Use of a Digital Modified Checklist for Autism in Toddlers - Revised with Follow-up to Improve Quality of Screening for Autism

A Study on the Screening of Children at Risk for Developmental Disabilities Using Facial Landmarks Derived From a Mobile-Based Application

OBJECTIVE

Early detection and intervention of developmental disabilities (DDs) are critical to improving the long-term outcomes of afflicted children. In this study, our objective was to utilize facial landmark features from mobile application to distinguish between children with DDs and typically developing (TD) children.

METHODS

The present study recruited 89 children, including 33 diagnosed with DD, and 56 TD children. The aim was to examine the effectiveness of a deep learning classification model using facial video collected from children through mobile-based application. The study participants underwent comprehensive developmental assessments, which included the child completion of the Korean Psychoeducational Profile-Revised and caregiver completing the Korean versions of Vineland Adaptive Behavior Scale, Korean version of the Childhood Autism Rating Scale, Social Responsiveness Scale, and Child Behavior Checklist. We extracted facial landmarks from recorded videos using mobile application and performed DDs classification using long short-term memory with stratified 5-fold cross-validation.

RESULTS

The classification model shows an average accuracy of 0.88 (range: 0.78-1.00), an average precision of 0.91 (range: 0.75-1.00), and an average F1-score of 0.80 (range: 0.60-1.00). Upon interpreting prediction results using SHapley Additive exPlanations (SHAP), we verified that the most crucial variable was the nodding head angle variable, with a median SHAP score of 2.6. All the top 10 contributing variables exhibited significant differences in distribution between children with DD and TD (p<0.05).

CONCLUSION

The results of this study provide evidence that facial landmarks, utilizing readily available mobile-based video data, can be used to detect DD at an early stage.

The Developmental Autism Early Screening (DAES): A Novel Test for Screening Autism Spectrum Disorder

This study was undertaken to set a novel developmental screening test for autism spectrum disorder (ASD) using the Griffiths Scales of Child Development (Griffith III) (Green et al., 2016; Stroud et al., 2016), in order to intercept the early atypical developmental patterns indicating ASD risk in the first 3 years of age. An observational and interactive ASD screener, the Developmental Autism Early Screening (DAES), was developed by detecting Griffiths III items differentiating toddlers with ASD risk from those with global developmental delay (DD) or neurotypical development. The DAES was validated with ASD-specific diagnostic instruments (ADOS-2) and the cut-off score based on sensitivity, specificity and positive predictive value that best differentiates between ASD and non-ASD children was identified. We enrolled a total sample of 297 subjects, including children at risk for ASD or DD and neurotypical children. At a cut-off score of 12.5, the DAES had a sensitivity of 93%, specificity of 98.4%, positive predictive value of 96.3% and negative predictive value of 96.9% for identifying children at risk for ASD from non-ASD participants (DD/neurotypical children). The DAES total score correlated significantly with the ADOS-2 calibrated severity scores (CSS) (R = 0.53, p < 0.001). Three ASD risk ranges were identified according to DAES total and ADOS-2 CSS: Little-to-no risk (CSS: 1-3, DAES: 1-7); Mild-to-moderate risk (CSS: 4-5, DAES: 8-14); Moderate-to-severe risk (CSS: 6-10, DAES ≥ 15). The DAES provides a direct approach based on developmental profiles to stratify risk for ASD in early childhood ensuring at risk children the most appropriate diagnostic procedures and targeted intervention.

Prevalence and nature of prior developmental and medical concerns in toddlers who screen positive for autism in primary care

LAY ABSTRACT

The American Academy of Pediatrics recommends that all children be screened for autism at their 18- and 24-month well-child visit. For children who screen positive for autism, it is unknown whether this usually represents the first time a developmental concern has been raised or if other developmental concerns typically precede a positive autism screen. Such knowledge could help guide providers in how to appropriately convey feedback regarding autism screening. This study found that, for close to 80% of children with a positive autism screen, caregivers or providers had a prior autism, language, motor, or other developmental concern documented in the electronic health record. Many also had other prior concerns frequently linked to autism, such as sleep and gastrointestinal problems, and received physical or speech therapy. On average, prior to screening children who received a positive Modified-Checklist for Autism in Toddlers had two documented concerns by at 1 year of age and three concerns by 2 years of age. These findings imply that screening for autism as a part of routine pediatric care likely takes place in the context of larger conversations regarding existing developmental concerns, allowing for a less stigmatizing discussion of autism. Framing the presence of prior concerns in the setting of a positive screen in this context may create a reaffirming space for existing caregiver concerns and a lessened emotional burden on caregivers.

