Exploring attentive task-based connectivity for screening attention deficit/hyperactivity disorder children: a functional near-infrared spectroscopy study

Predicting upper limb motor recovery in subacute stroke patients via fNIRS-measured cerebral functional responses induced by robotic training

BACKGROUND

Neural activation induced by upper extremity robot-assisted training (UE-RAT) helps characterize adaptive changes in the brains of poststroke patients, revealing differences in recovery potential among patients. However, it remains unclear whether these task-related neural activities can effectively predict rehabilitation outcomes. In this study, we utilized functional near-infrared spectroscopy (fNIRS) to measure participants' neural activity profiles during resting and UE-RAT tasks and developed models via machine learning to verify whether task-related functional brain responses can predict the recovery of upper limb motor function.

METHODS

Cortical activation and brain network functional connectivity (FC) in brain regions such as the superior frontal cortex, premotor cortex, and primary motor cortex were measured using fNIRS in 82 subacute stroke patients in the resting state and during UE-RAT. The Fugl-Meyer Upper Extremity Assessment Scale (FMA-UE) was chosen as the index for assessing upper extremity motor function, and clinical information such as demographic and neurophysiological data was also collected. Robust features were screened in 100 randomly divided training sets using the least absolute shrinkage and selection operator (LASSO) method. Based on the selected robust features, machine learning algorithms were used to develop clinical models, fNIRS models, and combined models that integrated both clinical and fNIRS features. Finally, Shapley Additive Explanations (SHAP) was applied to interpret the prediction process and analyze key predictive factors.

RESULTS

Compared to the resting state, task-related FC is a more robust feature for modeling, with screening frequencies above 90%. The combined models built using artificial neural networks (ANNs) and support vector machines (SVMs) significantly outperformed the other algorithms, with an average AUC of 0.861 (± 0.087) for the ANN and an average correlation coefficient (r) of 0.860 (± 0.069) for the SVM. Furthermore, predictive factor analysis of the models revealed that FC measured during tasks is the most important factor for predicting upper limb motor function.

CONCLUSION

This study confirmed that UE-RAT-induced FC can serve as an important predictor of rehabilitation, especially when combined with clinical information, further enhancing the accuracy of model predictions. These findings provide new insights for the early prediction of patients' recovery potential, which may contribute to personalized rehabilitation decisions.

Advances in the etiology and neuroimaging of children with attention deficit hyperactivity disorder

Attention deficit hyperactivity disorder (ADHD) is the most common neurodevelopmental disorder in children, characterized by age-inappropriate inattention, hyperactivity, and impulsivity, which can cause extensive damage to children's academic, occupational, and social skills. This review will present current advancements in the field of attention deficit hyperactivity disorder, including genetics, environmental factors, epigenetics, and neuroimaging features. Simultaneously, we will discuss the highlights of promising directions for further study.

A state-of-the-art overview of candidate diagnostic biomarkers for Attention-deficit/hyperactivity disorder (ADHD)

INTRODUCTION

Attention-deficit/hyperactivity disorder (ADHD) is one of the most common neurodevelopmental conditions and is highly heterogeneous in terms of symptom profile, associated cognitive deficits, comorbidities, and outcomes. Heterogeneity may also affect the ability to recognize and diagnose this condition. The diagnosis of ADHD is primarily clinical but there are increasing research efforts aiming at identifying biomarkers that can aid the diagnosis.

AREAS COVERED

We first discuss the definition of biomarkers and the necessary research steps from discovery to implementation. We then provide a broad overview of research studies on candidate diagnostic biomarkers in ADHD encompassing genetic/epigenetic, biochemical, neuroimaging, neurophysiological and neuropsychological techniques. Finally, we critically appraise current limitations in the field and suggest possible ways forward.

EXPERT OPINION

Despite the large number of studies and variety of techniques used, no promising biomarkers have been identified so far. Clinical and biological heterogeneity as well as methodological limitations, including small sample size, lack of standardization, confounding factors, and poor replicability, have hampered progress in the field. Going forward, increased international collaborative efforts are warranted to support larger and more robustly designed studies, develop multimodal datasets to combine biomarkers and improve diagnostic accuracy, and ensure reproducibility and meaningful clinical translation.

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.

Functional near-infrared spectroscopy in pediatric clinical research: Different pathophysiologies and promising clinical applications

Over its 30 years of existence, functional near-infrared spectroscopy (fNIRS) has matured into a highly versatile tool to study brain function in infants and young children. Its advantages, amongst others, include its ease of application and portability, the option to combine it with electrophysiology, and its relatively good tolerance to movement. As shown by the impressive body of fNIRS literature in the field of cognitive developmental neuroscience, the method's strengths become even more relevant for (very) young individuals who suffer from neurological, behavioral, and/or cognitive impairment. Although a number of studies have been conducted with a clinical perspective, fNIRS cannot yet be considered as a truly clinical tool. The first step has been taken in this direction by studies exploring options in populations with well-defined clinical profiles. To foster further progress, here, we review several of these clinical approaches to identify the challenges and perspectives of fNIRS in the field of developmental disorders. We first outline the contributions of fNIRS in selected areas of pediatric clinical research: epilepsy, communicative and language disorders, and attention-deficit/hyperactivity disorder. We provide a scoping review as a framework to allow the highlighting of specific and general challenges of using fNIRS in pediatric research. We also discuss potential solutions and perspectives on the broader use of fNIRS in the clinical setting. This may be of use to future research, targeting clinical applications of fNIRS in children and adolescents.

