Objective:

To investigate changes in motor cortical oscillatory activity using fractal dimension (FD) in HALO and 6-OHDA rat models of Parkinson's Disease (PD) and to test a support vector machine (SVM) model for predicting neuronal dynamics specifically in the chronic 6-OHDA model.

Key Findings:

• Average FD values in the motor cortex were significantly higher in both PD models compared to controls (P < 0.001), indicating altered cortical dynamics.
• Apomorphine injection and STN DBS significantly reduced average FD values in both models, suggesting a potential therapeutic effect.
• The SVM model achieved 80% classification accuracy and an AUC of 0.86 in the 6-OHDA rat model, demonstrating its predictive capability.

Interpretation:

The non-linear analysis of FD indicates significant changes in cortical oscillatory patterns in rodent models of PD, suggesting potential for adaptive DBS strategies that could be informed by these findings.

Limitations:

• The study is limited to rodent models, which may not fully replicate human PD conditions, potentially affecting the translatability of results.
• Further validation of SVM predictions in clinical settings is necessary to establish its applicability.

Conclusion:

Fractal dimension analysis reveals altered cortical oscillatory patterns in PD models, and SVM-based predictions may enhance strategies for adaptive DBS.