Non-Invasive Biosensing for Healthcare Using Artificial Intelligence: A Semi-Systematic Review.

The rapid development of biosensing technologies together with the advent of deep learning has marked an era in healthcare and biomedical research where widespread devices like smartphones, smartwatches, and health-specific technologies have the potential to facilitate remote and accessible diagnosis, monitoring, and adaptive therapy in a naturalistic environment. This systematic review focuses on the impact of combining multiple biosensing techniques with deep learning algorithms and the application of these models to healthcare. We explore the key areas that researchers and engineers must consider when developing a deep learning model for biosensing: the data modality, the model architecture, and the real-world use case for the model. We also discuss key ongoing challenges and potential future directions for research in this field. We aim to provide useful insights for researchers who seek to use intelligent biosensing to advance precision healthcare.

A Perspective on Crowdsourcing and Human-in-the-Loop Workflows in Precision Health.

Modern machine learning approaches have led to performant diagnostic models for a variety of health conditions. Several machine learning approaches, such as decision trees and deep neural networks, can, in principle, approximate any function. However, this power can be considered to be both a gift and a curse, as the propensity toward overfitting is magnified when the input data are heterogeneous and high dimensional and the output class is highly nonlinear. This issue can especially plague diagnostic systems that predict behavioral and psychiatric conditions that are diagnosed with subjective criteria. An emerging solution to this issue is crowdsourcing, where crowd workers are paid to annotate complex behavioral features in return for monetary compensation or a gamified experience. These labels can then be used to derive a diagnosis, either directly or by using the labels as inputs to a diagnostic machine learning model. This viewpoint describes existing work in this emerging field and discusses ongoing challenges and opportunities with crowd-powered diagnostic systems, a nascent field of study. With the correct considerations, the addition of crowdsourcing to human-in-the-loop machine learning workflows for the prediction of complex and nuanced health conditions can accelerate screening, diagnostics, and ultimately access to care.

Personalized AI-Driven Real-Time Models to Predict Stress-Induced Blood Pressure Spikes Using Wearable Devices: Proposal for a Prospective Cohort Study.

BACKGROUND: Referred to as the "silent killer," elevated blood pressure (BP) often goes unnoticed due to the absence of apparent symptoms, resulting in cumulative harm over time. Chronic stress has been consistently linked to increased BP. Prior studies have found that elevated BP often arises due to a stressful lifestyle, although the effect of exact stressors varies drastically between individuals. The heterogeneous nature of both the stress and BP response to a multitude of lifestyle decisions can make it difficult if not impossible to pinpoint the most deleterious behaviors using the traditional mechanism of clinical interviews. OBJECTIVE: The aim of this study is to leverage machine learning (ML) algorithms for real-time predictions of stress-induced BP spikes using consumer wearable devices such as Fitbit, providing actionable insights to both patients and clinicians to improve diagnostics and enable proactive health monitoring. This study also seeks to address the significant challenges in identifying specific deleterious behaviors associated with stress-induced hypertension through the development of personalized artificial intelligence models for individual patients, departing from the conventional approach of using generalized models. METHODS: The study proposes the development of ML algorithms to analyze biosignals obtained from these wearable devices, aiming to make real-time predictions about BP spikes. Given the longitudinal nature of the data set comprising time-series data from wearables (eg, Fitbit) and corresponding time-stamped labels representing stress levels from Ecological Momentary Assessment reports, the adoption of self-supervised learning for pretraining the network and using transformer models for fine-tuning the model on a personalized prediction task is proposed. Transformer models, with their self-attention mechanisms, dynamically weigh the importance of different time steps, enabling the model to focus on relevant temporal features and dependencies, facilitating accurate prediction. RESULTS: Supported as a pilot project from the Robert C Perry Fund of the Hawaii Community Foundation, the study team has developed the core study app, CardioMate. CardioMate not only reminds participants to initiate BP readings using an Omron HeartGuide wearable monitor but also prompts them multiple times a day to report stress levels. Additionally, it collects other useful information including medications, environmental conditions, and daily interactions. Through the app's messaging system, efficient contact and interaction between users and study admins ensure smooth progress. CONCLUSIONS: Personalized ML when applied to biosignals offers the potential for real-time digital health interventions for chronic stress and its symptoms. The project's clinical use for Hawaiians with stress-induced high BP combined with its methodological innovation of personalized artificial intelligence models highlights its significance in advancing health care interventions. Through iterative refinement and optimization, the aim is to develop a personalized deep-learning framework capable of accurately predicting stress-induced BP spikes, thereby promoting individual well-being and health outcomes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/55615.

