Risk Assessment for Parents Who Suspect Their Child Has Autism Spectrum Disorder: Machine Learning Approach

Latest clinical frontiers related to autism diagnostic strategies

The diagnosis of autism is currently based on the developmental history, direct observation of behavior, and reported symptoms, supplemented by rating scales/interviews/structured observational evaluations-which is influenced by the clinician's knowledge and experience-with no established diagnostic biomarkers. A growing body of research has been conducted over the past decades to improve diagnostic accuracy. Here, we provide an overview of the current diagnostic assessment process as well as of recent and ongoing developments to support diagnosis in terms of genetic evaluation, telemedicine, digital technologies, use of machine learning/artificial intelligence, and research on candidate diagnostic biomarkers. Genetic testing can meaningfully contribute to the assessment process, but caution is required when interpreting negative results, and more work is needed to strengthen the transferability of genetic information into clinical practice. Digital diagnostic and machine-learning-based analyses are emerging as promising approaches, but larger and more robust studies are needed. To date, there are no available diagnostic biomarkers. Moving forward, international collaborations may help develop multimodal datasets to identify biomarkers, ensure reproducibility, and support clinical translation.

Clinical, socio-demographic, and parental correlates of early autism traits in a community cohort of toddlers

Identifying factors linked to autism traits in the general population may improve our understanding of the mechanisms underlying divergent neurodevelopment. In this study we assess whether factors increasing the likelihood of childhood autism are related to early autistic trait emergence, or if other exposures are more important. We used data from 536 toddlers from London (UK), collected at birth (gestational age at birth, sex, maternal body mass index, age, parental education, parental language, parental history of neurodevelopmental conditions) and at 18 months (parents cohabiting, measures of socio-economic deprivation, measures of maternal parenting style, and a measure of maternal depression). Autism traits were assessed using the Quantitative Checklist for Autism in Toddlers (Q-CHAT) at 18 months. A multivariable model explained 20% of Q-CHAT variance, with four individually significant variables (two measures of parenting style and two measures of socio-economic deprivation). In order to address variable collinearity we used principal component analysis, finding that a component which was positively correlated with Q-CHAT was also correlated to measures of parenting style and socio-economic deprivation. Our results show that parenting style and socio-economic deprivation correlate with the emergence of autism traits at age 18 months as measured with the Q-CHAT in a community sample.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Locating Youth Exposed to Parental Justice Involvement in the Electronic Health Record: Development of a Natural Language Processing Model

BACKGROUND

Parental justice involvement (eg, prison, jail, parole, or probation) is an unfortunately common and disruptive household adversity for many US youths, disproportionately affecting families of color and rural families. Data on this adversity has not been captured routinely in pediatric health care settings, and if it is, it is not discrete nor able to be readily analyzed for purposes of research.

OBJECTIVE

In this study, we outline our process training a state-of-the-art natural language processing model using unstructured clinician notes of one large pediatric health system to identify patients who have experienced a justice-involved parent.

METHODS

Using the electronic health record database of a large Midwestern pediatric hospital-based institution from 2011-2019, we located clinician notes (of any type and written by any type of provider) that were likely to contain such evidence of family justice involvement via a justice-keyword search (eg, prison and jail). To train and validate the model, we used a labeled data set of 7500 clinician notes identifying whether the patient was ever exposed to parental justice involvement. We calculated the precision and recall of the model and compared those rates to the keyword search.

RESULTS

The development of the machine learning model increased the precision (positive predictive value) of locating children affected by parental justice involvement in the electronic health record from 61% (a simple keyword search) to 92%.

CONCLUSIONS

The use of machine learning may be a feasible approach to addressing the gaps in our understanding of the health and health services of underrepresented youth who encounter childhood adversities not routinely captured-particularly for children of justice-involved parents.

Application of Artificial Intelligence in Community-Based Primary Health Care: Systematic Scoping Review and Critical Appraisal

BACKGROUND

Research on the integration of artificial intelligence (AI) into community-based primary health care (CBPHC) has highlighted several advantages and disadvantages in practice regarding, for example, facilitating diagnosis and disease management, as well as doubts concerning the unintended harmful effects of this integration. However, there is a lack of evidence about a comprehensive knowledge synthesis that could shed light on AI systems tested or implemented in CBPHC.

OBJECTIVE

We intended to identify and evaluate published studies that have tested or implemented AI in CBPHC settings.

