Bispectral_Analysis_of_Parkinsonian_Rest_Tremor_7_13_2022.pdf (4.99 MB)

Bispectral Analysis of Parkinsonian Rest Tremor: New Characterization and Classification Insights Pre-/Post-DBS and Medication Treatment

Download (4.99 MB)
posted on 2022-07-19, 03:31 authored by Charalampos Lamprou, Ioannis ZiogasIoannis Ziogas, Leontios J. Hadjileontiadis

Rest tremor is a most common symptom of Parkinson’s Disease (PD), with diagnosis and severity estimation often being hindered by subjectivity and limitations of existing methods. Hence, methods that can accurately describe properties of PD rest tremor, while accounting for the presence of ongoing treatments, such as Deep Brain Stimulation (DBS) and medication, are important. A Higher Order Spectrum (HOS)-based analysis to extract features from index finger velocity recordings of 16 PD patients is proposed. Two different scenarios are implemented for characterizing and classifying tremor severity (Low-/High-Amplitude (LAT/HAT)) and treatment (medication/DBS) effectiveness, by means of statistical tests and a leave-one-subject-out cross-validation classification scheme, respectively. The proposed analysis resulted in area under the Receiver Operating Characteristics curve (AUC) score of 0.94 with 1/0.83 Sensitivity/Specificity, respectively, for the Medication treatment classification. For the DBS treatment, the proposed analysis resulted in an AUC score of 0.71, with 0.63/0.67 Sensitivity/Specificity, respectively. For LAT/HAT prediction, scores of 1/0.93 are achieved for AUC/Accuracy metrics, with 1/0.87 Sensitivity/Specificity, respectively. The proposed methodology outperforms existing methods regarding the prediction of LAT/HAT and treatment effectiveness. Additionally, our HOS-based methodology enables the establishment of new rest tremor classes, based on its nonlinearity and allows for new insights about the dynamic nature of the resting tremor production system. We propose a method that can effectively recognize rest tremor severity and assess the influence of medication and DBS. This study introduces, for the first time, nonlinearity-based classes for rest tremor and provides an accurate representation of tremor dynamics through HOS. 


European Union's Horizon 2020 Research and Innovation Programme under the Grant Agreement No 690494 -- i-PROGNOSIS: Intelligent Parkinson early detection guiding novel supportive interventions


Email Address of Submitting Author

Submitting Author's Institution

Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki

Submitting Author's Country

  • Greece