Objective ADHD Diagnosis Using Convolutional Neural Networks Over Daily-Life Activity Records

Automated ADHD detection using dual-modal sensory data and machine learning

This study explores using dual-modal sensory data and machine learning to objectively identify Attention-Deficit/Hyperactivity Disorder (ADHD), a neurodevelopmental disorder traditionally diagnosed through subjective clinical evaluations. Six machine learning algorithms, including Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), Neural Network (NN), and Support Vector Machine (SVM), were evaluated using both activity and heart rate variability (HRV) data collected from 103 participants. The results show that both activity and HRV data performed similarly when analyzed individually. However, when the two datasets were combined, the highest F1-score increased by 12 % compared to the activity data and 23 % compared to the HRV data. This combination leverages the complementary strengths of both data, representing a key contribution of our work. With the combined data, the SVM model performed best, achieving an F1-Score of 0.87 and a Matthews Correlation Coefficient of 0.77. This study highlights the significant potential of interdisciplinary collaboration and the use of diverse data sources to advance ADHD detection through cutting-edge machine learning techniques.

Objective approach to diagnosing attention deficit hyperactivity disorder by using pixel subtraction and machine learning classification of outpatient consultation videos

BACKGROUND

Attention deficit hyperactivity disorder (ADHD) is a common childhood neurodevelopmental disorder, affecting between 5% and 7% of school-age children. ADHD is typically characterized by persistent patterns of inattention or hyperactivity-impulsivity, and it is diagnosed on the basis of the criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, through subjective observations and information provided by parents and teachers. Diagnosing ADHD in children is challenging, despite several assessment tools, such as the Swanson, Nolan, and Pelham questionnaire, being widely available. Such scales provide only a subjective understanding of the disorder. In this study, we employed video pixel subtraction and machine learning classification to objectively categorize 85 participants (43 with a diagnosis of ADHD and 42 without) into an ADHD group or a non-ADHD group by quantifying their movements.

METHODS

We employed pixel subtraction movement quantization by analyzing movement features in videos of patients in outpatient consultation rooms. Pixel subtraction is a technique in which the number of pixels in one frame is subtracted from that in another frame to detect changes between the two frames. A difference between the pixel values indicates the presence of movement. In the current study, the patients' subtracted image sequences were characterized using three movement feature values: mean, variance, and Shannon entropy value. A classification analysis based on six machine learning models was performed to compare the performance indices and the discriminatory power of various features.

RESULTS

The results revealed that compared with the non-ADHD group, the ADHD group had significantly larger values for all movement features. Notably, the Shannon entropy values were 2.38 ± 0.59 and 1.0 ± 0.38 in the ADHD and non-ADHD groups, respectively (P < 0.0001). The Random Forest machine learning classification model achieved the most favorable results, with an accuracy of 90.24%, sensitivity of 88.85%, specificity of 91.75%, and area under the curve of 93.87%.

CONCLUSION

Our pixel subtraction and machine learning classification approach is an objective and practical method that can aid to clinical decisions regarding ADHD diagnosis.

The utility of wearable electroencephalography combined with behavioral measures to establish a practical multi-domain model for facilitating the diagnosis of young children with attention-deficit/hyperactivity disorder

BACKGROUND

A multi-method, multi-informant approach is crucial for evaluating attention-deficit/hyperactivity disorders (ADHD) in preschool children due to the diagnostic complexities and challenges at this developmental stage. However, most artificial intelligence (AI) studies on the automated detection of ADHD have relied on using a single datatype. This study aims to develop a reliable multimodal AI-detection system to facilitate the diagnosis of ADHD in young children.

METHODS

78 young children were recruited, including 43 diagnosed with ADHD (mean age: 68.07 ± 6.19 months) and 35 with typical development (mean age: 67.40 ± 5.44 months). Machine learning and deep learning methods were adopted to develop three individual predictive models using electroencephalography (EEG) data recorded with a wearable wireless device, scores from the computerized attention assessment via Conners' Kiddie Continuous Performance Test Second Edition (K-CPT-2), and ratings from ADHD-related symptom scales. Finally, these models were combined to form a single ensemble model.

RESULTS

The ensemble model achieved an accuracy of 0.974. While individual modality provided the optimal classification with an accuracy rate of 0.909, 0.922, and 0.950 using the ADHD-related symptom rating scale, the K-CPT-2 score, and the EEG measure, respectively. Moreover, the findings suggest that teacher ratings, K-CPT-2 reaction time, and occipital high-frequency EEG band power values are significant features in identifying young children with ADHD.

CONCLUSIONS

This study addresses three common issues in ADHD-related AI research: the utility of wearable technologies, integrating databases from diverse ADHD diagnostic instruments, and appropriately interpreting the models. This established multimodal system is potentially reliable and practical for distinguishing ADHD from TD, thus further facilitating the clinical diagnosis of ADHD in preschool young children.

