Clinical Validation of Eye Vergence as an Objective Marker for Diagnosis of ADHD in Children

A Pilot Study to Improve Cognitive Performance and Pupil Responses in Mild Cognitive Impaired Patients Using Gaze-Controlled Gaming

Mild cognitive impairment (MCI) may progress to severe forms of dementia, so therapy is needed to maintain cognitive abilities. The neural circuitry for oculomotor control is closely linked to that which controls cognitive behavior. In this study, we tested whether training the oculomotor system with gaze-controlled video games could improve cognitive behavior in MCI patients. Patients played a simple game for 2-3 weeks while a control group played the same game using a mouse. Cognitive improvement was assessed using the MoCA screening test and CANTAB. We also measured eye pupil and vergence responses in an oddball paradigm. The results showed an increased score on the MoCA test specifically for the visuospatial domain and on the Rapid Visual Information Processing test of the CANTAB battery. Pupil responses also increased to target stimuli. Patients in the control group did not show significant improvements. This pilot study provides evidence for the potential cognitive benefits of gaze-controlled gaming in MCI patients.

Inclusion of a computerized test in ADHD diagnosis process can improve trust in the specialists' decision and elevate adherence levels

Attention deficit and hyperactivity disorder (ADHD) affects many life aspects of children and adults. Accurate identification, diagnosis and treatment of ADHD can facilitate better care. However, ADHD diagnosis and treatment methods are subject of controversy. Objective measures can elevate trust in specialist's decision and treatment adherence. In this observational study we asked whether knowing that a computerized test was included in ADHD diagnosis process results in more trust and intention to adhere with treatment recommendations. Questionnaires were administered to 459 people, 196 men, average age = 40.57 (8.90). Questions regarding expected trust and adherence, trust trait, trust in physician and health-care-institutions, and ADHD scales followed a scenario about parents referred to a neurologist for sons' ADHD diagnosis. The scenario presented to the test group (n = 185) mentioned that a computerized test was part of the diagnostic process. The control group scenario didn't mention any computerized test in the diagnostic process. Test group participants expressed more trust in the diagnosis and greater levels of intention for treatment adherence. Group differences in intention for treatment adherence were mediated by trust in decision. Inclusion of a computerized test in ADHD diagnosis process can improve trust in the specialists' decision and elevate adherence levels.

Cognitive Vergence Recorded with a Webcam-Based Eye-Tracker during an Oddball Task in an Elderly Population

(1) Background: Our previous research provides evidence that vergence eye movements may significantly influence cognitive processing and could serve as a reliable measure of cognitive issues. The rise of consumer-grade eye tracking technology, which uses sophisticated imaging techniques in the visible light spectrum to determine gaze position, is noteworthy. In our study, we explored the feasibility of using webcam-based eye tracking to monitor the vergence eye movements of patients with Mild Cognitive Impairment (MCI) during a visual oddball paradigm. (2) Methods: We simultaneously recorded eye positions using a remote infrared-based pupil eye tracker. (3) Results: Both tracking methods effectively captured vergence eye movements and demonstrated robust cognitive vergence responses, where participants exhibited larger vergence eye movement amplitudes in response to targets versus distractors. (4) Conclusions: In summary, the use of a consumer-grade webcam to record cognitive vergence shows potential. This method could lay the groundwork for future research aimed at creating an affordable screening tool for mental health care.

A Comparative Investigation of Wavelet Families for Classification of EOG Signals Related to Healthy and ADHD Children

Based on previous research, there are differences between eye movements of people with attention-deficit hyperactivity disorder (ADHD) and of healthy people, as a result, the existence of differences regarding the electrooculogram (EOG) signals of the 2 groups exists. Thus, this study aimed to examine the recorded EOG signals of 30 ADHD children and 30 healthy children while performing an attention-related task. For this purpose, the EOG signals of these 2 groups were decomposed utilizing various wavelet functions. Afterward, features, including mean, energy, and standard deviation (SD) of approximation and detail wavelet coefficients were calculated. The Davies-Bouldin (DB) index was used for the evaluation of the feature space quality. Finally, the 2 groups were classified using one-dimensional feature vector and support vector machine (SVM). The SD of detail coefficients (db4) was selected as the most effective feature for separating the 2 groups. Statistical analysis revealed that the values of energy and SD of EOG signals' detail coefficients were significantly lower in the ADHD group in comparison with the healthy group (P<.001). These results showed that the speed of the ADHD group's eye movements was slower due to the fact that the high-frequency band activity of EOG signals in the healthy group was higher. In addition, the EOG signals were classified with a detection accuracy of 83.42 ± 3.8%. The results of this study can be applied in designing an EOG biofeedback protocol to treat or mitigate the symptoms of ADHD patients.

