Search

Background: Deep brain stimulation (DBS) to the subthalamic nucleus (STN) is an effective neurosurgery that overcomes the motor system alternations of patients with advanced Parkinson's disease. The most challenging aspect of DBS surgery is the accurate identification of STN and its borders. In general, it is performed manually by a neurophysiologist using the microelectrode recordings (MERs). This process is subjective, and tedious and further, interpretation of MERs is difficult because of its inherent nonstationary variations., New Methods: In this work, the wavelet-packet based features are proposed to automatically localize the STN and its subcortical structures using microelectrode recorded signals during DBS surgery. The study analyses 2904 MERs of 26 PD patients who underwent DBS implantation. The low and high order statistical parameters are extracted from the wavelet packet coefficients of MERs and used in the classifications, namely, non-STN vs. STN, pre-STN vs. STN and STN vs. post-STN., Results: Most of the features are significantly different in STN and its subcortical regions, namely, pre-STN and post-STN. The proposed features achieve an average accuracy of 85 % in non-STN vs. STN, 87.2 % in pre-STN vs. STN and 77.7 % in STN vs. post-STN. The accuracy is improved by around 10 % in non-STN vs. STN and STN vs. post-STN when the transition error is 1 mm., Comparison With Existing Methods: The proposed features are found to be better than the wavelet features., Conclusions: The proposed approach could be a potential useful adjunct for the real-time rapid intraoperative identification of STN and its anatomical borders., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Introduction: Deep brain stimulation of the subthalamic nucleus (STN DBS) has been shown to reduce antiparkinsonian medication in Parkinson's disease. We aimed to investigate the changes in long-term medication profile with STN DBS., Methods: Antiparkinsonian medication data for 56 patients were collected from as early as 3 years before STN DBS up to 10 years after. Cost spending on medication changes was analyzed. Mean levodopa equivalent daily dose (LEDD) was projected 10 years into the future based on preoperative data to create a comparator group wherein the patients did not undergo STN DBS. Use of neuroleptics and antidepressants was also recorded., Results: LEDD requirement was significantly reduced by a mean of 31 ± 2% over 10 years after DBS, from 1049 ± 381 mg at pre-DBS baseline, to 713 ± 392 mg at 1 year post-DBS, and 712 ± 385 mg at 10 years post-DBS. This was associated with a mean reduction of 35 ± 3% in medicine cost. Modeled LEDD requirements for not having STN DBS were in the range of 1489 mg to 2721 mg at 10 years post-DBS (109-282% higher than the observed mean LEDD in DBS cohort). The proportion of patients increased from 5% before STN DBS to 14% at 10 year post-DBS for neuroleptics, and 11-23% for antidepressants., Conclusion: STN DBS led to LEDD reduction and antiparkinsonian medication cost savings in our South-East Asian cohort. Medication reduction with STN DBS in our cohort over the 10-year period was comparable to those reported in Western populations.

Accurate localization of subthalamic nucleus (STN) is a key prior in deep brain stimulation (DBS) surgery for the patients with advanced Parkinson's disease (PD). Microelectrode recordings (MERs) along with preplanned trajectories are often employed for the STN localization and it remains challenging task. These MER signals are nonstationary and multicomponent in nature. In this study, we propose a system based on time-frequency features of MERs to differentiate the STN and non-STN regions. We assessed the system with 50 MER trajectories from 26 PD patients who have undergone DBS surgery. The signals are pre-processed and subjected to six-level wavelet decomposition. Then, the entropy is computed from the detailed and approximate coefficients. These features are fed to the random forest classifier and the model is evaluated by leave one patient out cross-validation. The results show that entropy associated with detailed wavelet coefficients (D 1 and D 2 ) are higher in STN where as it is lower in other wavelet scales. All extracted features except entropy from approximate coefficients are found to have significant difference between non-STN and STN (p<; 0.05). The random forest classifier achieves about 83% accuracy and 87% precision in differentiating the STN and non-STN regions.

Highlights • Automatic STN detection improves the efficiency and accuracy of target location. • Both spike independent and dependent features are useful for detection of STN. • Further research required for STN sub territories. Abstract Objective This study seeks to systematically review the selection of features and algorithms for machine learning and automation in deep brain stimulation surgery (DBS) for Parkinson's disease. This will assist in consolidating current knowledge and accuracy levels to allow greater understanding and research to be performed in automating this process, which could lead to improved clinical outcomes. Methods A systematic literature review search was conducted for all studies that utilized machine learning and DBS in Parkinson's disease. Results Ten studies were identified from 2006 utilizing machine learning in DBS surgery for Parkinson's disease. Different combinations of both spike independent and spike dependent features have been utilized with different machine learning algorithms to attempt to delineate the subthalamic nucleus (STN) and its surrounding structures. Conclusion The state-of-the-art algorithms achieve good accuracy and error rates with relatively short computing time, however, the currently achievable accuracy is not sufficiently robust enough for clinical practice. Moreover, further research is required for identifying subterritories of the STN. Significance This is a comprehensive summary of current machine learning algorithms that discriminate the STN and its adjacent structures for DBS surgery in Parkinson's disease. [ABSTRACT FROM AUTHOR]