METHODS

We conducted a systematic scoping review informed by an earlier study and the Joanna Briggs Institute (JBI) scoping review framework and reported the findings according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analysis-Scoping Reviews) reporting guidelines. An information specialist performed a comprehensive search from the date of inception until February 2020, in seven bibliographic databases: Cochrane Library, MEDLINE, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), ScienceDirect, and IEEE Xplore. The selected studies considered all populations who provide and receive care in CBPHC settings, AI interventions that had been implemented, tested, or both, and assessed outcomes related to patients, health care providers, or CBPHC systems. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Two authors independently screened the titles and abstracts of the identified records, read the selected full texts, and extracted data from the included studies using a validated extraction form. Disagreements were resolved by consensus, and if this was not possible, the opinion of a third reviewer was sought. A third reviewer also validated all the extracted data.

RESULTS

We retrieved 22,113 documents. After the removal of duplicates, 16,870 documents were screened, and 90 peer-reviewed publications met our inclusion criteria. Machine learning (ML) (41/90, 45%), natural language processing (NLP) (24/90, 27%), and expert systems (17/90, 19%) were the most commonly studied AI interventions. These were primarily implemented for diagnosis, detection, or surveillance purposes. Neural networks (ie, convolutional neural networks and abductive networks) demonstrated the highest accuracy, considering the given database for the given clinical task. The risk of bias in diagnosis or prognosis studies was the lowest in the participant category (4/49, 4%) and the highest in the outcome category (22/49, 45%).

CONCLUSIONS

We observed variabilities in reporting the participants, types of AI methods, analyses, and outcomes, and highlighted the large gap in the effective development and implementation of AI in CBPHC. Further studies are needed to efficiently guide the development and implementation of AI interventions in CBPHC settings.

Retracted: Diagnostic Classification and Prognostic Prediction Using Common Genetic Variants in Autism Spectrum Disorder: Genotype-Based Deep Learning

BACKGROUND

In the United States, about 3 million people have autism spectrum disorder (ASD), and around 1 out of 59 children are diagnosed with ASD. People with ASD have characteristic social communication deficits and repetitive behaviors. The causes of this disorder remain unknown; however, in up to 25% of cases, a genetic cause can be identified. Detecting ASD as early as possible is desirable because early detection of ASD enables timely interventions in children with ASD. Identification of ASD based on objective pathogenic mutation screening is the major first step toward early intervention and effective treatment of affected children.

OBJECTIVE

Recent investigation interrogated genomics data for detecting and treating autism disorders, in addition to the conventional clinical interview as a diagnostic test. Since deep neural networks perform better than shallow machine learning models on complex and high-dimensional data, in this study, we sought to apply deep learning to genetic data obtained across thousands of simplex families at risk for ASD to identify contributory mutations and to create an advanced diagnostic classifier for autism screening.

METHODS

After preprocessing the genomics data from the Simons Simplex Collection, we extracted top ranking common variants that may be protective or pathogenic for autism based on a chi-square test. A convolutional neural network-based diagnostic classifier was then designed using the identified significant common variants to predict autism. The performance was then compared with shallow machine learning-based classifiers and randomly selected common variants.

RESULTS

The selected contributory common variants were significantly enriched in chromosome X while chromosome Y was also discriminatory in determining the identification of autistic individuals from nonautistic individuals. The ARSD, MAGEB16, and MXRA5 genes had the largest effect in the contributory variants. Thus, screening algorithms were adapted to include these common variants. The deep learning model yielded an area under the receiver operating characteristic curve of 0.955 and an accuracy of 88% for identifying autistic individuals from nonautistic individuals. Our classifier demonstrated a considerable improvement of ~13% in terms of classification accuracy compared to standard autism screening tools.

CONCLUSIONS

Common variants are informative for autism identification. Our findings also suggest that the deep learning process is a reliable method for distinguishing the diseased group from the control group based on the common variants of autism.

A systematic review of technological approaches for autism spectrum disorder assessment in children: Implications for the COVID-19 pandemic

BACKGROUND

Screening and diagnostic assessments tools for autism spectrum disorder (ASD) are important to administer during childhood to facilitate timely entry into intervention services that can promote developmental outcomes across the lifespan. However, assessment services are not always readily available to families, as they require significant time and resources. Currently, in-person screening and diagnostic assessments for ASD are limited due to the COVID-19 pandemic and will continue to be a concern for situations that limit in-person contact. Thus, it is important to expand the modalities in which child assessments are provided, including the use of technology.

AIMS

This systematic review aims to identify technologies that screen or assess for ASD in 0-12 year-old children, summarizing the current state of the field and suggesting future directions.

METHODS

An electronic database search was conducted to gather relevant articles to synthesize for this review.

OUTCOMES AND RESULTS

16 studies reported use of novel technology to assess children suspected of ASD.

CONCLUSIONS AND IMPLICATIONS

Results strongly supported live-video evaluations, video observations, and online or phone methods, but there is a need for research targeting the feasibility of these methods as it applies to the stay-at-home orders required by the pandemic, and other situations that limit clients from seeing providers in-person.