Using #ActuallyAutistic on Twitter for Precision Diagnosis of Autism Spectrum Disorder: Machine Learning Study.

BACKGROUND: The increasing use of social media platforms has given rise to an unprecedented surge in user-generated content, with millions of individuals publicly sharing their thoughts, experiences, and health-related information. Social media can serve as a useful means to study and understand public health. Twitter (subsequently rebranded as "X") is one such social media platform that has proven to be a valuable source of rich information for both the general public and health officials. We conducted the first study applying Twitter data mining to autism screening. OBJECTIVE: This study used Twitter as the primary source of data to study the behavioral characteristics and real-time emotional projections of individuals identifying with autism spectrum disorder (ASD). We aimed to improve the rigor of ASD analytics research by using the digital footprint of an individual to study the linguistic patterns of individuals with ASD. METHODS: We developed a machine learning model to distinguish individuals with autism from their neurotypical peers based on the textual patterns from their public communications on Twitter. We collected 6,515,470 tweets from users' self-identification with autism using "#ActuallyAutistic" and a separate control group to identify linguistic markers associated with ASD traits. To construct the data set, we targeted English-language tweets using the search query "#ActuallyAutistic" posted from January 1, 2014, to December 31, 2022. From these tweets, we identified unique users who used keywords such as "autism" OR "autistic" OR "neurodiverse" in their profile description and collected all the tweets from their timeline. To build the control group data set, we formulated a search query excluding the hashtag, "-#ActuallyAutistic," and collected 1000 tweets per day during the same time period. We trained a word2vec model and an attention-based, bidirectional long short-term memory model to validate the performance of per-tweet and per-profile classification models. We also illustrate the utility of the data set through common natural language processing tasks such as sentiment analysis and topic modeling. RESULTS: Our tweet classifier reached a 73% accuracy, a 0.728 area under the receiver operating characteristic curve score, and an 0.71 F1-score using word2vec representations fed into a logistic regression model, while the user profile classifier achieved an 0.78 area under the receiver operating characteristic curve score and an F1-score of 0.805 using an attention-based, bidirectional long short-term memory model. This is a promising start, demonstrating the potential for effective digital phenotyping studies and large-scale intervention using text data mined from social media. CONCLUSIONS: Textual differences in social media communications can help researchers and clinicians conduct symptomatology studies in natural settings.

Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol for a Human-in-the-Loop Machine Learning Study.

BACKGROUND: A 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. OBJECTIVE: This 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. METHODS: The 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. RESULTS: A 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. CONCLUSIONS: The 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.

Personalized Deep Learning for Substance Use in Hawaii: Protocol for a Passive Sensing and Ecological Momentary Assessment Study.

