Connectome-Based Model Predicts Deep Brain Stimulation Outcome in Parkinson's Disease

Ruihong Shang; Le He; Xiaodong Ma; Yu Ma; Xuesong Li

doi:10.3389/fncom.2020.571527

Connectome-Based Model Predicts Deep Brain Stimulation Outcome in Parkinson's Disease

Ruihong Shang, Le He, Xiaodong Ma, Yu Ma^*, Xuesong Li^*

^*Corresponding author for this work

School of Computer Science and Technology

Research output: Contribution to journal › Article › peer-review

12 Citations (Scopus)

Abstract

Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective invasive treatment for advanced Parkinson's disease (PD) at present. Due to the invasiveness and cost of operations, a reliable tool is required to predict the outcome of therapy in the clinical decision-making process. This work aims to investigate whether the topological network of functional connectivity states can predict the outcome of DBS without medication. Fifty patients were recruited to extract the features of the brain related to the improvement rate of PD after STN-DBS and to train the machine learning model that can predict the therapy's effect. The functional connectivity analyses suggested that the GBRT model performed best with Pearson's correlations of r = 0.65, p = 2.58E−07 in medication-off condition. The connections between middle frontal gyrus (MFG) and inferior temporal gyrus (ITG) contribute most in the GBRT model.

Original language	English
Article number	571527
Journal	Frontiers in Computational Neuroscience
Volume	14
DOIs	https://doi.org/10.3389/fncom.2020.571527
Publication status	Published - 28 Oct 2020

Keywords

Parkinson's disease
brain network
deep brain stimulation (DBS) surgery
machine learning
rs-fMRI

Access to Document

10.3389/fncom.2020.571527

Cite this

@article{a1c9acf593b944869e29c4b950dfcbc1,

title = "Connectome-Based Model Predicts Deep Brain Stimulation Outcome in Parkinson's Disease",

abstract = "Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective invasive treatment for advanced Parkinson's disease (PD) at present. Due to the invasiveness and cost of operations, a reliable tool is required to predict the outcome of therapy in the clinical decision-making process. This work aims to investigate whether the topological network of functional connectivity states can predict the outcome of DBS without medication. Fifty patients were recruited to extract the features of the brain related to the improvement rate of PD after STN-DBS and to train the machine learning model that can predict the therapy's effect. The functional connectivity analyses suggested that the GBRT model performed best with Pearson's correlations of r = 0.65, p = 2.58E−07 in medication-off condition. The connections between middle frontal gyrus (MFG) and inferior temporal gyrus (ITG) contribute most in the GBRT model.",

keywords = "Parkinson's disease, brain network, deep brain stimulation (DBS) surgery, machine learning, rs-fMRI",

author = "Ruihong Shang and Le He and Xiaodong Ma and Yu Ma and Xuesong Li",

note = "Publisher Copyright: {\textcopyright} Copyright {\textcopyright} 2020 Shang, He, Ma, Ma and Li.",

year = "2020",

month = oct,

day = "28",

doi = "10.3389/fncom.2020.571527",

language = "English",

volume = "14",

journal = "Frontiers in Computational Neuroscience",

issn = "1662-5188",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - Connectome-Based Model Predicts Deep Brain Stimulation Outcome in Parkinson's Disease

AU - Shang, Ruihong

AU - He, Le

AU - Ma, Xiaodong

AU - Ma, Yu

AU - Li, Xuesong

PY - 2020/10/28

Y1 - 2020/10/28

N2 - Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective invasive treatment for advanced Parkinson's disease (PD) at present. Due to the invasiveness and cost of operations, a reliable tool is required to predict the outcome of therapy in the clinical decision-making process. This work aims to investigate whether the topological network of functional connectivity states can predict the outcome of DBS without medication. Fifty patients were recruited to extract the features of the brain related to the improvement rate of PD after STN-DBS and to train the machine learning model that can predict the therapy's effect. The functional connectivity analyses suggested that the GBRT model performed best with Pearson's correlations of r = 0.65, p = 2.58E−07 in medication-off condition. The connections between middle frontal gyrus (MFG) and inferior temporal gyrus (ITG) contribute most in the GBRT model.

AB - Subthalamic nucleus deep brain stimulation (STN-DBS) is an effective invasive treatment for advanced Parkinson's disease (PD) at present. Due to the invasiveness and cost of operations, a reliable tool is required to predict the outcome of therapy in the clinical decision-making process. This work aims to investigate whether the topological network of functional connectivity states can predict the outcome of DBS without medication. Fifty patients were recruited to extract the features of the brain related to the improvement rate of PD after STN-DBS and to train the machine learning model that can predict the therapy's effect. The functional connectivity analyses suggested that the GBRT model performed best with Pearson's correlations of r = 0.65, p = 2.58E−07 in medication-off condition. The connections between middle frontal gyrus (MFG) and inferior temporal gyrus (ITG) contribute most in the GBRT model.

KW - Parkinson's disease

KW - brain network

KW - deep brain stimulation (DBS) surgery

KW - machine learning

KW - rs-fMRI

UR - http://www.scopus.com/inward/record.url?scp=85095932116&partnerID=8YFLogxK

U2 - 10.3389/fncom.2020.571527

DO - 10.3389/fncom.2020.571527

M3 - Article

AN - SCOPUS:85095932116

SN - 1662-5188

VL - 14

JO - Frontiers in Computational Neuroscience

JF - Frontiers in Computational Neuroscience

M1 - 571527

ER -

Connectome-Based Model Predicts Deep Brain Stimulation Outcome in Parkinson's Disease

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this