Identification of autism spectrum disorder based on short-term spontaneous hemodynamic fluctuations using deep learning in a multi-layer neural network

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Using dynamic spatio-temporal graph pooling network for identifying autism spectrum disorders in spontaneous functional infrared spectral sequence signals

BACKGROUND

Autism classification work on fNIRS data using dynamic graph networks. Explore the impact of the dynamic connection relationship between brain channels on ASD, and compare the brain channel connection diagrams of ASD and TD to explore potential factors that influence the development of autism.

METHOD

Using dynamic graph construction to mine the dynamic relationships of fNIRS data, obtain spatio-temporal correlations through dynamic feature extraction, and improve the information extraction capabilities of the network through spatio-temporal graph pooling to achieve classification of ASD.

RESULT

A classification effect with an accuracy of 97.2% was achieved using a short sequence of 1.75s. The results showed that the dynamic connections of channel 5 and 19, channel 12 and 25, and channel 7 and 34 have a greater impact on the classification of autism. Comparison with previously used method(s): Compared with previous deep learning models, our model achieves efficient classification using short-term fNIRS data of 1.75s, and analyzes the impact of dynamic connections on classification through dynamic graphs.

CONCLUSION

Using Dynamic Spatio-Temporal Graph Pooled Neural Networks (DSTGPN), dynamic connectivity between brain channels was found to have an impact on the classification of autism. By modeling the brain channel relationship maps of ASD and TD, hyperlink clusters were found to exist on the brain channel connections of ASD.

ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework

Autism Spectrum Disorder (ASD) treatment requires accurate diagnosis and effective rehabilitation. Artificial intelligence (AI) techniques in medical diagnosis and rehabilitation can aid doctors in detecting a wide range of diseases more effectively. Nevertheless, due to its highly heterogeneous symptoms and complicated nature, ASD diagnostics continues to be a challenge for researchers. This study introduces an intelligent system based on the Artificial Gorilla Troops Optimizer (GTO) metaheuristic optimizer to detect ASD using Deep Learning and Machine Learning. Kaggle and UCI ML Repository are the data sources used in this study. The first dataset is the Autistic Children Data Set, which contains 3,374 facial images of children divided into Autistic and Non-Autistic categories. The second dataset is a compilation of data from three numerical repositories: (1) Autism Screening Adults, (2) Autistic Spectrum Disorder Screening Data for Adolescents, and (3) Autistic Spectrum Disorder Screening Data for Children. When it comes to image dataset experiments, the most notable results are (1) a TF learning ratio greater than or equal to 50 is recommended, (2) all models recommend data augmentation, and (3) the DenseNet169 model reports the lowest loss value of 0.512. Concerning the numeric dataset, five experiments recommend standardization and the final five attributes are optional in the classification process. The performance metrics demonstrate the worthiness of the proposed feature selection technique using GTO more than counterparts in the literature review.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Detection of autism spectrum disorder (ASD) in children and adults using machine learning

Autism spectrum disorder (ASD) presents a neurological and developmental disorder that has an impact on the social and cognitive skills of children causing repetitive behaviours, restricted interests, communication problems and difficulty in social interaction. Early diagnosis of ASD can prevent from its severity and prolonged effects. Federated learning (FL) is one of the most recent techniques that can be applied for accurate ASD diagnoses in early stages or prevention of its long-term effects. In this article, FL technique has been uniquely applied for autism detection by training two different ML classifiers including logistic regression and support vector machine locally for classification of ASD factors and detection of ASD in children and adults. Due to FL, results obtained from these classifiers have been transmitted to central server where meta classifier is trained to determine which approach is most accurate in the detection of ASD in children and adults. Four different ASD patient datasets, each containing more than 600 records of effected children and adults have been obtained from different repository for features extraction. The proposed model predicted ASD with 98% accuracy (in children) and 81% accuracy (in adults).

Classification of autism based on short-term spontaneous hemodynamic fluctuations using an adaptive graph neural network

BACKGROUND

Short-term spontaneous hemodynamic fluctuations were collected by the functional near-infrared spectroscopy (fNIRS) system to classify children with autism spectrum disorder (ASD) and typical development (TD), and to explore abnormalities in the left inferior frontal gyrus in ASD.

METHODS

Using the fNIRS data of 25 children with ASD and 22 children with TD, a graph neural network combined with the temporal convolution module and the graph convolution module was used, to extract the spatio-temporal features of the data and achieve accurate classification of ASD.

RESULTS

The graph neural network was used to obtain a good classification result in the left inferior frontal gyrus, with an accuracy of 97.1%, precision of 95.1%, and specificity of 93.4%. It was found that the 5th channel (which is located in BA 10) and the 8th channel (which is located in BA 47) in the left inferior frontal gyrus were closely correlated with ASD.

COMPARISON WITH PREVIOUSLY USED METHOD(S)

Compared with the previous deep learning model using the same input, the accuracy of our model has increased by up to 13%, and the correlation between channels in the left inferior frontal gyrus area with the best classification effect was explored through the graph neural network.

CONCLUSION

The adaptive graph neural network (AGNN) model may be able to mine more valuable information to distinguish ASD from TD and in addition, the left inferior frontal gyrus may have greater investigative value.

Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network

The accurate diagnosis of autism spectrum disorder (ASD) is of great practical significance in clinical practice. The spontaneous hemodynamic fluctuations were collected by functional near-infrared spectroscopy (fNIRS) from the bilateral frontal and temporal cortices of typically developing (TD) children and children with ASD. Since traditional machine learning and deep learning methods cannot make full use of the potential spatial dependence between variable pairs, and require a long time series to diagnose ASD. Therefore, we use adaptive spatiotemporal graph convolution network (ASGCN) and short time series to classify ASD and TD. To capture spatial and temporal features of fNIRS multivariable time series without the pre-defined graph, we combined the improved adaptive graph convolution network (GCN) and gated recurrent units (GRU). We conducted a series of experiments on the fNIRS dataset, and found that only using 2.1 s short time series could achieve high precision classification, with an accuracy of 95.4%. This suggests that our approach may have the potential to detect pathological signals in autism patients within 2.1 s. In different brain regions, the left frontal lobe has the best classification effect, and the abnormalities occur more frequently in left hemisphere and frontal lobe region. Moreover, we also found that there were correlations between multiple channels, which had different degrees of influence on the classification of ASD. From this, we can also generalize to a wider range, there may be potential correlations between different brain regions. This may help to better understand the cortical mechanism of ASD.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-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.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed 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.

FINDINGS

A 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 RELEVANCE

This 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.

Technologies to support the diagnosis and/or treatment of neurodevelopmental disorders: A systematic review

In recent years, there has been a great interest in utilizing technology in mental health research. The rapid technological development has encouraged researchers to apply technology as a part of a diagnostic process or treatment of Neurodevelopmental Disorders (NDDs). With the large number of studies being published comes an urgent need to inform clinicians and researchers about the latest advances in this field. Here, we methodically explore and summarize findings from studies published between August 2019 and February 2022. A search strategy led to the identification of 4108 records from PubMed and APA PsycInfo databases. 221 quantitative studies were included, covering a wide range of technologies used for diagnosis and/or treatment of NDDs, with the biggest focus on Autism Spectrum Disorder (ASD). The most popular technologies included machine learning, functional magnetic resonance imaging, electroencephalogram, magnetic resonance imaging, and neurofeedback. The results of the review indicate that technology-based diagnosis and intervention for NDD population is promising. However, given a high risk of bias of many studies, more high-quality research is needed.

Identifying autism spectrum disorder in resting-state fNIRS signals based on multiscale entropy and a two-branch deep learning network

BACKGROUND

The demand for early and precise identification of autism spectrum disorder (ASD) presented a challenge to the prediction of ASD with a non-invasive neuroimaging method.

NEW METHOD

A deep learning model was proposed to identify children with ASD using the resting-state functional near-infrared spectroscopy (fNIRS) signals. In this model, the input was the pattern of brain complexity represented by multiscale entropy of fNIRS time-series signals, with the purpose to solve the problem of deep learning analysis when the raw signals were limited by length and the number of subjects. The model consisted of a two-branch deep learning network, where one branch was a convolution neural network and the other was a long short-term memory neural network based on an attention mechanism.

RESULTS

Our model could achieve an identification accuracy of 94%. Further analysis used the SHapley Additive exPlanations (SHAP) method to balance the accuracy and the number of optical channels, thus reducing the complexity of fNIRS experiment. COMPARISON WITH PREVIOUSLY USED METHOD(S): in identification accuracy, our model was about 14% higher than previously used deep learning models with the same input and 4% higher than the same model but directly using fNIRS signals as input. We could obtain a discriminative accuracy of 90% with nearly half of the measurement channels by the SHAP method.

CONCLUSIONS

Using the pattern of brain complexity as input was effective in the deep learning model when the fNIRS signals were insufficient. With the SHAP method, it was possible to reduce the number of optical channels, while maintaining high accuracy in ASD identification.

Deep learning in fNIRS: a review

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional near-infrared spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, deep learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields. Aim: We aim to review the emerging DL applications in fNIRS studies. Approach: We first introduce some of the commonly used DL techniques. Then, the review summarizes current DL work in some of the most active areas of this field, including brain-computer interface, neuro-impairment diagnosis, and neuroscience discovery. Results: Of the 63 papers considered in this review, 32 report a comparative study of DL techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of the classification accuracy. In addition, eight studies also utilize DL to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions: The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.

Looking for “fNIRS Signature” in Autism Spectrum: A Systematic Review Starting From Preschoolers

Accumulating evidence suggests that functional Near-Infrared Spectroscopy (fNIRS) can provide an essential bridge between our current understanding of neural circuit organization and cortical activity in the developing brain. Indeed, fNIRS allows studying brain functions through the measurement of neurovascular coupling that links neural activity to subsequent changes in cerebral blood flow and hemoglobin oxygenation levels. While the literature offers a multitude of fNIRS applications to typical development, only recently this tool has been extended to the study of neurodevelopmental disorders (NDDs). The exponential rise of scientific publications on this topic during the last years reflects the interest to identify a “fNIRS signature” as a biomarker of high translational value to support both early clinical diagnosis and treatment outcome. The purpose of this systematic review is to describe the updating clinical applications of fNIRS in NDDs, with a specific focus on preschool population. Starting from this rationale, a systematic search was conducted for relevant studies in different scientific databases (Pubmed, Scopus, and Web of Science) resulting in 13 published articles. In these studies, fNIRS was applied in individuals with Autism Spectrum Disorder (ASD) or infants at high risk of developing ASD. Both functional connectivity in resting-state conditions and task-evoked brain activation using multiple experimental paradigms were used in the selected investigations, suggesting that fNIRS might be considered a promising method for identifying early quantitative biomarkers in the autism field.

