Machine Learning-Based Prediction of Attention-Deficit/Hyperactivity Disorder and Sleep Problems With Wearable Data in Children

Machine learning approach to investigate pregnancy and childbirth risk factors of sleep problems in early adolescence: Evidence from two cohort studies

BACKGROUND

This study aimed to predict early adolescent sleep problems using pregnancy and childbirth risk factors through machine learning algorithms, and to evaluate model performance internally and externally.

METHODS

Data from the China Jintan Child Cohort study (CJCC; n=848) for model development and the US Healthy Brain and Behavior Study (HBBS; n=454) for external validation were employed. Maternal pregnancy histories, obstetric data, and adolescent sleep problems were collected. Several machine learning techniques were employed, including least absolute shrinkage and selection operator, logistic regression, random forest, naïve bayes, extreme gradient boosting, decision tree, and neural network. The area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, and root mean square of residuals were used to evaluate model performance.

RESULTS

Key predictors for CJCC adolescents' sleep problems include gestational age, birthweight, duration of delivery, and maternal happiness during pregnancy. In HBBS adolescents, the duration of postnatal depressive emotions was the primary perinatal predictor. The prediction models developed in the CJCC had good-to-excellent internal validation performance but poor performance in predicting the sleep problems in HBBS adolescents.

CONCLUSION

The identification of specific perinatal risk factors associated with adolescent sleep problems can inform targeted interventions during and after pregnancy to mitigate these risks. Health providers should consider integrating these predictive factors into routine pre- and postnatal assessments to identify at-risk populations. The variability in model performance across different cohorts highlights the need for context-specific models and the cautious application of predictive analytics across diverse populations. Future research should focus on refining predictive models to account for such variations, potentially through the incorporation of additional socio-cultural factors and genetic markers. This study emphasizes the importance of personalized and culturally sensitive approaches in the prediction and management of adolescent sleep problems, leveraging advanced computational methods to enhance maternal and child health outcomes.

Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations

Psychiatric disorders are complex and influenced by both genetic and environmental factors. However, studying the full spectrum of these disorders is hindered by practical limitations on measuring human behavior. This highlights the need for novel technologies that can measure behavioral changes at an intermediate level between diagnosis and genotype. Wearable devices are a promising tool in precision medicine, since they can record physiological measurements over time in response to environmental stimuli and do so at low cost and minimal invasiveness. Here we analyzed wearable and genetic data from a cohort of the Adolescent Brain Cognitive Development study. We generated >250 wearable-derived features and used them as intermediate phenotypes in an interpretable AI modeling framework to assign risk scores and classify adolescents with psychiatric disorders. Our model identifies key physiological processes and leverages their temporal patterns to achieve a higher performance than has been previously possible. To investigate how these physiological processes relate to the underlying genetic architecture of psychiatric disorders, we also utilized these intermediate phenotypes in univariate and multivariate GWAS. We identified a total of 29 significant genetic loci and 52 psychiatric-associated genes, including ELFN1 and ADORA3. These results show that wearable-derived continuous features enable a more precise representation of psychiatric disorders and exhibit greater detection power compared to categorical diagnostic labels. In summary, we demonstrate how consumer wearable technology can facilitate dimensional approaches in precision psychiatry and uncover etiological linkages between behavior and genetics.

Digital assessments for children and adolescents with ADHD: a scoping review

Introduction

In spite of rapid advances in evidence-based treatments for attention deficit hyperactivity disorder (ADHD), community access to rigorous gold-standard diagnostic assessments has lagged far behind due to barriers such as the costs and limited availability of comprehensive diagnostic evaluations. Digital assessment of attention and behavior has the potential to lead to scalable approaches that could be used to screen large numbers of children and/or increase access to high-quality, scalable diagnostic evaluations, especially if designed using user-centered participatory and ability-based frameworks. Current research on assessment has begun to take a user-centered approach by actively involving participants to ensure the development of assessments that meet the needs of users (e.g., clinicians, teachers, patients).

Methods

The objective of this mapping review was to identify and categorize digital mental health assessments designed to aid in the initial diagnosis of ADHD as well as ongoing monitoring of symptoms following diagnosis.

Results

Results suggested that the assessment tools currently described in the literature target both cognition and motor behaviors. These assessments were conducted using a variety of technological platforms, including telemedicine, wearables/sensors, the web, virtual reality, serious games, robots, and computer applications/software.

Discussion

Although it is evident that there is growing interest in the design of digital assessment tools, research involving tools with the potential for widespread deployment is still in the early stages of development. As these and other tools are developed and evaluated, it is critical that researchers engage patients and key stakeholders early in the design process.