Information and Communication Technologies to Support Early Screening of Autism Spectrum Disorder: A Systematic Review

 The aim of this systematic review is to identify recent digital technologies used to detect early signs of autism spectrum disorder (ASD) in preschool children (i.e., up to six years of age). A systematic literature search was performed for English language articles and conference papers indexed in Pubmed, PsycInfo, ERIC, CINAHL, WoS, IEEE, and ACM digital libraries up until January 2020. A follow-up search was conducted to cover the literature published until December 2020 for the usefulness and interest in this area of research during the Covid-19 emergency. In total, 2427 articles were initially retrieved from databases search. Additional 481 articles were retrieved from follow-up search. Finally, 28 articles met the inclusion criteria and were included in the review. The studies included involved four main interface modalities: Natural User Interface (e.g., eye trackers), PC or mobile, Wearable, and Robotics. Most of the papers included (n = 20) involved the use of Level 1 screening tools. Notwithstanding the variability of the solutions identified, psychometric information points to considering available technologies as promising supports in clinical practice to detect early sign of ASD in young children. Further research is needed to understand the acceptability and increase use rates of technology-based screenings in clinical settings.&nbsp.

Early Detection and Diagnosis of Autism Spectrum Disorder: Why Is It So Difficult?

Autism spectrum disorder (ASD) affects approximately 2% of children in the United States (US). Therapeutic interventions are most effective if applied early, yet diagnosis often remains delayed, partly because the diagnosis is based on identifying abnormal behaviors that may not emerge until the disorder is well established. Universal screening has been recommended by the America Academy of Pediatrics at 18 and 24 months yet studies show low compliance by pediatricians and the US Preventive Services Task Force does not support universal screening. To better understand the limitations of universal screening this article looks at the performance of screening tests given the prevalence of ASD. Specifically, although the sensitivity and specificity of the Modified Checklist for Autism in Toddlers, Revised with Follow-up, the de facto screening tool, exceeds 90%, the relatively low prevalence of ASD in the general population (∼2%) results in a positive predictive value of about 33%, resulting in only 1 of 3 children identified by the Modified Checklist for Autism in Toddlers, Revised with Follow-up actually having ASD. To mitigate this issue, the America Academy of Pediatrics has recently recommended the use of a Level 2 screener after failing a Level 1 screener, before referring children on for a full comprehensive evaluation for ASD. In this way, a series of screening tools are used to enrich the population of children referred for further evaluation so fewer without an ASD diagnosis are evaluated. We have developed a program to train pediatricians to utilize these instruments as well as learn to diagnose ASD so children can effectively be referred for appropriate services at the front lines. Given the current burden on the medical system with the diagnosis and evaluation of children with ASD, it is important to create efficient systems for screening children which can best identify those most likely to have ASD. Developing methods to identify those children most at risk for developing ASD, either through consideration of medical or family history or through the use of biomarkers, may be helpful in identifying the children that require increased surveillance and those that do not need screening.

Lymelight: forecasting Lyme disease risk using web search data

Lyme disease is the most common tick-borne disease in the Northern Hemisphere. Existing estimates of Lyme disease spread are delayed a year or more. We introduce Lymelight-a new method for monitoring the incidence of Lyme disease in real-time. We use a machine-learned classifier of web search sessions to estimate the number of individuals who search for possible Lyme disease symptoms in a given geographical area for two years, 2014 and 2015. We evaluate Lymelight using the official case count data from CDC and find a 92% correlation (p < 0.001) at county level. Importantly, using web search data allows us not only to assess the incidence of the disease, but also to examine the appropriateness of treatments subsequently searched for by the users. Public health implications of our work include monitoring the spread of vector-borne diseases in a timely and scalable manner, complementing existing approaches through real-time detection, which can enable more timely interventions. Our analysis of treatment searches may also help reduce misdiagnosis of the disease.

Study protocol for an evaluation of ASDetect - a Mobile application for the early detection of autism

Background

Autism Spectrum Conditions (ASC) can be reliably diagnosed by 24 months of age. However, despite the well-known benefits of early intervention, there is still a research-practice gap in the timely identification of ASC, particularly in low-resourced settings. The Social Attention and Communication Surveillance (SACS) tool, which assesses behavioural markers of autism between 12 to 24 months of age, has been implemented in Maternal and Child Health (MCH) settings, with excellent psychometric properties. ASDetect is a free mobile application based on the SACS, which is designed to meet the need for an effective, evidence-based tool for parents, to learn about children’s early social-communication development and assess their child’s ‘likelihood’ for ASC.

Study aims

The primary aim of this study is to evaluate the psychometric properties of ASDetect in the early detection of children with ASC. A secondary aim is to assess ASDetect’s acceptability and parental user experience with the application.