Domain adaptation based on rough adjoint inconsistency and optimal transport for identifying autistic patients

BACKGROUND AND OBJECTIVE

Computer aided diagnosis technology has been widely used to diagnose autism spectrum disorder (ASD) from neural images. The performance of the model usually depends largely on a sufficient number of training samples that reflect the real sample distribution. Due to the lack of labelled neural images data, multisite data are often pooled together to expand the sample size. However, the heterogeneity among sites will inevitably lead to a decline in the generalization of models. To solve this problem, we propose a multisource unsupervised domain adaptation method using rough adjoint inconsistency and optimal transport.

METHODS

First, we define the concept of rough adjoint inconsistency and propose a double quantization method based on rough adjoint inconsistency and Dempster-Shafer (D-S) evidence theory to estimate the weight coefficient of each source domain to accurately describe the importance of each source domain to the target domain. Second, using optimal transport theory, we weaken the data distribution differences between domains and solve the problem of class imbalance by adjusting the sampling weights among classes.

RESULTS

The ASD recognition accuracy of the proposed method is improved on all eight tasks, which are 70.67%, 64.86%, 62.50%, 70.80%, 73.08%, 71.19%, 75.41% and 75.76%, respectively. Our proposed model achieves superior performance compared to traditional machine learning methods and other recently proposed deep learning model.

CONCLUSIONS

Our method demonstrates that the fusion of rough adjoint inconsistency and optimal transport can be a powerful tool for identifying ASD and quantifying the correlations between domains.

The amplitude of fNIRS hemodynamic response in the visual cortex unmasks autistic traits in typically developing children

Autistic traits represent a continuum dimension across the population, with autism spectrum disorder (ASD) being the extreme end of the distribution. Accumulating evidence shows that neuroanatomical and neurofunctional profiles described in relatives of ASD individuals reflect an intermediate neurobiological pattern between the clinical population and healthy controls. This suggests that quantitative measures detecting autistic traits in the general population represent potential candidates for the development of biomarkers identifying early pathophysiological processes associated with ASD. Functional near-infrared spectroscopy (fNIRS) has been extensively employed to investigate neural development and function. In contrast, the potential of fNIRS to define reliable biomarkers of brain activity has been barely explored. Features of non-invasiveness, portability, ease of administration, and low-operating costs make fNIRS a suitable instrument to assess brain function for differential diagnosis, follow-up, analysis of treatment outcomes, and personalized medicine in several neurological conditions. Here, we introduce a novel standardized procedure with high entertaining value to measure hemodynamic responses (HDR) in the occipital cortex of adult subjects and children. We found that the variability of evoked HDR correlates with the autistic traits of children, assessed by the Autism-Spectrum Quotient. Interestingly, HDR amplitude was especially linked to social and communication features, representing the core symptoms of ASD. These findings establish a quick and easy strategy for measuring visually-evoked cortical activity with fNIRS that optimize the compliance of young subjects, setting the background for testing the diagnostic value of fNIRS visual measurements in the ASD clinical population.

fNIRS-derived neurocognitive ratio as a biomarker for neuropsychiatric diseases

Significance: Clinical use of fNIRS-derived features has always suffered low sensitivity and specificity due to signal contamination from background systemic physiological fluctuations. We provide an algorithm to extract cognition-related features by eliminating the effect of background signal contamination, hence improving the classification accuracy. Aim: The aim in this study is to investigate the classification accuracy of an fNIRS-derived biomarker based on global efficiency (GE). To this end, fNIRS data were collected during a computerized Stroop task from healthy controls and patients with migraine, obsessive compulsive disorder, and schizophrenia. Approach: Functional connectivity (FC) maps were computed from [HbO] time series data for neutral (N), congruent (C), and incongruent (I) stimuli using the partial correlation approach. Reconstruction of FC matrices with optimal choice of principal components yielded two independent networks: cognitive mode network (CM) and default mode network (DM). Results: GE values computed for each FC matrix after applying principal component analysis (PCA) yielded strong statistical significance leading to a higher specificity and accuracy. A new index, neurocognitive ratio (NCR), was computed by multiplying the cognitive quotients (CQ) and ratio of GE of CM to GE of DM. When mean values of NCR ( N C R ¯ ) over all stimuli were computed, they showed high sensitivity (100%), specificity (95.5%), and accuracy (96.3%) for all subjects groups. Conclusions: N C R ¯ can reliable be used as a biomarker to improve the classification of healthy to neuropsychiatric patients.