BACKGROUND: Artificial intelligence (AI)-powered digital therapies that detect methamphetamine cravings via consumer devices have the potential to reduce health care disparities by providing remote and accessible care solutions to communities with limited care solutions, such as Native Hawaiian, Filipino, and Pacific Islander communities. However, Native Hawaiian, Filipino, and Pacific Islander communities are understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other racial groups. OBJECTIVE: In this study, we aimed to understand the feasibility of continuous remote digital monitoring and ecological momentary assessments in Native Hawaiian, Filipino, and Pacific Islander communities in Hawaii by curating a novel data set of longitudinal Fitbit (Fitbit Inc) biosignals with the corresponding craving and substance use labels. We also aimed to develop personalized AI models that predict methamphetamine craving events in real time using wearable sensor data. METHODS: We will develop personalized AI and machine learning models for methamphetamine use and craving prediction in 40 individuals from Native Hawaiian, Filipino, and Pacific Islander communities by curating a novel data set of real-time Fitbit biosensor readings and the corresponding participant annotations (ie, raw self-reported substance use data) of their methamphetamine use and cravings. In the process of collecting this data set, we will gain insights into cultural and other human factors that can challenge the proper acquisition of precise annotations. With the resulting data set, we will use self-supervised learning AI approaches, which are a new family of machine learning methods that allows a neural network to be trained without labels by being optimized to make predictions about the data. The inputs to the proposed AI models are Fitbit biosensor readings, and the outputs are predictions of methamphetamine use or craving. This paradigm is gaining increased attention in AI for health care. RESULTS: To date, more than 40 individuals have expressed interest in participating in the study, and we have successfully recruited our first 5 participants with minimal logistical challenges and proper compliance. Several logistical challenges that the research team has encountered so far and the related implications are discussed. CONCLUSIONS: We expect to develop models that significantly outperform traditional supervised methods by finetuning according to the data of a participant. Such methods will enable AI solutions that work with the limited data available from Native Hawaiian, Filipino, and Pacific Islander populations and that are inherently unbiased owing to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/46493.

Localizing unmapped sequences with families to validate the Telomere-to-Telomere assembly and identify new hotspots for genetic diversity.

Although it is ubiquitous in genomics, the current human reference genome (GRCh38) is incomplete: It is missing large sections of heterochromatic sequence, and as a singular, linear reference genome, it does not represent the full spectrum of human genetic diversity. To characterize gaps in GRCh38 and human genetic diversity, we developed an algorithm for sequence location approximation using nuclear families (ASLAN) to identify the region of origin of reads that do not align to GRCh38. Using unmapped reads and variant calls from whole-genome sequences (WGSs), ASLAN uses a maximum likelihood model to identify the most likely region of the genome that a subsequence belongs to given the distribution of the subsequence in the unmapped reads and phasings of families. Validating ASLAN on synthetic data and on reads from the alternative haplotypes in the decoy genome, ASLAN localizes >90% of 100-bp sequences with >92% accuracy and ∼1 Mb of resolution. We then ran ASLAN on 100-mers from unmapped reads from WGS from more than 700 families, and compared ASLAN localizations to alignment of the 100-mers to the recently released T2T-CHM13 assembly. We found that many unmapped reads in GRCh38 originate from telomeres and centromeres that are gaps in GRCh38. ASLAN localizations are in high concordance with T2T-CHM13 alignments, except in the centromeres of the acrocentric chromosomes. Comparing ASLAN localizations and T2T-CHM13 alignments, we identified sequences missing from T2T-CHM13 or sequences with high divergence from their aligned region in T2T-CHM13, highlighting new hotspots for genetic diversity.

Identifying crossovers and shared genetic material in whole genome sequencing data from families.

Large, whole-genome sequencing (WGS) data sets containing families provide an important opportunity to identify crossovers and shared genetic material in siblings. However, the high variant calling error rates of WGS in some areas of the genome can result in spurious crossover calls, and the special inheritance status of the X Chromosome presents challenges. We have developed a hidden Markov model that addresses these issues by modeling the inheritance of variants in families in the presence of error-prone regions and inherited deletions. We call our method PhasingFamilies. We validate PhasingFamilies using the platinum genome family NA1281 (precision: 0.81; recall: 0.97), as well as simulated genomes with known crossover positions (precision: 0.93; recall: 0.92). Using 1925 quads from the Simons Simplex Collection, we found that PhasingFamilies resolves crossovers to a median resolution of 3527.5 bp. These crossovers recapitulate existing recombination rate maps, including for the X Chromosome; produce sibling pair IBD that matches expected distributions; and are validated by the haplotype estimation tool SHAPEIT. We provide an efficient, open-source implementation of PhasingFamilies that can be used to identify crossovers from family sequencing data.