Validation of the Electronic Modified Checklist for Autism in Toddlers, Revised with Follow-Up: A Nonrandomized Controlled Trial

OBJECTIVE

To examine the classification rates and screening properties, including sensitivity and specificity, of the web-based Modified Checklist for Autism in Toddler, Revised with Follow-Up (M-CHAT-R/F) compared with paper-phone administration, and to determine the extent to which electronic M-CHAT-R/F streamlines screening, increases screening fidelity, increases diagnostic evaluation participation, and decreases waiting time from screening to evaluation compared with paper-phone modality.

STUDY DESIGN

Primary-care practices in urban and suburban settings administered either the web-based or paper-phone M-CHAT-R/F using a prospective nonrandomized control design. Toddlers (n = 17 900) were screened between 2009 and 2016 at routine well-child check-ups. Toddlers who screened at risk on the M-CHAT-R/F were invited to complete diagnostic evaluations; 176 children were diagnosed with autism. The χ2, Fisher exact, and t-tests, as well as regression and screening properties, were used to compare outcome distributions, screening properties, and implementation by modality.

RESULTS

Classification rates of the initial M-CHAT-R into low, medium, and high risk were significantly different across modalities with very small effect sizes. Sensitivity and specificity were high across both modalities. For children in the medium-risk range, the web-based modality had a greater rate of predicting risk for autism after Follow-Up compared with the paper-phone modality, and the web eliminated delay between initial screen and Follow-Up. The web-based modality showed increased screening fidelity, no data loss, and similar rates of evaluation attendance and time to evaluation from Follow-Up administration.

CONCLUSIONS

The web-based M-CHAT-R/F is a valid tool for universal autism screening. Systems-level decisions should balance the increased feasibility of the electronic administration with the increase in Follow-Up accuracy provided by skilled clinician interview.

Implementation of child-centred outcome measures in routine paediatric healthcare practice: a systematic review

BACKGROUND

Person-centred outcome measures (PCOMs) are commonly used in routine adult healthcare to measure and improve outcomes, but less attention has been paid to PCOMs in children's services. The aim of this systematic review is to identify and synthesise existing evidence of the determinants, strategies, and mechanisms that influence the implementation of PCOMs into paediatric healthcare practice.

METHODS

The review was conducted and reported in accordance with PRISMA guidelines. Databased searched included CINAHL, Embase, Medline, and PsycInfo. Google scholar was also searched for grey literature on 25^th March 2022. Studies were included if the setting was a children's healthcare service, investigating the implementation or use of an outcome measure or screening tool in healthcare practice, and reported outcomes relating to use of a measure. Data were tabulated and thematically analysed through deductive coding to the constructs of the adapted-Consolidated Framework for Implementation Research (CFIR). Results were presented as a narrative synthesis, and a logic model developed.

RESULTS

We retained 69 studies, conducted across primary (n = 14), secondary (n = 13), tertiary (n = 37), and community (n = 8) healthcare settings, including both child self-report (n = 46) and parent-proxy (n = 47) measures. The most frequently reported barriers to measure implementation included staff lack of knowledge about how the measure may improve care and outcomes; the complexity of using and implementing the measure; and a lack of resources to support implementation and its continued use including funding and staff. The most frequently reported facilitators of implementation and continued use include educating and training staff and families on: how to implement and use the measure; the advantages of using PCOMs over current practice; and the benefit their use has on patient care and outcomes. The resulting logic model presents the mechanisms through which strategies can reduce the barriers to implementation and support the use of PCOMs in practice.

CONCLUSIONS

These findings can be used to support the development of context-specific implementation plans through a combination of existing strategies. This will enable the implementation of PCOMs into routine paediatric healthcare practice to empower settings to better identify and improve child-centred outcomes.

TRIAL REGISTRATION

Prospero CRD 42022330013.

Meta-analysis of the Modified Checklist for Autism in Toddlers, Revised/Follow-up for Screening

CONTEXT

The Modified Checklist for Autism in Toddlers, Revised with Follow-up (M-CHAT-R/F) is used worldwide to screen for autism spectrum disorder (ASD).

