Search for: All records

The development of digital instruments for mental health monitoring using biosensor data from wearable devices can enable remote, longitudinal, and objective quantitative benchmarks. To survey developments and trends in this field, we conducted a systematic review of artificial intelligence (AI) models using data from wearable biosensors to predict mental health conditions and symptoms. Following PRISMA guidelines, we identified 48 studies using a variety of wearable and smartphone biosensors including heart rate, heart rate variability (HRV), electrodermal activity/galvanic skin response (EDA/GSR), and digital proxies for biosignals such as accelerometry, location, audio, and usage metadata. We observed several technical and methodological challenges across studies in this field, including lack of ecological validity, data heterogeneity, small sample sizes, and battery drainage issues. We outline several corresponding opportunities for advancement in the field of AI-driven biosensing for mental health. 

ABSTRACT Early identification and intervention often leads to improved life outcomes for individuals with Autism Spectrum Disorder (ASD). However, traditional diagnostic methods are time-consuming, frequently delaying treatment. This study examines the application of machine learning (ML) techniques to 10-question Quantitative Checklist for Autism in Toddlers (QCHAT-10) datasets, aiming to evaluate the predictive value of questionnaire features and overall accuracy metrics across different cultures. We trained models using three distinct datasets from three different countries: Poland, New Zealand, and Saudi Arabia. The New Zealand and Saudi Arabian-trained models were both tested on the Polish dataset, which consisted of diagnostic class labels derived from clinical diagnostic processes. The Decision Tree, Random Forest, and XGBoost models were evaluated, with XGBoost consistently performing best. Feature importance rankings revealed little consistency across models; however, Recursive Feature Elimination (RFE) to select the models with the four most predictive features retained three common features. Both models performed similarly on the Polish test dataset with clinical diagnostic labels, with the New Zealand models with all 13 features achieving an AUROC of 0.94 ± 0.06, and the Saudi Model having an AUROC of 93% ± 6. This compared favorably to the cross-validation analysis of a Polish-trained model, which had an AUROC of 94% ± 5, suggesting that answers to the QCHAT-10 can be predictive of an official autism diagnosis, even across cultures. The New Zealand model with four features had an AUROC of 85% ± 13, and the Saudi model had a similar result of 87% ± 11. These results were somewhat lower than the Polish cross-validation AUROC of 91% ± 5. Adjusting probability thresholds improved sensitivity in some models, which is crucial for screening tools. However, this threshold adjustment often resulted in low levels of specificity during the final testing phase. Our findings suggest that these screening tools may generalize well across cultures; however, more research is needed regarding differences in feature importance for different populations. 

Substance use disorders affect 17.3% of Americans. Digital health solutions that use machine learning to detect substance use from wearable biosignal data can eventually pave the way for real-time digital interventions. However, difficulties in addressing severe between-subject data heterogeneity have hampered the adaptation of machine learning approaches for substance use detection, necessitating more robust technological solutions. We tested the utility of personalized machine learning using participant-specific convolutional neural networks (CNNs) enhanced with self-supervised learning (SSL) to detect drug use. In a pilot feasibility study, we collected data from 9 participants using Fitbit Charge 5 devices, supplemented by ecological momentary assessments to collect real-time labels of substance use. We implemented a baseline 1D-CNN model with traditional supervised learning and an experimental SSL-enhanced model to improve individualized feature extraction under limited label conditions. Results: Among the 9 participants, we achieved an average area under the receiver operating characteristic curve score across participants of 0.695 for the supervised CNNs and 0.729 for the SSL models. Strategic selection of an optimal threshold enabled us to optimize either sensitivity or specificity while maintaining reasonable performance for the other metric. Conclusion: These findings suggest that Fitbit data have the potential to enhance substance use monitoring systems. However, the small sample size in this study limits its generalizability to diverse populations, so we call for future research that explores SSL-powered personalization at a larger scale. 