Unsupervised machine learning for identifying attention-deficit/hyperactivity disorder subtypes based on cognitive function and their implications for brain structure

BACKGROUND

Structural anomalies in the frontal lobe and basal ganglia have been reported in patients with attention-deficit/hyperactivity disorder (ADHD). However, these findings have been not always consistent because of ADHD diversity. This study aimed to identify ADHD subtypes based on cognitive function and find their distinct brain structural characteristics.

METHODS

Using the data of 656 children with ADHD from the Adolescent Brain Cognitive Development (ABCD) Study, we applied unsupervised machine learning to identify ADHD subtypes using the National Institutes of Health Toolbox Tasks. Moreover, we compared the regional brain volumes between each ADHD subtype and 6601 children without ADHD (non-ADHD).

RESULTS

Hierarchical cluster analysis automatically classified ADHD into three distinct subtypes: ADHD-A (n = 212, characterized by high-order cognitive ability), ADHD-B (n = 190, characterized by low cognitive control, processing speed, and episodic memory), and ADHD-C (n = 254, characterized by strikingly low cognitive control, working memory, episodic memory, and language ability). Structural analyses revealed that the ADHD-C type had significantly smaller volumes of the left inferior temporal gyrus and right lateral orbitofrontal cortex than the non-ADHD group, and the right lateral orbitofrontal cortex volume was positively correlated with language performance in the ADHD-C type. However, the volumes of the ADHD-A and ADHD-B types were not significantly different from those of the non-ADHD group.

CONCLUSIONS

These results indicate the presence of anomalies in the lateral orbitofrontal cortex associated with language deficits in the ADHD-C type. Subtype specificity may explain previous inconsistencies in brain structural anomalies reported in ADHD.

A systematic review on the application of machine learning models in psychometric questionnaires for the diagnosis of attention deficit hyperactivity disorder

Attention deficit hyperactivity disorder is one of the most prevalent neurodevelopmental disorders worldwide. Recent studies show that machine learning has great potential for the diagnosis of attention deficit hyperactivity disorder. The aim of the present article is to systematically review the scientific literature on machine learning studies for the diagnosis of attention deficit hyperactivity disorder, focusing on psychometric questionnaire tools. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines were adopted. The review protocol was registered in the PROSPERO database. A search was conducted in three databases-Web of Science Core Collection, Scopus and Pubmed-with the aim of identifying studies that apply ML techniques to support the diagnosis of attention deficit hyperactivity disorder. A total of 17 empirical studies were found that met the established inclusion criteria. The results showed that machine learning can be used to increase the accuracy of attention deficit hyperactivity disorder diagnosis. Machine learning techniques are useful and effective strategies that can complement traditional diagnostics in patients with attention deficit hyperactivity disorder.

Contributions of brain regions to machine learning-based classifications of attention deficit hyperactivity disorder (ADHD) utilizing EEG signals

OBJECTIVE

The study presented focuses on the creation of a machine learning (ML) model that uses electrophysiological (EEG) data to identify kids with attention deficit hyperactivity disorder (ADHD) from healthy controls. The EEG signals are acquired during cognitive tasks to distinguish children with ADHD from their counterparts.

METHODOLOGY

The EEG data recorded in cognitive exercises was filtered using low pass Bessel filter and notch filters to remove artifacts, by the data set owners. To identify unique EEG patterns, we used many well-known classifiers, including Naïve Bayes (NB), Random Forest, Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost and Linear Discriminant Analysis (LDA), to identify distinct EEG patterns. Input features comprised EEG data from nineteen channels, individually and in combination.

FINDINGS

Study indicates that EEG-based categorization can differentiate between individuals with ADHD and healthy individuals with accuracy of 84%. The RF classifier achieved a maximum accuracy of 0.84 when particular region combinations were used. Evaluation of classification performance utilizing hemisphere-specific EEG data yielded promising outcomes, particularly in the right hemisphere channels.

NOVELTY

The study goes beyond traditional methodologies by investigating the effect of regional data on categorization results. The contributions of various brain regions to these classifications are being extensively researched. Understanding the role of different brain regions in ADHD can lead to better diagnosis and treatment options for individuals with ADHD. The study of categorization ability, utilizing EEG data specific to each hemisphere, particularly channels in the right hemisphere region, provides further granularity to the findings.

Generalized sleep decoding with basal ganglia signals in multiple movement disorders

Sleep disturbances profoundly affect the quality of life in individuals with neurological disorders. Closed-loop deep brain stimulation (DBS) holds promise for alleviating sleep symptoms, however, this technique necessitates automated sleep stage decoding from intracranial signals. We leveraged overnight data from 121 patients with movement disorders (Parkinson's disease, Essential Tremor, Dystonia, Essential Tremor, Huntington's disease, and Tourette's syndrome) in whom synchronized polysomnograms and basal ganglia local field potentials were recorded, to develop a generalized, multi-class, sleep specific decoder - BGOOSE. This generalized model achieved 85% average accuracy across patients and across disease conditions, even in the presence of recordings from different basal ganglia targets. Furthermore, we also investigated the role of electrocorticography on decoding performances and proposed an optimal decoding map, which was shown to facilitate channel selection for optimal model performances. BGOOSE emerges as a powerful tool for generalized sleep decoding, offering exciting potentials for the precision stimulation delivery of DBS and better management of sleep disturbances in movement disorders.

