Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2023 (2) (remove)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- DBS biomarkers (1)
- DBS programming (1)
- Parkinson's disease (1)
- beta power (1)
- computer vision (1)
- deep brain stimulation (1)
- digital medicine (1)
- eye movement disorders (1)
- local field potentials (1)
- nystagmus (1)
Highlights
• Beta-Guided programming is an innovative approach that may streamline the programming process for PD patients with STN DBS.
• While preliminary findings from our study suggest that Beta Titration may potentially mitigate STN overstimulation and enhance symptom control,
• Our results demonstrate that beta-guided programming significantly reduces programming time, suggesting it could be efficiently integrated into routine clinical practice using a commercially available patient programmer.
Background
Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective treatment for advanced Parkinson's disease (PD). Clinical outcomes after DBS can be limited by poor programming, which remains a clinically driven, lengthy and iterative process. Electrophysiological recordings in PD patients undergoing STN-DBS have shown an association between STN spectral power in the beta frequency band (beta power) and the severity of clinical symptoms. New commercially-available DBS devices now enable the recording of STN beta oscillations in chronically-implanted PD patients, thereby allowing investigation into the use of beta power as a biomarker for DBS programming.
Objective
To determine the potential advantages of beta-guided DBS programming over clinically and image-guided programming in terms of clinical efficacy and programming time.
Methods
We conducted a randomized, blinded, three-arm, crossover clinical trial in eight Parkinson's patients with STN-DBS who were evaluated three months after DBS surgery. We compared clinical efficacy and time required for each DBS programming paradigm, as well as DBS parameters and total energy delivered between the three strategies (beta-, clinically- and image-guided).
Results
All three programming methods showed similar clinical efficacy, but the time needed for programming was significantly shorter for beta- and image-guided programming compared to clinically-guided programming (p < 0.001).
Conclusion
Beta-guided programming may be a useful and more efficient approach to DBS programming in Parkinson's patients with STN-DBS. It takes significantly less time to program than traditional clinically-based programming, while providing similar symptom control. In addition, it is readily available within the clinical DBS programmer, making it a valuable tool for improving current clinical practice.
Background
Eye movement abnormalities are commonplace in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness precludes its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances.
Methods
A convolutional neural network was fine-tuned for pupil tracking using > 550 annotated frames: ConVNG. In a cross-sectional approach, slow-phase velocity of optokinetic nystagmus was calculated in 10 subjects using ConVNG and VOG. Equivalence of accuracy and precision was assessed using the “two one-sample t-test” (TOST) and Bayesian interval-null approaches. ConVNG was systematically compared to OpenFace and MediaPipe as computer vision (CV) benchmarks for gaze estimation.
Results
ConVNG tracking accuracy reached 9–15% of an average pupil diameter. In a fully independent clinical video dataset, ConVNG robustly detected pupil keypoints (median prediction confidence 0.85). SPV measurement accuracy was equivalent to VOG (TOST p < 0.017; Bayes factors (BF) > 24). ConVNG, but not MediaPipe, achieved equivalence to VOG in all SPV calculations. Median precision was 0.30°/s for ConVNG, 0.7°/s for MediaPipe and 0.12°/s for VOG. ConVNG precision was significantly higher than MediaPipe in vertical planes, but both algorithms’ precision was inferior to VOG.
Conclusions
ConVNG enables offline smartphone video nystagmography with an accuracy comparable to VOG and significantly higher precision than MediaPipe, a benchmark computer vision application for gaze estimation. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.