Background: Machine learning models often use passively recorded sensor data streams as inputs to train machine learning models that predict outcomes captured through ecological momentary assessments (EMA). Despite the growth of mobile data collection, challenges in obtaining proper authorization to send notifications, receive background events, and perform background tasks persist. Objective: We investigated challenges faced by mobile sensing apps in real-world settings in order to develop design guidelines. For active data, we compared 2 prompting strategies: setup prompting, where the app requests authorization during its initial run, and contextual prompting, where authorization is requested when an event or notification occurs. Additionally, we evaluated 2 passive data collection paradigms: collection during scheduled background tasks and persistent reminders that trigger passive data collection. We investigated the following research questions (RQs): (RQ1) how do setup prompting and contextual prompting affect scheduled notification delivery and the response rate of notification-initiated EMA? (RQ2) Which authorization paradigm, setup or contextual prompting, is more successful in leading users to grant authorization to receive background events? and (RQ3) Which polling-based method, persistent reminders or scheduled background tasks, completes more background sessions?. Methods: We developed mobile sensing apps for iOS and Android devices and tested them through a 30-day user study asking college students (n=145) about their stress levels. Participants responded to a daily EMA question to test active data collection. The sensing apps collected background location events, polled for passive data with persistent reminders, and scheduled background tasks to test passive data collection.Results: For RQ1, setup and contextual prompting yielded no significant difference (ANOVA F1,144=0.0227; P=.88) in EMA compliance, with an average of 23.4 (SD 7.36) out of 30 assessments completed. However, qualitative analysis revealed that contextual prompting on iOS devices resulted in inconsistent notification deliveries. For RQ2, contextual prompting for background events was 55.5% (χ21=4.4; P=.04) more effective in gaining authorization. For RQ3, users demonstrated resistance to installing the persistent reminder, but when installed, the persistent reminder performed 226.5% more background sessions than traditional background tasks. Conclusions: We developed design guidelines for improving mobile sensing on consumer mobile devices based on our qualitative and quantitative results. Our qualitative results demonstrated that contextual prompts on iOS devices resulted in inconsistent notification deliveries, unlike setup prompting on Android devices. We therefore recommend using setup prompting for EMA when possible. We found that contextual prompting is more efficient for authorizing background events. We therefore recommend using contextual prompting for passive sensing. Finally, we conclude that developing a persistent reminder and requiring participants to install it provides an additional way to poll for sensor and user data and could improve data collection to support adaptive interventions powered by machine learning. 

BackgroundA considerable number of minors in the United States are diagnosed with developmental or psychiatric conditions, potentially influenced by underdiagnosis factors such as cost, distance, and clinician availability. Despite the potential of digital phenotyping tools with machine learning (ML) approaches to expedite diagnoses and enhance diagnostic services for pediatric psychiatric conditions, existing methods face limitations because they use a limited set of social features for prediction tasks and focus on a single binary prediction, resulting in uncertain accuracies. ObjectiveThis study aims to propose the development of a gamified web system for data collection, followed by a fusion of novel crowdsourcing algorithms with ML behavioral feature extraction approaches to simultaneously predict diagnoses of autism spectrum disorder and attention-deficit/hyperactivity disorder in a precise and specific manner. MethodsThe proposed pipeline will consist of (1) gamified web applications to curate videos of social interactions adaptively based on the needs of the diagnostic system, (2) behavioral feature extraction techniques consisting of automated ML methods and novel crowdsourcing algorithms, and (3) the development of ML models that classify several conditions simultaneously and that adaptively request additional information based on uncertainties about the data. ResultsA preliminary version of the web interface has been implemented, and a prior feature selection method has highlighted a core set of behavioral features that can be targeted through the proposed gamified approach. ConclusionsThe prospect for high reward stems from the possibility of creating the first artificial intelligence–powered tool that can identify complex social behaviors well enough to distinguish conditions with nuanced differentiators such as autism spectrum disorder and attention-deficit/hyperactivity disorder. International Registered Report Identifier (IRRID)PRR1-10.2196/52205 

