Relationships between motor and cognitive functions and subsequent post-stroke mood disorders revealed by machine...

Area of Science:

• Neuroscience
• Psychiatry
• Rehabilitation Medicine

Background:

• Mood disorders, including depression and anxiety, are prevalent in stroke survivors.
• These mood disturbances negatively affect functional recovery and cognitive performance post-stroke.
• Understanding the relationship between mood and function is crucial for effective rehabilitation.

Purpose of the Study:

• To investigate the cross-sectional associations between mood disorders and motor/cognitive functions in stroke patients.
• To identify specific clinical and functional indices related to mood disorders after stroke.
• To explore the underlying mechanisms contributing to mood disorders post-stroke.

Main Methods:

• An artificial neural network model was developed to predict three types of mood disorders.
• The model utilized 36 evaluation indices from functional, physical, and cognitive tests in 274 stroke patients.
• Input dimensionality reduction techniques were applied to analyze the relationship between mood and function.

Main Results:

• The artificial neural network achieved a moderate to high predictive accuracy (Area Under the Curve > 0.85).
• Input dimensionality reduction identified key evaluation indices strongly associated with mood disorders.
• The findings suggest a stress threshold hypothesis linking stroke-induced lesions to mood disorder vulnerability.

Conclusions:

• Mood disorders in stroke patients are significantly associated with specific motor and cognitive deficits.
• Artificial neural networks can effectively predict mood disorders based on functional and cognitive assessments.
• Stroke-induced stress vulnerability may play a critical role in the development of mood disorders post-stroke.