Literature DB >> 33497391

Clinical outcome prediction from analysis of microelectrode recordings using deep learning in subthalamic deep brain stimulation for Parkinson`s disease.

Kwang Hyon Park1, Sukkyu Sun2, Yong Hoon Lim1, Hye Ran Park3, Jae Meen Lee4, Kawngwoo Park5, Beomseok Jeon6, Hee-Pyoung Park7, Hee Chan Kim2,8,9, Sun Ha Paek1,10,11.   

Abstract

BACKGROUND: Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for improving the motor symptoms of advanced Parkinson's disease (PD). Accurate positioning of the stimulation electrodes is necessary for better clinical outcomes.
OBJECTIVE: We applied deep learning techniques to microelectrode recording (MER) signals to better predict motor function improvement, represented by the UPDRS part III scores, after bilateral STN DBS in patients with advanced PD. If we find the optimal stimulation point with MER by deep learning, we can improve the clinical outcome of STN DBS even under restrictions such as general anesthesia or non-cooperation of the patients.
METHODS: In total, 696 4-second left-side MER segments from 34 patients with advanced PD who underwent bilateral STN DBS surgery under general anesthesia were included. We transformed the original signal into three wavelets of 1-50 Hz, 50-500 Hz, and 500-5,000 Hz. The wavelet-transformed MER was used for input data of the deep learning. The patients were divided into two groups, good response and moderate response groups, according to DBS on to off ratio of UPDRS part III score for the off-medication state, 6 months postoperatively. The ratio were used for output data in deep learning. The Visual Geometry Group (VGG)-16 model with a multitask learning algorithm was used to estimate the bilateral effect of DBS. Different ratios of the loss function in the task-specific layer were applied considering that DBS affects both sides differently.
RESULTS: When we divided the MER signals according to the frequency, the maximal accuracy was higher in the 50-500 Hz group than in the 1-50 Hz and 500-5,000 Hz groups. In addition, when the multitask learning method was applied, the stability of the model was improved in comparison with single task learning. The maximal accuracy (80.21%) occurred when the right-to-left loss ratio was 5:1 or 6:1. The area under the curve (AUC) was 0.88 in the receiver operating characteristic (ROC) curve.
CONCLUSION: Clinical improvements in PD patients who underwent bilateral STN DBS could be predicted based on a multitask deep learning-based MER analysis.

Entities:  

Mesh:

Year:  2021        PMID: 33497391      PMCID: PMC7837468          DOI: 10.1371/journal.pone.0244133

Source DB:  PubMed          Journal:  PLoS One        ISSN: 1932-6203            Impact factor:   3.240


  24 in total

1.  Comparison of electrode location between immediate postoperative day and 6 months after bilateral subthalamic nucleus deep brain stimulation.

Authors:  Yong Hwy Kim; Hee Jin Kim; Cheolyoung Kim; Dong Gyu Kim; Beom Seok Jeon; Sun Ha Paek
Journal:  Acta Neurochir (Wien)       Date:  2010-08-19       Impact factor: 2.216

Review 2.  Deep brain stimulation of the subthalamic nucleus for the treatment of Parkinson's disease.

Authors:  Alim Louis Benabid; Stephan Chabardes; John Mitrofanis; Pierre Pollak
Journal:  Lancet Neurol       Date:  2009-01       Impact factor: 44.182

3.  Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy.

Authors:  Romany F Mansour
Journal:  Biomed Eng Lett       Date:  2017-08-31

4.  Direct visualization of deep brain stimulation targets in Parkinson disease with the use of 7-tesla magnetic resonance imaging.

Authors:  Zang-Hee Cho; Hoon-Ki Min; Se-Hong Oh; Jae-Yong Han; Chan-Woong Park; Je-Geun Chi; Young-Bo Kim; Sun Ha Paek; Andres M Lozano; Kendall H Lee
Journal:  J Neurosurg       Date:  2010-09       Impact factor: 5.115

5.  Unilateral Subthalamic Nucleus Stimulation in the Treatment of Asymmetric Parkinson"s Disease with Early Motor Complications.

Authors:  Michal Sobstyl; Miroslaw Zabek; Artur Zaczynski; Wojciech Gorecki; Zbigniew Mossakowski; Grazyna Brzuszkiewicz-Kuzmicka
Journal:  Turk Neurosurg       Date:  2017       Impact factor: 1.003

6.  A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations.

Authors:  Holger R Roth; Le Lu; Ari Seff; Kevin M Cherry; Joanne Hoffman; Shijun Wang; Jiamin Liu; Evrim Turkbey; Ronald M Summers
Journal:  Med Image Comput Comput Assist Interv       Date:  2014

7.  Low-frequency versus high-frequency subthalamic nucleus deep brain stimulation on postural control and gait in Parkinson's disease: a quantitative study.

Authors:  Srikant Vallabhajosula; Ihtsham U Haq; Nelson Hwynn; Genko Oyama; Michael Okun; Mark D Tillman; Chris J Hass
Journal:  Brain Stimul       Date:  2014-10-28       Impact factor: 8.955

8.  Pallidal neuronal activity: implications for models of dystonia.

Authors:  William D Hutchison; Anthony E Lang; Jonathan O Dostrovsky; Andres M Lozano
Journal:  Ann Neurol       Date:  2003-04       Impact factor: 10.422

9.  Influence of propofol and fentanyl on deep brain stimulation of the subthalamic nucleus.

Authors:  Wonki Kim; In Ho Song; Yong Hoon Lim; Mi-Ryoung Kim; Young Eun Kim; Jae Ha Hwang; In Keyoung Kim; Sang Woo Song; Jin Wook Kim; Woong-Woo Lee; Han-Joon Kim; Cheolyoung Kim; Hee Chan Kim; In Young Kim; Hee Pyoung Park; Dong Gyu Kim; Beom Seok Jeon; Sun Ha Paek
Journal:  J Korean Med Sci       Date:  2014-09-02       Impact factor: 2.153

10.  Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics.

Authors:  Yeong-Hyeon Byeon; Sung-Bum Pan; Keun-Chang Kwak
Journal:  Sensors (Basel)       Date:  2019-02-22       Impact factor: 3.576

View more
  1 in total

Review 1.  Therapeutic Potential of Ursolic Acid in Cancer and Diabetic Neuropathy Diseases.

Authors:  Manzar Alam; Sabeeha Ali; Sarfraz Ahmed; Abdelbaset Mohamed Elasbali; Mohd Adnan; Asimul Islam; Md Imtaiyaz Hassan; Dharmendra Kumar Yadav
Journal:  Int J Mol Sci       Date:  2021-11-10       Impact factor: 5.923

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.