Personalized Machine Learning using Passive Sensing and Ecological Momentary Assessments for Meth Users in Hawaii: A Research Protocol.

Background: Artificial intelligence (AI)-powered digital therapies which detect meth cravings delivered on consumer devices have the potential to reduce these disparities by providing remote and accessible care solutions to Native Hawaiians, Filipinos, and Pacific Islanders (NHFPI) communities with limited care solutions. However, NHFPI are fully understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other races. Objective: We seek to fulfill two research aims: (1) Understand the feasibility of continuous remote digital monitoring and ecological momentary assessments (EMAs) in NHFPI in Hawaii by curating a novel dataset of longitudinal FitBit biosignals with corresponding craving and substance use labels. (2) Develop personalized AI models which predict meth craving events in real time using wearable sensor data. Methods: We will develop personalized AI/ML (artificial intelligence/machine learning) models for meth use and craving prediction in 40 NHFPI individuals by curating a novel dataset of real-time FitBit biosensor readings and corresponding participant annotations (i.e., raw self-reported substance use data) of their meth use and cravings. In the process of collecting this dataset, we will glean insights about cultural and other human factors which can challenge the proper acquisition of precise annotations. With the resulting dataset, we will employ self-supervised learning (SSL) AI approaches, which are a new family of ML methods that allow a neural network to be trained without labels by being optimized to make predictions about the data itself. The inputs to the proposed AI models are FitBit biosensor readings and the outputs are predictions of meth use or craving. This paradigm is gaining increased attention in AI for healthcare. Conclusions: We expect to develop models which significantly outperform traditional supervised methods by fine-tuning to an individual subject's data. Such methods will enable AI solutions which work with the limited data available from NHFPI populations and which are inherently unbiased due to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse.

Parkinson Disease Recognition Using a Gamified Website: Machine Learning Development and Usability Study.

BACKGROUND: Parkinson disease (PD) affects millions globally, causing motor function impairments. Early detection is vital, and diverse data sources aid diagnosis. We focus on lower arm movements during keyboard and trackpad or touchscreen interactions, which serve as reliable indicators of PD. Previous works explore keyboard tapping and unstructured device monitoring; we attempt to further these works with structured tests taking into account 2D hand movement in addition to finger tapping. Our feasibility study uses keystroke and mouse movement data from a remotely conducted, structured, web-based test combined with self-reported PD status to create a predictive model for detecting the presence of PD. OBJECTIVE: Analysis of finger tapping speed and accuracy through keyboard input and analysis of 2D hand movement through mouse input allowed differentiation between participants with and without PD. This comparative analysis enables us to establish clear distinctions between the two groups and explore the feasibility of using motor behavior to predict the presence of the disease. METHODS: Participants were recruited via email by the Hawaii Parkinson Association (HPA) and directed to a web application for the tests. The 2023 HPA symposium was also used as a forum to recruit participants and spread information about our study. The application recorded participant demographics, including age, gender, and race, as well as PD status. We conducted a series of tests to assess finger tapping, using on-screen prompts to request key presses of constant and random keys. Response times, accuracy, and unintended movements resulting in accidental presses were recorded. Participants performed a hand movement test consisting of tracing straight and curved on-screen ribbons using a trackpad or mouse, allowing us to evaluate stability and precision of 2D hand movement. From this tracing, the test collected and stored insights concerning lower arm motor movement. RESULTS: Our formative study included 31 participants, 18 without PD and 13 with PD, and analyzed their lower limb movement data collected from keyboards and computer mice. From the data set, we extracted 28 features and evaluated their significances using an extra tree classifier predictor. A random forest model was trained using the 6 most important features identified by the predictor. These selected features provided insights into precision and movement speed derived from keyboard tapping and mouse tracing tests. This final model achieved an average F1-score of 0.7311 (SD 0.1663) and an average accuracy of 0.7429 (SD 0.1400) over 20 runs for predicting the presence of PD. CONCLUSIONS: This preliminary feasibility study suggests the possibility of using technology-based limb movement data to predict the presence of PD, demonstrating the practicality of implementing this approach in a cost-effective and accessible manner. In addition, this study demonstrates that structured mouse movement tests can be used in combination with finger tapping to detect PD.