What types of objective measures have been used to assess core ADHD symptoms in children and young people in naturalistic settings? A scoping review

OBJECTIVES

We described the range and types of objective measures of attention-deficit/hyperactivity disorder (ADHD) in children and young people (CYP) reported in research that can be applied in naturalistic settings.

DESIGN

Scoping review using best practice methods.

DATA SOURCES

MEDLINE, APA PsycINFO, Embase, (via OVID); British Education Index, Education Resources Information Centre, Education Abstracts, Education Research Complete, Child Development and Adolescent Papers, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Psychology and Behavioural Sciences Collection (via EBSCO) were searched between 1 December 2021 and 28 February 2022.

ELIGIBILITY CRITERIA

Papers reported an objective measure of ADHD traits in CYP in naturalistic settings written in English.

DATA EXTRACTION AND SYNTHESIS

2802 papers were identified; titles and abstracts were screened by two reviewers. 454 full-text papers were obtained and screened. 128 papers were eligible and included in the review. Data were extracted by the lead author, with 10% checked by a second team member. Descriptive statistics and narrative synthesis were used.

RESULTS

Of the 128 papers, 112 were primary studies and 16 were reviews. 87% were conducted in the USA, and only 0.8% originated from the Global South, with China as the sole representative. 83 objective measures were identified (64 observational and 19 acceleration-sensitive measures). Notably, the Behaviour Observation System for Schools (BOSS), a behavioural observation, emerged as one of the predominant measures. 59% of papers reported on aspects of the reliability of the measure (n=76). The highest inter-rater reliability was found in an unnamed measure (% agreement=1), Scope Classroom Observation Checklist (% agreement=0.989) and BOSS (% agreement=0.985). 11 papers reported on aspects of validity. 12.5% of papers reported on their method of data collection (eg, pen and paper, on an iPad). Of the 47 papers that reported observer training, 5 reported the length of time the training took ranging from 3 hours to 1 year. Despite recommendations to integrate objective measures alongside conventional assessments, use remains limited, potentially due to inconsistent psychometric properties across studies.

CONCLUSIONS

Many objective measures of ADHD have been developed and described, with the majority of these being direct behavioural observations. There is a lack of reporting of psychometric properties and guidance for researchers administering these measures in practice and in future studies. Methodological transparency is needed. Encouragingly, recent papers begin to address these issues.

Optimal interval and feature selection in activity data for detecting attention deficit hyperactivity disorder

Attention deficit hyperactivity disorder (ADHD) is a heterogeneous neurobehavioral disorder that is common in children and adolescents. Inattention, impulsivity, and hyperactivity are the key symptoms of ADHD patients. Traditional clinical assessments delay ADHD diagnosis and increase undiagnosed cases and costs, as well. The use of deep learning (DL) and machine learning (ML)-based objective techniques for diagnosing ADHD has grown exponentially in recent years as the efficiency of early diagnosis has improved. This research highlights the significance of utilizing feature selection techniques before constructing machine learning models on activity datasets. It also explores the distinctions between specific time-interval activity data and broader interval activity data in identifying ADHD patients from the clinical control group. Five ML models were developed and tested to assess the performance of two sets of features and different categories of activity data in predicting ADHD. The study concludes with the following findings: (i) the model's performance showed a notable improvement of 0.11 in accuracy with the adoption of a precise feature selection process; (ii) activity data recorded in the morning and at night are more significant predictors of ADHD compared to other times; (iii) the utilization of specific time interval data is crucial for ADHD prediction; (iv) the random forest performs better than the other machine learning models used in the study, with 84% accuracy, 79% precision, 85% F1-score, and 92% recall. As we move into an era where early disease prediction is possible, combining artificial intelligence methods with activity data could create a strong framework for helping doctors make decisions that can be used far beyond hospitals.

Reduced thalamic activity in ADHD under ABR forward masking conditions

Attention-deficit hyperactivity disorder (ADHD) is a common chronic neurodevelopmental disorder characterized by symptoms of inattention, overactivity, and/or impulsiveness. The prevalence of ADHD varies in different settings and there have been voices raised to call for more objective measures in order to avoid over- and underdiagnosing of ADHD. Auditory Brainstem Response (ABR) is a method where click shaped sounds evoke potentials that are recorder from electrodes on the skull of a patient. The aim of this study was to explore possible alterations in the ABR of 29 patients with ADHD compared to 39 healthy controls. We used a forward masked sound. We found differences in ABR that correspond to the thalamic area. The thalamus seems to play an active role in regulation of activity level in ADHD. More research is needed to draw any further conclusions on using ABR as an objective measurement to detect ADHD.