OBJECTIVE

To calculate psychometric properties of the M-CHAT-R/F for subsequent diagnosis of ASD.

DATA SOURCES

Systematic searches of Medline, Embase, SCOPUS, and Trip Pro databases from January 2014 to November 2021.

STUDY SELECTION

Studies were included if they (1) used the M-CHAT-R/F (2) applied standard scoring protocol, (3) used a diagnostic assessment for ASD, and (4) reported at least 1 psychometric property of the M-CHAT-R/F.

DATA EXTRACTION

Two independent reviewers completed screening, full-text review, data extraction, and quality assessment, following Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. A random-effects model was used to derive pooled estimates and assess for between-study heterogeneity.

RESULTS

Of 667 studies identified, 15 with 18 distinct samples from 10 countries (49 841 children) were used in the meta-analysis. Pooled positive predictive value (PPV), was 57.7% (95% confidence interval [CI] 48.6-66.8, τ2 = 0.031). PPV was higher among high-risk (75.6% [95% CI 66.0-85.2]) than low-risk samples (51.2% [95% CI 43.0-59.5]). Pooled negative predictive value was 72.5% (95% CI 62.5-82.4 τ2 = 0.031), sensitivity was 82.6% (95% CI 76.2-88.9) and specificity 45.7% (95% CI 25.0-66.4).

LIMITATIONS

Negative predictive value, sensitivity, and specificity were calculated based on small sample sizes because of limited or no evaluation of screen-negative children.

CONCLUSIONS

These results support use of the M-CHAT-R/F as a screening tool for ASD. Caregiver counseling regarding likelihood of an ASD diagnosis after positive screen should acknowledge the moderate PPV.

Evidence-Based Quality Improvement: a Scoping Review of the Literature

BACKGROUND

Quality improvement (QI) initiatives often reflect approaches based on anecdotal evidence, but it is unclear how initiatives can best incorporate scientific literature and methods into the QI process. Review of studies of QI initiatives that aim to systematically incorporate evidence review (termed evidence-based quality improvement (EBQI)) may provide a basis for further methodological development.

METHODS

In this scoping review (registration: https://osf.io/hr5bj ) of EBQI, we searched the databases PubMed, CINAHL, and SCOPUS. The review addressed three central questions: How is EBQI defined? How is evidence used to inform evidence-informed QI initiatives? What is the effectiveness of EBQI?

RESULTS

We identified 211 publications meeting inclusion criteria. In total, 170 publications explicitly used the term "EBQI." Published definitions emphasized relying on evidence throughout the QI process. We reviewed a subset of 67 evaluations of QI initiatives in primary care, including both studies that used the term "EBQI" with those that described an evidence-based initiative without using EBQI terminology. The most frequently reported EBQI components included use of evidence to identify previously tested effective QI interventions; engaging stakeholders; iterative intervention development; partnering with frontline clinicians; and data-driven evaluation of the QI intervention. Effectiveness estimates were positive but varied in size in ten studies that provided data on patient health outcomes.

CONCLUSIONS

EBQI is a promising strategy for integrating relevant prior scientific findings and methods systematically in the QI process, from the initial developmental phase of the IQ initiative through to its evaluation. Future QI researchers and practitioners can use these findings as the basis for further development of QI initiatives.

Implementing the Get SET Early Model in a Community Setting to Lower the Age of ASD Diagnosis

OBJECTIVE

The objective of this study was to implement a validated, university-based early detection program, the Get SET Early model, in a community-based setting. Get SET was developed to improve Screening, Evaluation, and Treatment referral practices. Specifically, its purpose was to lower the age of diagnosis and enable toddlers with autism spectrum disorder (ASD) to begin treatment by 36 months.

METHODS

One hundred nine pediatric health care providers were recruited to administer the Communication and Symbolic Behavior Scales Developmental Profile Infant-Toddler Checklist at 12-month, 18-month, and 24-month well-baby visits and referred toddlers whose scores indicated the need for a developmental evaluation. Licensed psychologists were trained to provide diagnostic evaluations to toddlers as young as 12 months. Mean age of diagnosis was compared with current population rates.