Machine learning algorithms to the early diagnosis of fetal alcohol spectrum disorders

Introduction

Fetal alcohol spectrum disorders include a variety of physical and neurocognitive disorders caused by prenatal alcohol exposure. Although their overall prevalence is around 0.77%, FASD remains underdiagnosed and little known, partly due to the complexity of their diagnosis, which shares some symptoms with other pathologies such as autism spectrum, depression or hyperactivity disorders.

Methods

This study included 73 control and 158 patients diagnosed with FASD. Variables selected were based on IOM classification from 2016, including sociodemographic, clinical, and psychological characteristics. Statistical analysis included Kruskal-Wallis test for quantitative factors, Chi-square test for qualitative variables, and Machine Learning (ML) algorithms for predictions.

Results

This study explores the application ML in diagnosing FASD and its subtypes: Fetal Alcohol Syndrome (FAS), partial FAS (pFAS), and Alcohol-Related Neurodevelopmental Disorder (ARND). ML constructed a profile for FASD based on socio-demographic, clinical, and psychological data from children with FASD compared to a control group. Random Forest (RF) model was the most efficient for predicting FASD, achieving the highest metrics in accuracy (0.92), precision (0.96), sensitivity (0.92), F1 Score (0.94), specificity (0.92), and AUC (0.92). For FAS, XGBoost model obtained the highest accuracy (0.94), precision (0.91), sensitivity (0.91), F1 Score (0.91), specificity (0.96), and AUC (0.93). In the case of pFAS, RF model showed its effectiveness, with high levels of accuracy (0.90), precision (0.86), sensitivity (0.96), F1 Score (0.91), specificity (0.83), and AUC (0.90). For ARND, RF model obtained the best levels of accuracy (0.87), precision (0.76), sensitivity (0.93), F1 Score (0.84), specificity (0.83), and AUC (0.88). Our study identified key variables for efficient FASD screening, including traditional clinical characteristics like maternal alcohol consumption, lip-philtrum, microcephaly, height and weight impairment, as well as neuropsychological variables such as the Working Memory Index (WMI), aggressive behavior, IQ, somatic complaints, and depressive problems.

Discussion

Our findings emphasize the importance of ML analyses for early diagnoses of FASD, allowing a better understanding of FASD subtypes to potentially improve clinical practice and avoid misdiagnosis.

Exploring an objective measure of overactivity in children with rare genetic syndromes

BACKGROUND

Overactivity is prevalent in several rare genetic neurodevelopmental syndromes, including Smith-Magenis syndrome, Angelman syndrome, and tuberous sclerosis complex, although has been predominantly assessed using questionnaire techniques. Threats to the precision and validity of questionnaire data may undermine existing insights into this behaviour. Previous research indicates objective measures, namely actigraphy, can effectively differentiate non-overactive children from those with attention-deficit hyperactivity disorder. This study is the first to examine the sensitivity of actigraphy to overactivity across rare genetic syndromes associated with intellectual disability, through comparisons with typically-developing peers and questionnaire overactivity estimates.

METHODS

A secondary analysis of actigraphy data and overactivity estimates from The Activity Questionnaire (TAQ) was conducted for children aged 4-15 years with Smith-Magenis syndrome (N=20), Angelman syndrome (N=26), tuberous sclerosis complex (N=16), and typically-developing children (N=61). Actigraphy data were summarized using the M10 non-parametric circadian rhythm variable, and 24-hour activity profiles were modelled via functional linear modelling. Associations between actigraphy data and TAQ overactivity estimates were explored. Differences in actigraphy-defined activity were also examined between syndrome and typically-developing groups, and between children with high and low TAQ overactivity scores within syndromes.

RESULTS

M10 and TAQ overactivity scores were strongly positively correlated for children with Angelman syndrome and Smith-Magenis syndrome. M10 did not substantially differ between the syndrome and typically-developing groups. Higher early morning activity and lower evening activity was observed across all syndrome groups relative to typically-developing peers. High and low TAQ group comparisons revealed syndrome-specific profiles of overactivity, persisting throughout the day in Angelman syndrome, occurring during the early morning and early afternoon in Smith-Magenis syndrome, and manifesting briefly in the evening in tuberous sclerosis complex.