Investigating #vapingcessation in Twitter.

Evidence suggests that an increasing number of e-cigarette users report intentions and attempts to quit vaping. Since exposure to e-cigarette-related content on social media may influence e-cigarette and other tobacco product use, including potentially e-cigarette cessation, we aimed to explore vaping cessation-related posts on Twitter by utilizing a mixed-methods approach. We collected tweets pertaining to vaping cessation for the time period between January 2022 and December 2022 using snscrape. Tweets were scraped for the following hashtags: #vapingcessation, #quitvaping, and #stopJuuling. Data were analysed using Azure Machine Learning and Nvivo 12 software. Sentiment analysis revealed that vaping cessation-related tweets typically embody positive sentiment and are mostly produced in the U.S. and Australia. Our qualitative analysis identified six emerging themes: vaping cessation support, promotion of vaping cessation, barriers and benefits to vaping cessation, personal vaping cessation, and usefulness of peer support for vaping cessation. Our findings imply that improved dissemination of evidence-based vaping cessation strategies to a broad audience through Twitter may promote vaping cessation at the population level.

A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism.

Autism spectrum disorder (autism) is a neurodevelopmental delay that affects at least 1 in 44 children. Like many neurological disorder phenotypes, the diagnostic features are observable, can be tracked over time, and can be managed or even eliminated through proper therapy and treatments. However, there are major bottlenecks in the diagnostic, therapeutic, and longitudinal tracking pipelines for autism and related neurodevelopmental delays, creating an opportunity for novel data science solutions to augment and transform existing workflows and provide increased access to services for affected families. Several efforts previously conducted by a multitude of research labs have spawned great progress toward improved digital diagnostics and digital therapies for children with autism. We review the literature on digital health methods for autism behavior quantification and beneficial therapies using data science. We describe both case-control studies and classification systems for digital phenotyping. We then discuss digital diagnostics and therapeutics that integrate machine learning models of autism-related behaviors, including the factors that must be addressed for translational use. Finally, we describe ongoing challenges and potential opportunities for the field of autism data science. Given the heterogeneous nature of autism and the complexities of the relevant behaviors, this review contains insights that are relevant to neurological behavior analysis and digital psychiatry more broadly.

Digitally Diagnosing Multiple Developmental Delays using Crowdsourcing fused with Machine Learning: A Research Protocol.

Background: Roughly 17% percent of minors in the United States aged 3 through 17 years have a diagnosis of one or more developmental or psychiatric conditions, with the true prevalence likely being higher due to underdiagnosis in rural areas and for minority populations. Unfortunately, timely diagnostic services are inaccessible to a large portion of the United States and global population due to cost, distance, and clinician availability. Digital phenotyping tools have the potential to shorten the time-to-diagnosis and to bring diagnostic services to more people by enabling accessible evaluations. While automated machine learning (ML) approaches for detection of pediatric psychiatry conditions have garnered increased research attention in recent years, existing approaches use a limited set of social features for the prediction task and focus on a single binary prediction. Objective: I propose the development of a gamified web system for data collection followed by a fusion of novel crowdsourcing algorithms with machine learning behavioral feature extraction approaches to simultaneously predict diagnoses of Autism Spectrum Disorder (ASD) and Attention-Deficit/Hyperactivity Disorder (ADHD) in a precise and specific manner. Methods: The proposed pipeline will consist of: (1) a gamified web applications to curate videos of social interactions adaptively based on needs of the diagnostic system, (2) behavioral feature extraction techniques consisting of automated ML methods and novel crowdsourcing algorithms, and (3) development of ML models which classify several conditions simultaneously and which adaptively request additional information based on uncertainties about the data. Conclusions: The prospective for high reward stems from the possibility of creating the first AI-powered tool which can identify complex social behaviors well enough to distinguish conditions with nuanced differentiators such as ASD and ADHD.

Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study.

BACKGROUND: Implementing automated facial expression recognition on mobile devices could provide an accessible diagnostic and therapeutic tool for those who struggle to recognize facial expressions, including children with developmental behavioral conditions such as autism. Despite recent advances in facial expression classifiers for children, existing models are too computationally expensive for smartphone use. OBJECTIVE: We explored several state-of-the-art facial expression classifiers designed for mobile devices, used posttraining optimization techniques for both classification performance and efficiency on a Motorola Moto G6 phone, evaluated the importance of training our classifiers on children versus adults, and evaluated the models' performance against different ethnic groups. METHODS: We collected images from 12 public data sets and used video frames crowdsourced from the GuessWhat app to train our classifiers. All images were annotated for 7 expressions: neutral, fear, happiness, sadness, surprise, anger, and disgust. We tested 3 copies for each of 5 different convolutional neural network architectures: MobileNetV3-Small 1.0x, MobileNetV2 1.0x, EfficientNetB0, MobileNetV3-Large 1.0x, and NASNetMobile. We trained the first copy on images of children, second copy on images of adults, and third copy on all data sets. We evaluated each model against the entire Child Affective Facial Expression (CAFE) set and by ethnicity. We performed weight pruning, weight clustering, and quantize-aware training when possible and profiled each model's performance on the Moto G6. RESULTS: Our best model, a MobileNetV3-Large network pretrained on ImageNet, achieved 65.78% accuracy and 65.31% F1-score on the CAFE and a 90-millisecond inference latency on a Moto G6 phone when trained on all data. This accuracy is only 1.12% lower than the current state of the art for CAFE, a model with 13.91x more parameters that was unable to run on the Moto G6 due to its size, even when fully optimized. When trained solely on children, this model achieved 60.57% accuracy and 60.29% F1-score. When trained only on adults, the model received 53.36% accuracy and 53.10% F1-score. Although the MobileNetV3-Large trained on all data sets achieved nearly a 60% F1-score across all ethnicities, the data sets for South Asian and African American children achieved lower accuracy (as much as 11.56%) and F1-score (as much as 11.25%) than other groups. CONCLUSIONS: With specialized design and optimization techniques, facial expression classifiers can become lightweight enough to run on mobile devices and achieve state-of-the-art performance. There is potentially a "data shift" phenomenon between facial expressions of children compared with adults; our classifiers performed much better when trained on children. Certain underrepresented ethnic groups (e.g., South Asian and African American) also perform significantly worse than groups such as European Caucasian despite similar data quality. Our models can be integrated into mobile health therapies to help diagnose autism spectrum disorder and provide targeted therapeutic treatment to children.

Session Introduction: TOWARDS ETHICAL BIOMEDICAL INFORMATICS: LEARNING FROM OLELO NOEAU, HAWAIIAN PROVERBS.

Innovations in human-centered biomedical informatics are often developed with the eventual goal of real-world translation. While biomedical research questions are usually answered in terms of how a method performs in a particular context, we argue that it is equally important to consider and formally evaluate the ethical implications of informatics solutions. Several new research paradigms have arisen as a result of the consideration of ethical issues, including but not limited for privacy-preserving computation and fair machine learning. In the spirit of the Pacific Symposium on Biocomputing, we discuss broad and fundamental principles of ethical biomedical informatics in terms of Olelo Noeau, or Hawaiian proverbs and poetical sayings that capture Hawaiian values. While we emphasize issues related to privacy and fairness in particular, there are a multitude of facets to ethical biomedical informatics that can benefit from a critical analysis grounded in ethics.