RESULTS

In 4 years, 45,504 screens were administered at well-baby visits, and 648 children were evaluated at least 1 time. The overall median age for ASD diagnosis was 22 months, which is significantly lower than the median age reported by the CDC (57 months). For children screened at 12 months, the age of first diagnosis was significantly lower at 15 months. Of the 350 children who completed at least 1 follow-up evaluation, 323 were diagnosed with ASD or another delay, and 239 (74%) were enrolled in a treatment program.

CONCLUSION

Toddlers with ASD were diagnosed nearly 3 years earlier than the most recent CDC report, which allowed children to start a treatment program by 36 months. Overall, Get SET Early was an effective strategy for improving the current approach to screening, evaluation, and treatment. Efforts to demonstrate sustainability are underway.

Separate scoring algorithms for specific identification priorities optimize the screening properties of the Screening Tool for Autism in Toddlers (STAT)

The Screening Tool for Autism in Toddlers (STAT) is a validated stage-2 autism spectrum disorder (ASD) screening measure that takes 20 minutes to administer and comprises 12 play-based items that are scored according to specific criteria. This study examines an expanded version (STAT-E) that includes the examiner's subjective ratings of children's social engagement (SE) and atypical behaviors (AB) in the scoring algorithm. The sample comprised 238 children who were 24-35 months old. The STAT-E assessors had limited ASD experience to mimic its use by community-based non-specialists, and were trained using a scalable web-based platform. A diagnostic evaluation was completed by clinical experts who were blind to the STAT-E results. Logistic regression, ROC curves, and classification matrices and metrics were used to determine the screening properties of STAT-E when scored using the original STAT scoring algorithm versus a new algorithm that included the SE and AB ratings. Inclusion of the SE and AB ratings improved positive risk classification appreciably, while the specificity declined. These results suggest that the STAT-E using the original STAT scoring algorithm optimizes specificity, while the STAT-E scoring algorithm with the two new ratings optimizes the positive risk classification. Using multiple scoring algorithms on the STAT may provide improved screening accuracy for diverse contexts, and a scalable web-based tutorial may be a pathway for increasing the number of community providers who can administer the STAT and contribute toward increased rates of autism screening.

Reducing Barriers to Autism Screening in Community Primary Care: A Pragmatic Trial Using Web-Based Screening

OBJECTIVE

To determine whether an intervention addressing both logistical and knowledge barriers to early screening for autism spectrum disorder (ASD) increases evidence-based screening during 18-month well-child visits and primary care providers' (PCPs') perceived self-efficacy in caring for children with ASD.

METHODS

Forty-six PCPs from 10 diverse practices across four counties in Washington State participated. PCPs attended a 2-hour training workshop on early recognition and care for toddlers with ASD and use of a REDCap-based version of the Modified Checklist for Autism in Toddlers-Revised with Follow-up (webM-CHAT-R/F) that provided automated presentation and scoring of follow-up questions. Data were collected at baseline and 6 months following each county's training window. PCPs' screening methods and rates and perceived self-efficacy regarding ASD care were measured by self-report and webM-CHAT-R/F use was measured via REDCap records.

RESULTS

At follow-up, 8 of the 10 practices were using the webM-CHAT-R/F routinely at 18-month visits. The proportion of PCPs reporting routine M-CHAT screening increased from 82% at baseline to 98% at follow-up (16% increase, 95% confidence interval [CI] 3%-28%; McNemar exact P = .02). The proportion using the M-CHAT-R/F follow-up interview questions increased from 33% to 82% (49% increase, 95% CI 30%-68%, exact McNemar test, P < .001). Significant increases in self-efficacy were found for all seven areas assessed (Ps ≤ .008).

CONCLUSIONS

This brief intervention increased PCPs' self-reported valid use of the M-CHAT-R/F at 18 months and their self-efficacy regarding ASD care. Combining educational information with a web-based ASD screen incorporating the M-CHAT-R/F follow-up questions may increase universal ASD screening with improved fidelity.

