Classification of Schizophrenia by Combination of Brain Effective and Functional Connectivity

Zhao, Zongya; Li, Jun; Niu, Yanxiang; Wang, Chang; Zhao, Junqiang; Yuan, Qingli; Ren, Qiongqiong; Xu, Yongtao; Yu, Yi

doi:10.3389/fnins.2021.651439

Cited by 19 publications

(15 citation statements)

References 62 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nearly half of the models (48.3% [268 of 555]) were found in studies authored by those with academic training in computers and data science (eTable 2 in Supplement 1). Schizophrenia (25.4% [141 of 555 models])…”

Section: Resultsmentioning

confidence: 99%

“…In the predictors domain, 187 of 555 models (33.7%; 95% CI, 29.9%- 37.6%) were rated with high ROB (Table 1). Defining predictors by knowing the outcome of these models was the unique source of the high ROB in this domain (ie, signaling question 2.2: were predictor assessments made without knowledge of outcome data?).…”

Section: Resultsmentioning

confidence: 99%

“…Defining predictors by knowing the outcome of these models was the unique source of the high ROB in this domain (ie, signaling question 2.2: were predictor assessments made without knowledge of outcome data?). In the outcome domain, high ROB was scored for 198 of 469 models (35.7%; 95% CI, 31.8%-39.7%) (Table 1). These models had a high ROB because the outcome knowledge of testing data sets was leaked into the predictors of the training set (ie, signaling question 3.3: were predictors excluded from the outcome definition?…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

ImportanceNeuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.ObjectiveTo systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.Evidence ReviewPubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.FindingsA total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).Conclusions and RelevanceThis systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…They reported convincing results when using synchronization measures and extracting the SSVEP features to distinguish schizophrenic patients finely. We hope that these two indicators, along with the functional features of brain connectivity (41), can help the psychiatrists better distinguish schizophrenic patients with positive and negative dominant symptoms.…”

Section: Discussionmentioning

confidence: 99%

Information-Theoretic Analysis of EEG Signals to Differentiate Schizophrenic Patients with Positive and Negative Symptoms and Control Group

Afrooz

Taghavi

2022

Iran J Psychiatry Behav Sci

View full text Add to dashboard Cite

Background: The precise differentiation of schizophrenic patients with positive and negative symptoms is still challenging; hence, psychiatrists mainly focus on diagnosing schizophrenic patients with positive symptoms. However, schizophrenic patients with negative symptoms have revealed remarkably poor outcomes. Objectives: This study aimed to differentiate schizophrenic patients with positive and negative dominant symptoms quantitatively by classifying their electroencephalography (EEG) features. Methods: In this study, 36 patients with schizophrenia and 26 age-matched control subjects voluntarily participated. Their EEG signals were captured and characterized by elicited multiscale entropy to decode the number of irregularities captured in each EEG channel. The principal component analysis (PCA) was deployed to decrease the dimension of elicited features, and the reduced features were applied to three Gaussian Naive Bayes classifiers, each of which was trained for a specific class. Results: The classification of the three groups resulted in 77.86% accuracy, while this accuracy in the schizophrenic groups provided 65% accuracy. In the resting state, the normal and schizophrenic subjects were differentiated by a high rate (95.43%). Conclusions: Exploiting information-theoretic features of the EEG signals over the scalp and automatic classification of these features, we can well-differentiate schizophrenic patients with different dominant symptoms. Moreover, better classification results can be achieved by passing the EEG features through PCA.

show abstract

“…Brain network techniques have been used to analyze the functional state of the brain in patients suffering from mental disorders, which are caused by structural damage or dysfunction of the brain. Zhao et al (2021) captured abnormal brain changes in the SCZ by their tools for functional connectivity. Sun et al (2017) extracted network features for evoked EEG of SCZ and HC with support vector machines (SVM) in which classification accuracy reached 80%, suggesting that the brain regions that play a major role were concentrated in the frontal and occipital lobes.…”

Section: Introductionmentioning

confidence: 99%

Abnormality of Functional Connections in the Resting State Brains of Schizophrenics

Zhu

Zhang

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

To explore the change of brain connectivity in schizophrenics (SCZ), the resting-state EEG source functional connections of SCZ and healthy control (HC) were investigated in this paper. Different band single-layer networks, multilayer networks, and improved multilayer networks were constructed and their topological attributes were extracted. The topological attributes of SCZ and HC were automatically distinguished using ensemble learning methods called Ensemble Learning based on Trees and Soft voting method, and the effectiveness of different network construction methods was compared based on the classification accuracy. The results showed that the classification accuracy was 89.38% for α band network, 82.5% for multilayer network, and 86.88% for improved multilayer network. Comparing patients with SCZ to those with Alzheimer’s disease (AD), the classification accuracy of improved multilayer network was the highest, which was 88.12%. The power spectrum in the α band of SCZ was significantly lower than HC, whereas there was no significant difference between SCZ and AD. This indicated that the improved multilayer network can effectively distinguish SCZ and other groups not only when their power spectrum was significantly different. The results also suggested that the improved multilayer topological attributes were regarded as biological markers in the clinical diagnosis of patients with schizophrenia and even other mental disorders.

show abstract

Classification of Schizophrenia by Combination of Brain Effective and Functional Connectivity

Cited by 19 publications

References 62 publications

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Information-Theoretic Analysis of EEG Signals to Differentiate Schizophrenic Patients with Positive and Negative Symptoms and Control Group

Abnormality of Functional Connections in the Resting State Brains of Schizophrenics

Contact Info

Product

Resources

About