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.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Detection of Emotional Sensitivity Using fNIRS Based Dynamic Functional Connectivity

In this study, we proposed an analytical framework to identify dynamic task-based functional connectivity (FC) features as new biomarkers of emotional sensitivity in nursing students, by using a combination of unsupervised and supervised machine learning techniques. The dynamic FC was measured by functional Near-Infrared Spectroscopy (fNIRS), and computed using a sliding window correlation (SWC) analysis. A k -means clustering technique was applied to derive four recurring connectivity states. The states were characterized by both graph theory and semi-metric analysis. Occurrence probability and state transition were extracted as dynamic FC network features, and a Random Forest (RF) classifier was implemented to detect emotional sensitivity. The proposed method was trialled on 39 nursing students and 19 registered nurses during decision-making, where we assumed registered nurses have developed strategies to cope with emotional sensitivity. Emotional stimuli were selected from International Affective Digitized Sound System (IADS) database. Experiment results showed that registered nurses demonstrated single dominant connectivity state of task-relevance, while nursing students displayed in two states and had higher level of task-irrelevant state connectivity. The results also showed that students were more susceptive to emotional stimuli, and the derived dynamic FC features provided a stronger discriminating power than heart rate variability (accuracy of 81.65% vs 71.03%) as biomarkers of emotional sensitivity. This work forms the first study to demonstrate the stability of fNIRS based dynamic FC states as a biomarker. In conclusion, the results support that the state distribution of dynamic FC could help reveal the differentiating factors between the nursing students and registered nurses during decision making, and it is anticipated that the biomarkers might be used as indicators when developing professional training related to emotional sensitivity.

Early Identification of Alzheimer's Disease in Mouse Models: Application of Deep Neural Network Algorithm to Cognitive Behavioral Parameters

Alzheimer's disease (AD) is a worldwide burden. Diagnosis is complicated by the fact that AD is asymptomatic at an early stage. Studies using AD-modeled animals offer important and useful insights. Here, we classified mice with a high risk of AD at a preclinical stage by using only their behaviors. Wild-type and knock-in AD-modeled (App NL-G-F/NL-G-F ) mice were raised, and their cognitive behaviors were assessed in an automated monitoring system. The classification utilized a machine learning method, i.e., a deep neural network, together with optimized stepwise feature selection and cross-validation. The AD risk could be identified on the basis of compulsive and learning behaviors (89.3% ± 9.8% accuracy) shown by AD-modeled mice in the early age (i.e., 8-12 months old) when the AD symptomatic cognitions were relatively underdeveloped. This finding reveals the advantage of machine learning in unveiling the importance of compulsive and learning behaviors for early AD diagnosis in mice.

Atypical Dynamic-Connectivity Recruitment in Attention-Deficit/Hyperactivity Disorder Children: An Insight Into Task-Based Dynamic Connectivity Through an fNIRS Study

Connectivity between brain regions has been redefined beyond a stationary state. Even when a person is in a resting state, brain connectivity dynamically shifts. However, shifted brain connectivity under externally evoked stimulus is still little understood. The current study, therefore, focuses on task-based dynamic functional-connectivity (FC) analysis of brain signals measured by functional near-infrared spectroscopy (fNIRS). We hypothesize that a stimulus may influence not only brain connectivity but also the occurrence probabilities of task-related and task-irrelevant connectivity states. fNIRS measurement (of the prefrontal-to-inferior parietal lobes) was conducted on 21 typically developing (TD) and 21 age-matched attention-deficit/hyperactivity disorder (ADHD) children performing an inhibitory control task, namely, the Go/No-Go (GNG) task. It has been reported that ADHD children lack inhibitory control; differences between TD and ADHD children in terms of task-based dynamic FC were also evaluated. Four connectivity states were found to occur during the temporal task course. Two dominant connectivity states (states 1 and 2) are characterized by strong connectivities within the frontoparietal network (occurrence probabilities of 40%-56% and 26%-29%), and presumptively interpreted as task-related states. A connectivity state (state 3) shows strong connectivities in the bilateral medial frontal-to-parietal cortices (occurrence probability of 7-15%). The strong connectivities were found at the overlapped regions related the default mode network (DMN). Another connectivity state (state 4) visualizes strong connectivities in all measured regions (occurrence probability of 10%-16%). A global effect coming from cerebral vascular may highly influence this connectivity state. During the GNG stimulus interval, the ADHD children tended to show decreased occurrence probability of the dominant connectivity state and increased occurrence probability of other connectivity states (states 3 and 4). Bringing a new perspective to explain neuropathophysiology, these findings suggest atypical dynamic network recruitment to accommodate task demands in ADHD children.