Machine learning models using mobile game play accurately classify children with autism.

Digitally-delivered healthcare is well suited to address current inequities in the delivery of care due to barriers of access to healthcare facilities. As the COVID-19 pandemic phases out, we have a unique opportunity to capitalize on the current familiarity with telemedicine approaches and continue to advocate for mainstream adoption of remote care delivery. In this paper, we specifically focus on the ability of GuessWhat? a smartphone-based charades-style gamified therapeutic intervention for autism spectrum disorder (ASD) to generate a signal that distinguishes children with ASD from neurotypical (NT) children. We demonstrate the feasibility of using "in-the-wild", naturalistic gameplay data to distinguish between ASD and NT by children by training a random forest classifier to discern the two classes (AU-ROC = 0.745, recall = 0.769). This performance demonstrates the potential for GuessWhat? to facilitate screening for ASD in historically difficult-to-reach communities. To further examine this potential, future work should expand the size of the training sample and interrogate differences in predictive ability by demographic.

The human "contaminome": bacterial, viral, and computational contamination in whole genome sequences from 1000 families.

The unmapped readspace of whole genome sequencing data tends to be large but is often ignored. We posit that it contains valuable signals of both human infection and contamination. Using unmapped and poorly aligned reads from whole genome sequences (WGS) of over 1000 families and nearly 5000 individuals, we present insights into common viral, bacterial, and computational contamination that plague whole genome sequencing studies. We present several notable results: (1) In addition to known contaminants such as Epstein-Barr virus and phiX, sequences from whole blood and lymphocyte cell lines contain many other contaminants, likely originating from storage, prep, and sequencing pipelines. (2) Sequencing plate and biological sample source of a sample strongly influence contamination profile. And, (3) Y-chromosome fragments not on the human reference genome commonly mismap to bacterial reference genomes. Both experiment-derived and computational contamination is prominent in next-generation sequencing data. Such contamination can compromise results from WGS as well as metagenomics studies, and standard protocols for identifying and removing contamination should be developed to ensure the fidelity of sequencing-based studies.

Causal Modeling to Mitigate Selection Bias and Unmeasured Confounding in Internet-Based Epidemiology of COVID-19: Model Development and Validation.

BACKGROUND: Selection bias and unmeasured confounding are fundamental problems in epidemiology that threaten study internal and external validity. These phenomena are particularly dangerous in internet-based public health surveillance, where traditional mitigation and adjustment methods are inapplicable, unavailable, or out of date. Recent theoretical advances in causal modeling can mitigate these threats, but these innovations have not been widely deployed in the epidemiological community. OBJECTIVE: The purpose of our paper is to demonstrate the practical utility of causal modeling to both detect unmeasured confounding and selection bias and guide model selection to minimize bias. We implemented this approach in an applied epidemiological study of the COVID-19 cumulative infection rate in the New York City (NYC) spring 2020 epidemic. METHODS: We collected primary data from Qualtrics surveys of Amazon Mechanical Turk (MTurk) crowd workers residing in New Jersey and New York State across 2 sampling periods: April 11-14 and May 8-11, 2020. The surveys queried the subjects on household health status and demographic characteristics. We constructed a set of possible causal models of household infection and survey selection mechanisms and ranked them by compatibility with the collected survey data. The most compatible causal model was then used to estimate the cumulative infection rate in each survey period. RESULTS: There were 527 and 513 responses collected for the 2 periods, respectively. Response demographics were highly skewed toward a younger age in both survey periods. Despite the extremely strong relationship between age and COVID-19 symptoms, we recovered minimally biased estimates of the cumulative infection rate using only primary data and the most compatible causal model, with a relative bias of +3.8% and -1.9% from the reported cumulative infection rate for the first and second survey periods, respectively. CONCLUSIONS: We successfully recovered accurate estimates of the cumulative infection rate from an internet-based crowdsourced sample despite considerable selection bias and unmeasured confounding in the primary data. This implementation demonstrates how simple applications of structural causal modeling can be effectively used to determine falsifiable model conditions, detect selection bias and confounding factors, and minimize estimate bias through model selection in a novel epidemiological context. As the disease and social dynamics of COVID-19 continue to evolve, public health surveillance protocols must continue to adapt; the emergence of Omicron variants and shift to at-home testing as recent challenges. Rigorous and transparent methods to develop, deploy, and diagnosis adapted surveillance protocols will be critical to their success.

