Cerebral Cortex: Subcortical-cortical functional connectivity as a potential biomarker to identify patients with functional dyspepsia

Functional dyspepsia (FD) is a common functional gastrointestinal disorder characterized by self-reported symptoms of epigastric pain, epigastric burning, postprandial satiety, and early satiety, but routine clinical assessment These symptoms cannot be explained
.

Epidemiological studies have shown that about 20% of the world's population suffers from dyspepsia , of which 80% have no endoscopic evidence of these symptoms

Functional dyspepsia (FD) is a common functional gastrointestinal disorder characterized by self-reported symptoms of epigastric pain, epigastric burning, postprandial satiety, and early satiety, but routine clinical assessment These symptoms cannot be explained

Zeng Fang et al.

The research team used the Support Vector Machine (SVM) algorithm to establish a classification model of FD patients and normal controls, with the purpose of: 1) To detect whether and to what extent functional brain network features can distinguish FD patients from FD patients at the individual level.
HS, 2) identify taxonomic functional brain network features that make important contributions to classification, and 3) validate the robustness of these taxonomic features across brain atlases, thereby exploring the feasibility and stability of identifying FD patients based on functional brain network biomarkers
.

The research team used the Support Vector Machine (SVM) algorithm to establish a classification model of FD patients and normal controls, with the purpose of: 1) To detect whether and to what extent functional brain network features can distinguish FD patients from FD patients at the individual level.
HS, 2) identify taxonomic functional brain network features that make important contributions to classification, and 3) validate the robustness of these taxonomic features across brain atlases, thereby exploring the feasibility and stability of identifying FD patients based on functional brain network biomarkers
.

First, functional brain magnetic resonance imaging data of 100 FD patients and 100 healthy subjects were collected, and functional brain network features were extracted by independent component analysis
.

Then, a support vector machine classifier was built based on these functional brain network features to distinguish FD patients from healthy subjects

First, functional brain magnetic resonance imaging data of 100 FD patients and 100 healthy subjects were collected, and functional brain network features were extracted by independent component analysis

Selected independent components and functional brain networks
.

(A) Spatial distribution map of selected 35 independent components in the four networks

Selected independent components and functional brain networks

The findings showed that the classifier performed well in distinguishing patients with FD

The performance of the classifier in 100 iterations
.

The performance of the classifier in 100 iterations
.

Finally , 15 connections between subcortical nuclei (thalamus and caudate nucleus) and sensorimotor cortex, parahippocampal gyrus, and orbitofrontal cortex were identified as classification features
.

Finally , 15 connections between subcortical nuclei (thalamus and caudate nucleus) and sensorimotor cortex, parahippocampal gyrus, and orbitofrontal cortex were identified as classification features
.

Classification characteristics of FD patients and HS patients

Classification characteristics of FD patients and HS patients

Furthermore, the results of cross-brain atlas validation showed that these categorical features were robust in identifying FD patients
.

Furthermore, the results of cross-brain atlas validation showed that these categorical features were robust in identifying FD patients
.

Functional connectivity between the subcortical nuclei (thalamus and caudate) and the sensorimotor cortex, parahippocampal gyrus, and orbitofrontal cortex is a key feature to accurately differentiate patients with FD
.

These findings suggest the potential of using machine learning methods and functional brain network biomarkers to identify patients with FD, which may provide a promising method for objectively and accurately diagnosing FD in the future
.

Functional connectivity between subcortical nuclei (thalamus and caudate) and sensorimotor cortex, parahippocampal gyrus, orbitofrontal cortex is a key feature to accurately distinguish subcortical nuclei (thalamus and caudate) from sensorimotor cortex, Functional connectivity between the parahippocampal gyrus and the orbitofrontal cortex is a key feature to accurately differentiate patients with FD
.
These findings suggest the potential of using machine learning methods and functional brain network biomarkers to identify patients with FD, which may provide a promising method for objectively and accurately diagnosing FD in the future
.
, the use of machine learning methods and functional brain network biomarkers to identify FD patients has the potential, which may provide a promising method for objectively and accurately diagnosing FD in the future
.

original source

original source

Tao Yin, Ruirui Sun, Zhaoxuan He, Yuan Chen, Shuai Yin, Xiaoyan Liu, Jin Lu, Peihong Ma, Tingting Zhang, Liuyang Huang, Yuzhu Qu, Xueling Suo, Du Lei, Qiyong Gong, Fanrong Liang, Shenghong Li, Fang Zeng , Subcortical–Cortical Functional Connectivity as a Potential Biomarker for Identifying Patients with Functional Dyspepsia,  Cerebral Cortex , 2021;, bhab419,  https://doi.
org/10.
1093/cercor/bhab419

Tao Yin, Ruirui Sun, Zhaoxuan He, Yuan Chen, Shuai Yin, Xiaoyan Liu, Jin Lu, Peihong Ma, Tingting Zhang, Liuyang Huang, Yuzhu Qu, Xueling Suo, Du Lei, Qiyong Gong, Fanrong Liang, Shenghong Li, Fang Zeng , Subcortical–Cortical Functional Connectivity as a Potential Biomarker for Identifying Patients with Functional Dyspepsia,  Cerebral Cortex https://doi.
org/10.
1093/cercor/bhab419 https://doi.
org/10.
1093/cercor/bhab419 Leave a comment here