Machine Learning Analysis Reveals Abnormal Static and Dynamic Low-Frequency Oscillations Indicative of Long-Term Menstrual Pain in Primary Dysmenorrhea Patients

Gui, Shaogao; Chen, Ri-Bo; Zhong, Yang; Huang, Xin

doi:10.2147/jpr.s332224

Cited by 10 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with other machine learning methods, such as random forest, naïve Bayes, and convolutional neural network. SVM methods have been successfully used to classify diseases, such as iridocyclitis ( Tong et al, 2021 ), primary dysmenorrhea ( Gui et al, 2021 ), and major depressive disorder ( Gao et al, 2021 ). However, no studies have used SVM and VMHC methods to distinguish patients with CE from HCs.…”

Section: Introductionmentioning

confidence: 99%

Altered Homotopic Connectivity in the Cerebellum Predicts Stereopsis Dysfunction in Patients With Comitant Exotropia

Chen

Liu

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

PurposeComitant exotropia (CE) is a common eye disorder characterized by impaired stereoscopic vision and eye deviation. Previous neuroimaging studies demonstrated that patients with CE were accompanied by specific functional and structural abnormalities of the brain. However, the effect of impaired stereoscopic vision and eye deviation on interhemispheric homotopic connectivity remains unknown.MethodsA total of thirty-six patients with CE (25 males and 11 females) and 36 well-matched healthy controls underwent magnetic resonance imaging scanning. The voxel-mirrored homotopic connectivity (VMHC) method was applied to assess the interhemispheric homotopic connectivity changes in patients with CE. Furthermore, the support vector machine method was applied to assess to differentiate patients with CE from healthy controls (HCs) with the VMHC maps as a feature.ResultsCompared with HCs, patients with CE showed significantly increased VMHC values in the bilateral cerebelum_ 8 and cerebelum_4_5. Moreover, we found that the VMHC maps showed an accuracy of 81.94% and an area under the curve of 0.87 for distinguishing the patients with CE from HCs.ConclusionOur study demonstrates that patients with CE showed interhemispheric homotopic connectivity changes in the cerebellum, which might reflect the neurological mechanisms of impaired stereoscopic vision and eye deviation in patients with CE.

show abstract

Section: Introductionmentioning

confidence: 99%

Altered Homotopic Connectivity in the Cerebellum Predicts Stereopsis Dysfunction in Patients With Comitant Exotropia

Chen

Liu

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Although the application of artificial intelligence in the medical field is still in the initial stage, with more in-depth development of machine learning technology, it will become a general trend for doctors to use artificial intelligence to diagnose and manage the health of the patients in the future. SVM has been widely applied in various diseases and achieved great classification performance ( Chan et al, 2019 ; Gui et al, 2021 ). Using the SVM classifier, the patients with TIA could be differentiated from HCs by dynamic local metrics.…”

Section: Discussionmentioning

confidence: 99%

The Predictive Value of Dynamic Intrinsic Local Metrics in Transient Ischemic Attack

Huang

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

BackgroundTransient ischemic attack (TIA) is known as “small stroke.” However, the diagnosis of TIA is currently difficult due to the transient symptoms. Therefore, objective and reliable biomarkers are urgently needed in clinical practice.ObjectiveThe purpose of this study was to investigate whether dynamic alterations in resting-state local metrics could differentiate patients with TIA from healthy controls (HCs) using the support-vector machine (SVM) classification method.MethodsBy analyzing resting-state functional MRI (rs-fMRI) data from 48 patients with and 41 demographically matched HCs, we compared the group differences in three dynamic local metrics: dynamic amplitude of low-frequency fluctuation (d-ALFF), dynamic fractional amplitude of low-frequency fluctuation (d-fALFF), and dynamic regional homogeneity (d-ReHo). Furthermore, we selected the observed alterations in three dynamic local metrics as classification features to distinguish patients with TIA from HCs through SVM classifier.ResultsWe found that TIA was associated with disruptions in dynamic local intrinsic brain activities. Compared with HCs, the patients with TIA exhibited increased d-fALFF, d-fALFF, and d-ReHo in vermis, right calcarine, right middle temporal gyrus, opercular part of right inferior frontal gyrus, left calcarine, left occipital, and left temporal and cerebellum. These alternations in the dynamic local metrics exhibited an accuracy of 80.90%, sensitivity of 77.08%, specificity of 85.37%, precision of 86.05%, and area under curve of 0.8501 for distinguishing the patients from HCs.ConclusionOur findings may provide important evidence for understanding the neuropathology underlying TIA and strong support for the hypothesis that these local metrics have potential value in clinical diagnosis.