Abstract Background Many children with autism cannot receive timely in-person diagnosis and therapy, especially in situations where access is limited by geography, socioeconomics, or global health concerns such as the current COVD-19 pandemic. Mobile solutions that work outside of traditional clinical environments can safeguard against gaps in access to quality care. Objective The aim of the study is to examine the engagement level and therapeutic feasibility of a mobile game platform for children with autism. Methods We designed a mobile application, GuessWhat, which, in its current form, delivers game-based therapy to children aged 3 to 12 in home settings through a smartphone. The phone, held by a caregiver on their forehead, displays one of a range of appropriate and therapeutically relevant prompts (e.g., a surprised face) that the child must recognize and mimic sufficiently to allow the caregiver to guess what is being imitated and proceed to the next prompt. Each game runs for 90 seconds to create a robust social exchange between the child and the caregiver. Results We examined the therapeutic feasibility of GuessWhat in 72 children (75% male, average age 8 years 2 months) with autism who were asked to play the game for three 90-second sessions per day, 3 days per week, for a total of 4 weeks. The group showed significant improvements in Social Responsiveness Score-2 (SRS-2) total (3.97, p <0.001) and Vineland Adaptive Behavior Scales-II (VABS-II) socialization standard (5.27, p = 0.002) scores. Conclusion The results support that the GuessWhat mobile game is a viable approach for efficacious treatment of autism and further support the possibility that the game can be used in natural settings to increase access to treatment when barriers to care exist. 

Background Autism spectrum disorder (ASD) is a developmental disorder characterized by deficits in social communication and interaction, and restricted and repetitive behaviors and interests. The incidence of ASD has increased in recent years; it is now estimated that approximately 1 in 40 children in the United States are affected. Due in part to increasing prevalence, access to treatment has become constrained. Hope lies in mobile solutions that provide therapy through artificial intelligence (AI) approaches, including facial and emotion detection AI models developed by mainstream cloud providers, available directly to consumers. However, these solutions may not be sufficiently trained for use in pediatric populations. Objective Emotion classifiers available off-the-shelf to the general public through Microsoft, Amazon, Google, and Sighthound are well-suited to the pediatric population, and could be used for developing mobile therapies targeting aspects of social communication and interaction, perhaps accelerating innovation in this space. This study aimed to test these classifiers directly with image data from children with parent-reported ASD recruited through crowdsourcing. Methods We used a mobile game called Guess What? that challenges a child to act out a series of prompts displayed on the screen of the smartphone held on the forehead of his or her care provider. The game is intended to be a fun and engaging way for the child and parent to interact socially, for example, the parent attempting to guess what emotion the child is acting out (eg, surprised, scared, or disgusted). During a 90-second game session, as many as 50 prompts are shown while the child acts, and the video records the actions and expressions of the child. Due in part to the fun nature of the game, it is a viable way to remotely engage pediatric populations, including the autism population through crowdsourcing. We recruited 21 children with ASD to play the game and gathered 2602 emotive frames following their game sessions. These data were used to evaluate the accuracy and performance of four state-of-the-art facial emotion classifiers to develop an understanding of the feasibility of these platforms for pediatric research. Results All classifiers performed poorly for every evaluated emotion except happy. None of the classifiers correctly labeled over 60.18% (1566/2602) of the evaluated frames. Moreover, none of the classifiers correctly identified more than 11% (6/51) of the angry frames and 14% (10/69) of the disgust frames. Conclusions The findings suggest that commercial emotion classifiers may be insufficiently trained for use in digital approaches to autism treatment and treatment tracking. Secure, privacy-preserving methods to increase labeled training data are needed to boost the models’ performance before they can be used in AI-enabled approaches to social therapy of the kind that is common in autism treatments.