Objective and automatic assessment approach for diagnosing attention-deficit/hyperactivity disorder based on skeleton detection and classification analysis in outpatient videos

BACKGROUND

Attention-deficit/hyperactivity disorder (ADHD) is diagnosed in accordance with Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria by using subjective observations and information provided by parents and teachers. However, subjective analysis often leads to overdiagnosis or underdiagnosis. There are two types of motor abnormalities in patients with ADHD. First, hyperactivity with fidgeting and restlessness is the major diagnostic criterium for ADHD. Second, developmental coordination disorder characterized by deficits in the acquisition and execution of coordinated motor skills is not the major criterium for ADHD. In this study, a machine learning-based approach was proposed to evaluate and classify 96 patients into ADHD (48 patients, 26 males and 22 females, with mean age: 7y6m) and non-ADHD (48 patients, 26 males and 22 females, with mean age: 7y8m) objectively and automatically by quantifying their movements and evaluating the restlessness scales.

METHODS

This approach is mainly based on movement quantization through analysis of variance in patients' skeletons detected in outpatient videos. The patients' skeleton sequence in the video was detected using OpenPose and then characterized using 11 values of feature descriptors. A classification analysis based on six machine learning classifiers was performed to evaluate and compare the discriminating power of different feature combinations.

RESULTS

The results revealed that compared with the non-ADHD group, the ADHD group had significantly larger means in all cases of single feature descriptors. The single feature descriptor "thigh angle", with the values of 157.89 ± 32.81 and 15.37 ± 6.62 in ADHD and non-ADHD groups (p < 0.0001), achieved the best result (optimal cutoff, 42.39; accuracy, 91.03%; sensitivity, 90.25%; specificity, 91.86%; and AUC, 94.00%).

CONCLUSIONS

The proposed approach can be used to evaluate and classify patients into ADHD and non-ADHD objectively and automatically and can assist physicians in diagnosing ADHD.

Tools for the Diagnosis of ADHD in Children and Adolescents: A Systematic Review

CONTEXT

Correct diagnosis is essential for the appropriate clinical management of attention-deficit/hyperactivity disorder (ADHD) in children and adolescents.

OBJECTIVE

This systematic review provides an overview of the available diagnostic tools.

DATA SOURCES

We identified diagnostic accuracy studies in 12 databases published from 1980 through June 2023.

STUDY SELECTION

Any ADHD tool evaluation for the diagnosis of ADHD, requiring a reference standard of a clinical diagnosis by a mental health specialist.

DATA EXTRACTION

Data were abstracted and critically appraised by 1 reviewer and checked by a methodologist. Strength of evidence and applicability assessments followed Evidence-based Practice Center standards.

RESULTS

In total, 231 studies met eligibility criteria. Studies evaluated parental ratings, teacher ratings, youth self-reports, clinician tools, neuropsychological tests, biospecimen, EEG, and neuroimaging. Multiple tools showed promising diagnostic performance, but estimates varied considerably across studies, with a generally low strength of evidence. Performance depended on whether ADHD youth were being differentiated from neurotypically developing children or from clinically referred children.

LIMITATIONS

Studies used different components of available tools and did not report sufficient data for meta-analytic models.

CONCLUSIONS

A valid and reliable diagnosis of ADHD requires the judgment of a clinician who is experienced in the evaluation of youth with and without ADHD, along with the aid of standardized rating scales and input from multiple informants across multiple settings, including parents, teachers, and youth themselves.

Identification of attention deficit hyperactivity disorder with deep learning model

This article explores the detection of Attention Deficit Hyperactivity Disorder, a neurobehavioral disorder, from electroencephalography signals. Due to the unstable behavior of electroencephalography signals caused by complex neuronal activity in the brain, frequency analysis methods are required to extract the hidden patterns. In this study, the feature extraction was performed with the Multitaper and Multivariate Variational Mode Decomposition methods. Then, these features were analyzed with the neighborhood component analysis and the features that contribute effectively to the classification were selected. The deep learning model including the convolution, pooling, and bidirectional long short term cell and fully connected layer was trained with the selected features. The trained model could effectively classify the subjects with Attention Deficit Hyperactivity Disorder with a deep learning model, support vector machines and linear discriminant analysis. The experiments were validated with an Attention Deficit Hyperactivity Disorder open access dataset ( https://doi.org/10.21227/rzfh-zn36 ). In validation, the deep learning model was able to classify 1210 test samples (600 subjects in the control group as Normal and 610 subjects in the ADHD group as ADHD) in 0.1 s with an accuracy of 95.54%. This accuracy rate is quite high compared to the Linear Discriminant Analysis (76.38%) and Support Vector Machines (81.69%). Experimental results showed that the proposed approach can innovatively classify Attention Deficit Hyperactivity Disorder subjects from the Control group effectively.