show abstract

“…In addition, cerebellum activation may also be related to the transmission of negative emotional states caused by pain and mental stress ( Wittbrodt et al, 2020 ). RS-fMRI studies have shown abnormal local brain activity in the cerebellum and increased FC between the cerebellum and hippocampus in patients with chronic pain, which are closely related to pain perception and emotion regulation ( Wang et al, 2015 , 2016 ; Wei et al, 2020 ; Gui et al, 2021 ). In this study, TMD patients showed decreased ALFF of the right cerebellum_crus2 and increased FC between the PHG and vermis, and associated with the degree of oral-facial pain and depressive symptoms.…”

Section: Discussionmentioning

confidence: 99%

Disrupted Spontaneous Neural Activity and Its Interaction With Pain and Emotion in Temporomandibular Disorders

Chen

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

Background and PurposeTemporomandibular disorders (TMD), especially pain-related TMD, are closely related to social and psychological factors. We aimed to measure changes in spontaneous brain activity and its related functional connectivity (FC), as well as FC characteristics within the mood-regulating circuits (MRC) in TMD patients by resting-state functional magnetic resonance imaging (RS-fMRI), and to analyze the relationship between these parameters and emotional symptoms.Materials and MethodsTwenty-one adult TMD patients and thirty demographically matched healthy controls (HCs) underwent clinical scale evaluation and RS-fMRI scanning. After processing RS-fMRI data, the values of the amplitude of low-frequency fluctuation (ALFF) between the two groups were compared. Regions with abnormal ALFF values were selected as areas of interest (ROIs) to compare the differences of whole-brain seed-based FC between groups. The FCs between regions within MRC were also analyzed and compared. In addition, the relationships between RS-fMRI characteristics and pain and mood were explored by correlation and mediation analyses.ResultsCompared with HCs, TMD patients showed increased ALFF in the right parahippocampal gyrus (PHG), the right supplementary motor area, and the bilateral precentral gyrus, with decreased ALFF in the right cerebelum_crus2. Patients showed enhanced right PHG-related FC in the vermis and posterior cingulate cortex, orbitofrontal cortex (OFC)-related FC in the striatal-frontal regions, while decreased dorsolateral prefrontal cortex-related FC in the amygdala. In TMD patients, ALFF values in the right PHG and FC values between the right PHG and the vermis were positively correlated with depressive symptoms. Abnormal FCs in the left striatal-orbitofrontal pathway were correlated with pain and depressive symptoms. More importantly, mediation analysis revealed that chronic pain mediates the relationship between FC of right PHG with vermis and depressive symptoms, and abnormal FC in the left striatal-orbitofrontal pathway can mediate the association between pain and depressive symptoms.ConclusionTMD patients have dysregulated spontaneous activity and FC in the default mode network, sensorimotor network and pain-related regions, as well as dysfunction of the fronto-striatal-limbic circuits. The development of negative emotions in TMD may be related to the dysfunction of components within the reward system (especially hippocampus complex, OFC, striatum) due to chronic pain.

show abstract

Machine Learning Analysis Reveals Abnormal Static and Dynamic Low-Frequency Oscillations Indicative of Long-Term Menstrual Pain in Primary Dysmenorrhea Patients

Cited by 10 publications

References 38 publications

Altered Homotopic Connectivity in the Cerebellum Predicts Stereopsis Dysfunction in Patients With Comitant Exotropia

Altered Homotopic Connectivity in the Cerebellum Predicts Stereopsis Dysfunction in Patients With Comitant Exotropia

The Predictive Value of Dynamic Intrinsic Local Metrics in Transient Ischemic Attack

Disrupted Spontaneous Neural Activity and Its Interaction With Pain and Emotion in Temporomandibular Disorders

Contact Info

Product

Resources

About