Crowd annotations can approximate clinical autism impressions from short home videos with privacy protections.

Artificial Intelligence (A.I.) solutions are increasingly considered for telemedicine. For these methods to serve children and their families in home settings, it is crucial to ensure the privacy of the child and parent or caregiver. To address this challenge, we explore the potential for global image transformations to provide privacy while preserving the quality of behavioral annotations. Crowd workers have previously been shown to reliably annotate behavioral features in unstructured home videos, allowing machine learning classifiers to detect autism using the annotations as input. We evaluate this method with videos altered via pixelation, dense optical flow, and Gaussian blurring. On a balanced test set of 30 videos of children with autism and 30 neurotypical controls, we find that the visual privacy alterations do not drastically alter any individual behavioral annotation at the item level. The AUROC on the evaluation set was 90.0% ±7.5% for unaltered videos, 85.0% ±9.0% for pixelation, 85.0% ±9.0% for optical flow, and 83.3% ±9.3% for blurring, demonstrating that an aggregation of small changes across behavioral questions can collectively result in increased misdiagnosis rates. We also compare crowd answers against clinicians who provided the same annotations for the same videos as crowd workers, and we find that clinicians have higher sensitivity in their recognition of autism-related symptoms. We also find that there is a linear correlation (r = 0.75, p < 0.0001) between the mean Clinical Global Impression (CGI) score provided by professional clinicians and the corresponding score emitted by a previously validated autism classifier with crowd inputs, indicating that the classifier's output probability is a reliable estimate of the clinical impression of autism. A significant correlation is maintained with privacy alterations, indicating that crowd annotations can approximate clinician-provided autism impression from home videos in a privacy-preserved manner.

Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study.

BACKGROUND: Automated emotion classification could aid those who struggle to recognize emotions, including children with developmental behavioral conditions such as autism. However, most computer vision emotion recognition models are trained on adult emotion and therefore underperform when applied to child faces. OBJECTIVE: We designed a strategy to gamify the collection and labeling of child emotion-enriched images to boost the performance of automatic child emotion recognition models to a level closer to what will be needed for digital health care approaches. METHODS: We leveraged our prototype therapeutic smartphone game, GuessWhat, which was designed in large part for children with developmental and behavioral conditions, to gamify the secure collection of video data of children expressing a variety of emotions prompted by the game. Independently, we created a secure web interface to gamify the human labeling effort, called HollywoodSquares, tailored for use by any qualified labeler. We gathered and labeled 2155 videos, 39,968 emotion frames, and 106,001 labels on all images. With this drastically expanded pediatric emotion-centric database (>30 times larger than existing public pediatric emotion data sets), we trained a convolutional neural network (CNN) computer vision classifier of happy, sad, surprised, fearful, angry, disgust, and neutral expressions evoked by children. RESULTS: The classifier achieved a 66.9% balanced accuracy and 67.4% F1-score on the entirety of the Child Affective Facial Expression (CAFE) as well as a 79.1% balanced accuracy and 78% F1-score on CAFE Subset A, a subset containing at least 60% human agreement on emotions labels. This performance is at least 10% higher than all previously developed classifiers evaluated against CAFE, the best of which reached a 56% balanced accuracy even when combining "anger" and "disgust" into a single class. CONCLUSIONS: This work validates that mobile games designed for pediatric therapies can generate high volumes of domain-relevant data sets to train state-of-the-art classifiers to perform tasks helpful to precision health efforts.