Attention and impulsivity assessment using virtual reality games

The assessment of cognitive functions is mainly based on standardized neuropsychological tests, widely used in various fields such as personnel recruitment, education, or health. This paper presents a virtual reality game that allows collecting continuous measurements of both the performance and behaviour of the subject in an immersive, controllable, and naturalistic experience. The application registers variables related to the user's eye movements through the use of virtual reality goggles, as well as variables of the game performance. We study how virtual reality can provide data to help predict scores on the Attention Control Scale Test and the Barratt Impulsiveness Scale. We design the application and test it with a pilot group. We build a random forest regressor model to predict the attention and impulsivity scales' total score. When evaluating the performance of the model, we obtain a positive correlation with attention (0.434) and with impulsivity (0.382). In addition, our model identified that the most significant variables are the time spent looking at the target or at distractors, the eye movements variability, the number of blinks and the pupil dilation in both attention and impulsivity. Our results are consistent with previous results in the literature showing that it is possible to use data collected in virtual reality to predict the degree of attention and impulsivity.

Predicting childhood and adolescent attention-deficit/hyperactivity disorder onset: a nationwide deep learning approach

Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous disorder with a high degree of psychiatric and physical comorbidity, which complicates its diagnosis in childhood and adolescence. We analyzed registry data from 238,696 persons born and living in Sweden between 1995 and 1999. Several machine learning techniques were used to assess the ability of registry data to inform the diagnosis of ADHD in childhood and adolescence: logistic regression, random Forest, gradient boosting, XGBoost, penalized logistic regression, deep neural network (DNN), and ensemble models. The best fitting model was the DNN, achieving an area under the receiver operating characteristic curve of 0.75, 95% CI (0.74-0.76) and balanced accuracy of 0.69. At the 0.45 probability threshold, sensitivity was 71.66% and specificity was 65.0%. There was an overall agreement in the feature importance among all models (τ > .5). The top 5 features contributing to classification were having a parent with criminal convictions, male sex, having a relative with ADHD, number of academic subjects failed, and speech/learning disabilities. A DNN model predicting childhood and adolescent ADHD trained exclusively on Swedish register data achieved good discrimination. If replicated and validated in an external sample, and proven to be cost-effective, this model could be used to alert clinicians to individuals who ought to be screened for ADHD and to aid clinicians' decision-making with the goal of decreasing misdiagnoses. Further research is needed to validate results in different populations and to incorporate new predictors.

Attention Deficit Hyperactivity Disorder Assessment Based on Patient Behavior Exhibited in a Car Video Game: A Pilot Study

Symptoms of Attention Deficit Hyperactivity Disorder (ADHD) include excessive activity, difficulty sustaining attention, and inability to act in a reflective manner. Early diagnosis and treatment of ADHD is key but may be influenced by the observation and communication skills of caregivers, and the experience of the medical professional. Attempts to obtain additional measures to support the medical diagnosis, such as reaction time when performing a task, can be found in the literature. We propose an information recording system that allows to study in detail the behavior shown by children already diagnosed with ADHD during a car driving video game. We continuously record the participants’ activity throughout the task and calculate the error committed. Studying the trajectory graphs, some children showed uniform patterns, others lost attention from one point onwards, and others alternated attention/inattention intervals. Results show a dependence between the age of the children and their performance. Moreover, by analyzing the positions by age over time using clustering, we show that it is possible to classify children according to their performance. Future studies will examine whether this detailed information about each child’s performance pattern can be used to fine-tune treatment.

Oculomotor deficits in attention deficit hyperactivity disorder (ADHD): A systematic review and comprehensive meta-analysis

Atypical motor coordination and cognitive processes, such as response inhibition and working memory, have been extensively researched in individuals with attention deficit hyperactivity disorder (ADHD). Oculomotor neural circuits overlap extensively with regions involved in motor planning and cognition, therefore studies of oculomotor function may offer unique insights into motor and cognitive control in ADHD. We performed a series of pairwise meta-analyses based on data from 26 oculomotor studies in ADHD to examine whether there were differences in performance on visually-guided saccade, gap, antisaccade, memory-guided, pursuit eye movements and fixation tasks. These analyses revealed oculomotor disturbances in ADHD, particularly for difficulties relating to saccade inhibition, memorizing visual target locations and initiating antisaccades. There was no evidence for pursuit eye movement disturbances or saccade dysmetria. Investigating oculomotor abnormalities in ADHD may provide insight into top-down cognitive control processes and motor control, and may serve as a promising biomarker in ADHD research and clinical practice.

