorder, affects millions globally, with cognitive impairment as a significant non-motor complication. These cognitive changes, ranging from mild cognitive impairment (MCI) to severe dementia, drastically reduce quality of life and worsen prognosis. Early and accurate detection is critical for effective management and therapeutic interventions. Recent advancements in artificial intelligence (AI) offer novel solutions for diagnosing, predicting, and managing cognitive deficits in PD by integrating diverse data modalities, including neuroimaging, electrophysiology, kinetic markers, and laboratory biomarkers. Prominent AI techniques, such as support vector machines, random forests, and convolutional neural networks have demonstrated high accuracy in analyzing multimodal data for cognitive profile prediction. Additionally, AI supports the development of personalized treatment strategies, both pharmacological and non-pharmacological, and enhances accessibility through telemedicine initiatives. Despite these advancements, challenges persist in standardizing methodologies, improving model interpretability, and integrating AI tools into clinical practice. Overcoming these hurdles will require robust validation studies and multidisciplinary collaboration. This review examines the transformative role of AI in analyzing multimodal datasets to classify cognitive impairments, predict disease progression, and identify therapeutic targets, paving the way for personalized, patient-centered care in PD management.
Semantics
| Type | Source | Name |
|---|---|---|
| disease | MESH | Cognitive Impairment |
| disease | MESH | Parkinson’s Disease |
| disease | MESH | neurodegenerative disorder |
| disease | MESH | dementia |
| disease | MESH | disease progression |