DISCUSSION

These findings provide some support for the sensitivity of actigraphy to overactivity in children with rare genetic syndromes, and offer syndrome-specific temporal descriptions of overactivity. The findings advance existing descriptions of overactivity, provided by questionnaire techniques, in children with rare genetic syndromes and have implications for the measurement of overactivity. Future studies should examine the impact of syndrome-related characteristics on actigraphy-defined activity and overactivity estimates from actigraphy and questionnaire techniques.

Telepsychiatry in the Treatment of Major Depressive Disorders

This chapter explores the transformative role of telepsychiatry in managing major depressive disorders (MDD). Traversing geographical barriers and reducing stigma, this innovative branch of telemedicine leverages digital platforms to deliver effective psychiatric care. We investigate the evolution of telepsychiatry, examining its diverse interventions such as videoconferencing-based psychotherapy, medication management, and mobile applications. While offering significant advantages like increased accessibility, cost-effectiveness, and improved patient engagement, challenges in telepsychiatry include technological barriers, privacy concerns, ethical and legal considerations, and digital literacy gaps. Looking forward, emerging technologies like virtual reality, artificial intelligence, and precision medicine hold immense potential to personalize and enhance treatment effectiveness. Recognizing its limitations and advocating for equitable access, this chapter underscores telepsychiatry's power to revolutionize MDD treatment, making quality mental healthcare a reality for all.

Prediction of Postnatal Growth Failure in Very Low Birth Weight Infants Using a Machine Learning Model

Accurate prediction of postnatal growth failure (PGF) can be beneficial for early intervention and prevention. We aimed to develop a machine learning model to predict PGF at discharge among very low birth weight (VLBW) infants using extreme gradient boosting. A total of 729 VLBW infants, born between 2013 and 2017 in four hospitals, were included. PGF was defined as a decrease in z-score between birth and discharge that was greater than 1.28. Feature selection and addition were performed to improve the accuracy of prediction at four different time points, including 0, 7, 14, and 28 days after birth. A total of 12 features with high contribution at all time points by feature importance were decided upon, and good performance was shown as an area under the receiver operating characteristic curve (AUROC) of 0.78 at 7 days. After adding weight change to the 12 features-which included sex, gestational age, birth weight, small for gestational age, maternal hypertension, respiratory distress syndrome, duration of invasive ventilation, duration of non-invasive ventilation, patent ductus arteriosus, sepsis, use of parenteral nutrition, and reach at full enteral nutrition-the AUROC at 7 days after birth was shown as 0.84. Our prediction model for PGF performed well at early detection. Its potential clinical application as a supplemental tool could be helpful for reducing PGF and improving child health.

Potential effectiveness of digital therapeutics specialized in executive functions as adjunctive treatment for clinical symptoms of attention-deficit/hyperactivity disorder: a feasibility study

Introduction

The role of digital therapeutics (DTx) in the effective management of attention deficit/hyperactivity disorder (ADHD) is beginning to gain clinical attention. Therefore, it is essential to verify their potential efficacy.

Method

We aimed to investigate the improvement in the clinical symptoms of ADHD by using DTx AimDT01 (NUROW) (AIMMED Co., Ltd., Seoul, Korea) specialized in executive functions. NUROW, which consists of Go/No-go Task- and N-Back/Updating-based training modules and a personalized adaptive algorithm system that adjusts the difficulty level according to the user's performance, was implemented on 30 Korean children with ADHD aged 6 to 12 years. The children were instructed to use the DTx for 15 min daily for 4 weeks. The Comprehensive attention test (CAT) and Childhood Behavior Checklist (CBCL) were used to assess the children at baseline and endpoint. In contrast, the ADHD-Rating Scale (ARS) and PsyToolkit were used weekly and followed up at 1 month, for any sustained effect. Repeated measures ANOVA was used to identify differences between the participants during visits, while t-tests and Wilcoxon signed-rank tests were used to identify changes before and after the DTx.

Results

We included 27 participants with ADHD in this analysis. The ARS inattention (F = 4.080, p = 0.010), hyperactivity (F = 5.998. p < 0.001), and sum (F = 5.902, p < 0.001) significantly improved. After applying NUROW, internalized (t = -3.557, p = 0.001, 95% CI = -3.682--0.985), other (Z = -3.434, p = 0.001, effect size = -0.661), and sum scores (t = -3.081, p = 0.005, 95% CI = -10.126--2.022) were significantly changed in the CBCL. The overall effect was confirmed in the ARS sustained effect analysis even after 1 month of discontinuing the DTx intervention.

Discussion

According to caregivers, the findings indicate that DTx holds potential effect as an adjunctive treatment in children with ADHD, especially in subjective clinical symptoms. Future studies will require detailed development and application targeting specific clinical domains using DTx with sufficient sample sizes.Clinical trial registration: KCT0007579.