Methods

Families are recruited to download the application and participate in the study via social media, health professionals (e.g., MCH nurses, paediatricians) and word of mouth. All participating caregivers complete a demographic questionnaire, survey regarding their user experience, and the Social Responsiveness Scale-2 (SRS-2), an autism screening questionnaire; they are also invited to participate in focus groups. Children identified at ‘high likelihood’ for ASC based on the ASDetect results, the SRS-2 or parental and/or professional concerns undergo a formal, gold-standard, diagnostic assessment. Receiver Operating Characteristic analyses will be used to assess psychometric properties of ASDetect. Thematic analyses will be used to explore themes arising in the focus groups to provide insights regarding user experiences with the app. Multiple regression analyses will be carried out to determine the extent to which demographic factors, parental stress and beliefs on health surveillance and child results on ASDetect are associated with the parental user-experience of the application.

Discussion

With a strong evidence-base and global access, ASDetect has the potential to empower parents by providing them with knowledge of their child’s social-communication development, validating and reassuring any parental concerns, and supporting them in communicating with other health professionals, ultimately enhancing child and family outcomes and well-being.

Validity of Online Screening for Autism: Crowdsourcing Study Comparing Paid and Unpaid Diagnostic Tasks

BACKGROUND

Obtaining a diagnosis of neuropsychiatric disorders such as autism requires long waiting times that can exceed a year and can be prohibitively expensive. Crowdsourcing approaches may provide a scalable alternative that can accelerate general access to care and permit underserved populations to obtain an accurate diagnosis.

OBJECTIVE

We aimed to perform a series of studies to explore whether paid crowd workers on Amazon Mechanical Turk (AMT) and citizen crowd workers on a public website shared on social media can provide accurate online detection of autism, conducted via crowdsourced ratings of short home video clips.

METHODS

Three online studies were performed: (1) a paid crowdsourcing task on AMT (N=54) where crowd workers were asked to classify 10 short video clips of children as "Autism" or "Not autism," (2) a more complex paid crowdsourcing task (N=27) with only those raters who correctly rated ≥8 of the 10 videos during the first study, and (3) a public unpaid study (N=115) identical to the first study.

RESULTS

For Study 1, the mean score of the participants who completed all questions was 7.50/10 (SD 1.46). When only analyzing the workers who scored ≥8/10 (n=27/54), there was a weak negative correlation between the time spent rating the videos and the sensitivity (ρ=-0.44, P=.02). For Study 2, the mean score of the participants rating new videos was 6.76/10 (SD 0.59). The average deviation between the crowdsourced answers and gold standard ratings provided by two expert clinical research coordinators was 0.56, with an SD of 0.51 (maximum possible SD is 3). All paid crowd workers who scored 8/10 in Study 1 either expressed enjoyment in performing the task in Study 2 or provided no negative comments. For Study 3, the mean score of the participants who completed all questions was 6.67/10 (SD 1.61). There were weak correlations between age and score (r=0.22, P=.014), age and sensitivity (r=-0.19, P=.04), number of family members with autism and sensitivity (r=-0.195, P=.04), and number of family members with autism and precision (r=-0.203, P=.03). A two-tailed t test between the scores of the paid workers in Study 1 and the unpaid workers in Study 3 showed a significant difference (P<.001).

CONCLUSIONS

Many paid crowd workers on AMT enjoyed answering screening questions from videos, suggesting higher intrinsic motivation to make quality assessments. Paid crowdsourcing provides promising screening assessments of pediatric autism with an average deviation <20% from professional gold standard raters, which is potentially a clinically informative estimate for parents. Parents of children with autism likely overfit their intuition to their own affected child. This work provides preliminary demographic data on raters who may have higher ability to recognize and measure features of autism across its wide range of phenotypic manifestations.

Neuroinflammation in preterm babies and autism spectrum disorders

Genetic anomalies have a role in autism spectrum disorders (ASD). Each genetic factor is responsible for a small fraction of cases. Environment factors, like preterm delivery, have an important role in ASD. Preterm infants have a 10-fold higher risk of developing ASD. Preterm birth is often associated with maternal/fetal inflammation, leading to a fetal/neonatal inflammatory syndrome. There are demonstrated experimental links between fetal inflammation and the later development of behavioral symptoms consistent with ASD. Preterm infants have deficits in connectivity. Most ASD genes encode synaptic proteins, suggesting that ASD are connectivity pathologies. Microglia are essential for normal synaptogenesis. Microglia are diverted from homeostatic functions towards inflammatory phenotypes during perinatal inflammation, impairing synaptogenesis. Preterm infants with ASD have a different phenotype from term born peers. Our original hypothesis is that exposure to inflammation in preterm infants, combined with at risk genetic background, deregulates brain development leading to ASD.