Eye-Tracking Training Improves Inhibitory Control in Children with Attention-Deficit/Hyperactivity Disorder

Disinhibition is a common sign among children with attention-deficit/hyperactivity disorder (ADHD). The present study examined the effect of computerized eye-tracking training to improve inhibitory control in ADHD children. Thirty-two ADHD children (mean age = 8.4 years) were recruited. Half of the participants underwent 240 min of eye-tracking training over two weeks (i.e., experimental group), while the other half did not receive any training (i.e., control group). After training, the experimental group exhibited significant improvements in neuropsychological tests of inhibition, such as faster reaction time in the incongruent condition of the Flanker test, more unique designs in the Category Fluency and Five-Point Tests, and a faster completion time in Trail 2 of the Children's Color Trail Test. The control group did not show significant changes in any of these tests. Our findings support the use of eye-tracking training to improve the inhibitory control of ADHD children.

Machine Learning Applications in Pediatric Ophthalmology

Purpose: To describe emerging applications of machine learning (ML) in pediatric ophthalmology with an emphasis on the diagnosis and treatment of disorders affecting visual development. Methods: Literature review of studies applying ML algorithms to problems in pediatric ophthalmology. Results: At present, the ML literature emphasizes applications in retinopathy of prematurity. However, there are increasing efforts to apply ML techniques in the diagnosis of amblyogenic conditions such as pediatric cataracts, strabismus, and high refractive error. Conclusions: A greater understanding of the principles governing ML will enable pediatric eye care providers to apply the methodology to unexplored challenges within the subspecialty.

Atypical Visual Scan Path Affects Remembering in ADHD

OBJECTIVE

Several studies agree on the link between attention and eye movements during reading. It has been well established that attention and working memory (WM) interact. A question that could be addressed to better understand these relationships is: to what extent can an attention deficit affect eye movements and, consequently, remembering a word? The main aims of the present study were (1) to compare visual patterns of word stimuli between children with Attention Deficit Hyperactivity Disorder (ADHD) and typically developing (TD) children, during a visual task on word stimuli; (2) to examine the WM accuracy of the word stimuli; and (3) to compare the dynamic of visual scan path in both groups.

METHOD

A total of 49 children with ADHD, age and sex matched with 32 TD children, were recruited. We used eye-tracking technology in which the Word Memory Test was implemented. To highlight the scan path of participants, two measures were used: the ordered direction of reading and the entropy index.

RESULTS

ADHD groups showed a poorer WM than TD group. They did not follow a typical scan path across the words compared with TD children, but their visual scanning was discontinuous, uncoordinated, and chaotic. ADHD groups showed an index of entropy among the four categories of saccades higher than TD group.

CONCLUSIONS

The findings were discussed in light of two directions: the relationship between atypical visual scan path and WM and the training implications related to the necessity of redirecting the dynamic of visual scan path in ADHD to improve WM.

Emerging Opportunities Provided by Technology to Advance Research in Child Health Globally

Current approaches to longitudinal assessment of children's developmental and psychological well-being, as mandated in the United Nations Sustainable Development Goals, are expensive and time consuming. Substantive understanding of global progress toward these goals will require a suite of new robust, cost-effective research tools designed to assess key developmental processes in diverse settings. While first steps have been taken toward this end through efforts such as the National Institutes of Health's Toolbox, experience-near approaches including naturalistic observation have remained too costly and time consuming to scale to the population level. This perspective presents 4 emerging technologies with high potential for advancing the field of child health and development research, namely (1) affective computing, (2) ubiquitous computing, (3) eye tracking, and (4) machine learning. By drawing attention of scientists, policy makers, investors/funders, and the media to the applications and potential risks of these emerging opportunities, we hope to inspire a fresh wave of innovation and new solutions to the global challenges faced by children and their families.

Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare

Precision Medicine implies a deep understanding of inter-individual differences in health and disease that are due to genetic and environmental factors. To acquire such understanding there is a need for the implementation of different types of technologies based on artificial intelligence (AI) that enable the identification of biomedically relevant patterns, facilitating progress towards individually tailored preventative and therapeutic interventions. Despite the significant scientific advances achieved so far, most of the currently used biomedical AI technologies do not account for bias detection. Furthermore, the design of the majority of algorithms ignore the sex and gender dimension and its contribution to health and disease differences among individuals. Failure in accounting for these differences will generate sub-optimal results and produce mistakes as well as discriminatory outcomes. In this review we examine the current sex and gender gaps in a subset of biomedical technologies used in relation to Precision Medicine. In addition, we provide recommendations to optimize their utilization to improve the global health and disease landscape and decrease inequalities.

Eye vergence responses in children with and without reading difficulties during a word detection task

Vergence eye movements are movements of both eyes in opposite directions. Vergence is known to have a role in binocular vision. However recent studies link vergence eye movements also to attention and attention disorders. As attention may be involved in dyslexia, it is sensible to guess that the presence of reading difficulties can be associated with specific patterns in vergence responses. Data from school children performing a word-reading task have been analysed. In the task, children had to distinguish words from non-words (scrambled words or row of X's), while their eye positions were recorded. Our findings show that after stimulus presentation eyes briefly converge. These vergence responses depend on the stimulus type and age of the child, and are different for children with reading difficulties. Our findings support the idea of a role of attention in word reading and offer an explanation of altered attention in dyslexia.

Developing and adopting safe and effective digital biomarkers to improve patient outcomes

Biomarkers are physiologic, pathologic, or anatomic characteristics that are objectively measured and evaluated as an indicator of normal biologic processes, pathologic processes, or biological responses to therapeutic interventions. Recent advances in the development of mobile digitally connected technologies have led to the emergence of a new class of biomarkers measured across multiple layers of hardware and software. Quantified in ones and zeros, these "digital" biomarkers can support continuous measurements outside the physical confines of the clinical environment. The modular software-hardware combination of these products has created new opportunities for patient care and biomedical research, enabling remote monitoring and decentralized clinical trial designs. However, a systematic approach to assessing the quality and utility of digital biomarkers to ensure an appropriate balance between their safety and effectiveness is needed. This paper outlines key considerations for the development and evaluation of digital biomarkers, examining their role in clinical research and routine patient care.

Eye vergence responses to novel and familiar stimuli in young children

Eye vergence is the slow movement of both eyes in opposite directions enabling binocular vision. Recently, it was suggested that vergence could be involved in orienting visual attention and memory having a role in cognitive processing of sensory information. In the present study, we assessed whether such vergence responses are observed in early childhood. We measured eye vergence responses in 43 children (12-37 months of age) while looking at novel and repeated object images. Based on previous research, we hypothesized that visual attention and Visual Short-Term Memory (VSMT) would be evidenced by differential vergence responses for both experimental conditions, i.e. repeated (familiar) vs. novel items. The results show that attention related vergence is present in early childhood and that responses to repeated images differ from the ones to novel items. Our current findings suggest that vergence mechanisms could be linking visual attention with short-term memory recognition.

A Low-Level Perceptual Correlate of Behavioral and Clinical Deficits in ADHD

In many studies of attention-deficit hyperactivity disorder (ADHD), stimulus encoding and processing (perceptual function) and response selection (executive function) have been intertwined. To dissociate deficits in these functions, we introduced a task that parametrically varied low-level stimulus features (orientation and color) for fine-grained analysis of perceptual function. It also required participants to switch their attention between feature dimensions on a trial-by-trial basis, thus taxing executive processes. Furthermore, we used a response paradigm that captured task-irrelevant motor output (TIMO), reflecting failures to use the correct stimulus-response rule. ADHD participants had substantially higher perceptual variability than controls, especially for orientation, as well as higher TIMO. In both ADHD and controls, TIMO was strongly affected by the switch manipulation. Across participants, the perceptual variability parameter was correlated with TIMO, suggesting that perceptual deficits are associated with executive function deficits. Based on perceptual variability alone, we were able to classify participants into ADHD and controls with a mean accuracy of about 77%. Participants' self-reported General Executive Composite score correlated not only with TIMO but also with the perceptual variability parameter. Our results highlight the role of perceptual deficits in ADHD and the usefulness of computational modeling of behavior in dissociating perceptual from executive processes.