Insight into ADHD diagnosis with deep learning on Actimetry: Quantitative interpretation of occlusion maps in age and gender subgroups

Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD.

OBJECTIVE

This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations.

METHODS

Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity.

RESULTS

Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population.

CONCLUSION

The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized.

SIGNIFICANCE

Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Accurate Identification of ADHD among Adults Using Real-Time Activity Data

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopment disorder that affects millions of children and typically persists into adulthood. It must be diagnosed efficiently and consistently to receive adequate treatment, otherwise, it can have a detrimental impact on the patient’s professional performance, mental health, and relationships. In this work, motor activity data of adults suffering from ADHD and clinical controls has been preprocessed to obtain 788 activity-related statistical features. Afterwards, principal component analysis has been carried out to obtain significant features for accurate classification. These features are then fed into six different machine learning algorithms for classification, which include C4.5, kNN, Random Forest, LogitBoost, SVM, and Naive Bayes. The detailed evaluation of the results through 10-fold cross-validation reveals that SVM outperforms other classifiers with an accuracy of 98.43%, F-measure of 98.42%, sensitivity of 98.33%, specificity of 98.56% and AUC of 0.983. Thus, a PCA-based SVM approach appears to be an effective choice for accurate identification of ADHD patients among other clinical controls using real-time analysis of activity data.

A Wearable Diagnostic Assessment System vs. SNAP-IV for the auxiliary diagnosis of ADHD: a diagnostic test

OBJECTIVE

We design a diagnostic test to evaluate the effectiveness and accuracy of A non-intrusive Wearable Diagnostic Assessment System versus SNAP-IV for auxiliary diagnosis of children with ADHD.

METHODS

This study included 55 children aged 6-16 years who were clinically diagnosed with ADHD by DSM-5, and 55 healthy children (typically developing). Each subject completes 10 tasks on the WeDA system (Wearable Diagnostic Assessment System) and Parents of each subject complete the SNAP-IV scale. We will calculate the validity indexes, including sensitivity, specificity, Youden's index, likelihood ratio, and other indexes including predictive value, diagnostic odds ratio, diagnostic accuracy and area under the curve [AUC] to assess the effectiveness of the WeDA system as well as the SNAP-IV.

RESULTS

The sensitivity (94.55% vs. 76.36%) and the specificity (98.18% vs. 80.36%) of the WeDA system were significantly higher than the SNAP-IV. The AUC of the WeDA system (0.964) was higher than the SNAP-IV (0.907). There is non-statistically significant difference between groups (p = 0.068), and both of them have high diagnostic accuracy. In addition, the diagnostic efficacy of the WeDA system was higher than that of SNAP-IV in terms of the Youden index, diagnostic accuracy, likelihood ratio, diagnostic odds ratio and predictive value.

CONCLUSION

The advantages of the WeDA system in terms of diagnostic objectivity, scientific design and ease of operation make it a promising system for widespread use in clinical practice.

Can Deep Learning Hit a Moving Target? A Scoping Review of Its Role to Study Neurological Disorders in Children

Neurological disorders dramatically impact patients of any age population, their families, and societies. Pediatrics are among vulnerable age populations who differently experience the devastating consequences of neurological conditions, such as attention-deficit hyperactivity disorders (ADHD), autism spectrum disorders (ASD), cerebral palsy, concussion, and epilepsy. System-level understanding of these neurological disorders, particularly from the brain networks' dynamic perspective, has led to the significant trend of recent scientific investigations. While a dramatic maturation in the network science application domain is evident, leading to a better understanding of neurological disorders, such rapid utilization for studying pediatric neurological disorders falls behind that of the adult population. Aside from the specific technological needs and constraints in studying neurological disorders in children, the concept of development introduces uncertainty and further complexity topping the existing neurologically driven processes caused by disorders. To unravel these complexities, indebted to the availability of high-dimensional data and computing capabilities, approaches based on machine learning have rapidly emerged a new trend to understand pathways better, accurately diagnose, and better manage the disorders. Deep learning has recently gained an ever-increasing role in the era of health and medical investigations. Thanks to its relatively more minor dependency on feature exploration and engineering, deep learning may overcome the challenges mentioned earlier in studying neurological disorders in children. The current scoping review aims to explore challenges concerning pediatric brain development studies under the constraints of neurological disorders and offer an insight into the potential role of deep learning methodology on such a task with varying and uncertain nature. Along with pinpointing recent advancements, possible research directions are highlighted where deep learning approaches can assist in computationally targeting neurological disorder-related processes and translating them into windows of opportunities for interventions in diagnosis, treatment, and management of neurological disorders in children.