Integrating a New Online Platform in Primary Care for Early Detection, Referral, and Intervention in Autism Spectrum Disorder: The First Italian Pivotal Clinical Study

Autism spectrum disorder (ASD) is a heterogeneous condition characterized by deficits in social communication and a repetitive pattern of behavior, with recent Italian prevalence estimates of 1 in 77. Although the core behavioral features of ASD appear to emerge within the first two years of life, clinical diagnosis is often not received before the third birthday. The American Academy of Pediatrics (AAP) has recommended that primary care physicians routinely screen for ASD at the 18- and 24-month visits. In Italy, the Guidelines of the Italian National Institute for Health (ISS) recommend the Checklist for Autism in Toddlers (CHAT) as a screening tool for ASD, which compares parent responses with a semistructured observation by a healthcare provider. In the Italian National Health System, pediatricians have regular visits with all children; however, there is wide variability in following screening guidelines, and some barriers have been detected. For these reasons, other studies have highlighted the advantages of using telemedicine with the potential for enhancing ASD screening practices. The current study is an examination of the implementation of the first Italian online web-based screening tool (Web Italian Network for Autism Spectrum DisorderWIN4ASD), an innovative web app for pediatricians. We present the data obtained from the screening activity through the platform by a small group of pediatricians. The results of this study show that the implemented web-based platform appears to be an effective, efficient, and sustainable way to integrate screening services into primary care.

Psychometric Comparison of the English and Spanish Western-Hemisphere Versions of the Modified Checklist for Autism in Toddlers-Revised

OBJECTIVES

Parent-report screening tools for autism spectrum disorder (ASD) are widely used to promote early identification of children with or at risk for ASD. Most screening tools have been developed in English in the United States or United Kingdom; thus, translated versions are needed for use with culturally and linguistically diverse populations. Traditional translation methods include a forward translation, back translation, and review. However, when used in new cultural and linguistic contexts, this "forward-back" approach may have limitations, including differing psychometric properties compared with original instruments. This study presents a psychometric analysis of the forward-back translation methodology of an ASD screening tool.

METHODS

A retrospective chart review design was used to examine Modified Checklist for Autism in Toddlers-Revised (M-CHAT-R; Robins et al.) records from 2974 toddlers. Data were compared between caregivers who completed the original English M-CHAT-R and caregivers who completed its forward-back "Spanish-Western Hemisphere" translation to compare select psychometric properties of the 2 instruments.

RESULTS

Significant differences were observed between the 2 versions, including a higher overall risk score, higher initial screen-positive rate, and increased likelihood of leaving items blank among Spanish-speaking respondents.

CONCLUSION

Traditional translation methods seemed to affect select psychometric properties between translations of the M-CHAT-R. A more rigorous cultural adaptation approach may be necessary to maintain equivalence with the original instrument. Until new rigorous translations are available, it is recommended that language-specific screening tools continue to be used, along with recommended follow-up interviews, to avoid exacerbating existing health disparities.

Family Impact During the Time Between Autism Screening and Definitive Diagnosis

Over the past 10 years, identification of Autism Spectrum Disorder (ASD) risk has dramatically increased due to the wide-spread implementation of screening programs; yet, there is limited understanding about parent perceptions and experiences during the time period when risk is identified, but prior to receiving a formal diagnosis-a period that can last months to years given the long wait-lists for formal ASD evaluations. The current study aimed to examine parent perceptions of family impact (i.e., the impact their child's behaviors have on the family) between the time of risk-identification and formal diagnosis among 277 children identified as at-risk for ASD through screening positive in primary care. We aimed to compare family impact among those whose child met diagnostic criteria for ASD and those who did not. Parents of children who received a non-ASD diagnosis reported a higher baseline level of family impact (F[1, 274] = 5.82, p = .017); however, perceived difficult child behavior was a stronger predictor of family impact (t[6] = 13.11, p < .001) than later diagnostic group (t[6] = - 2.10, p = .037), and child functioning did not predict family impact (t[6] = -0.31, p = .76). These results suggest that in this population, perceived difficult child behavior is a stronger predictor of family impact than later diagnostic category and should be considered an important factor in family support.

Get SET Early to Identify and Treatment Refer Autism Spectrum Disorder at 1 Year and Discover Factors That Influence Early Diagnosis

OBJECTIVES

To examine the impact of a new approach, Get SET Early, on the rates of early autism spectrum disorder (ASD) detection and factors that influence the screen-evaluate-treat chain.

STUDY DESIGN

After attending Get SET Early training, 203 pediatricians administered 57 603 total screens using the Communication and Symbolic Behavior Scales Infant-Toddler Checklist at 12-, 18-, and 24-month well-baby examinations, and parents designated presence or absence of concern. For screen-positive toddlers, pediatricians specified if the child was being referred for evaluation, and if not, why not.

RESULTS

Collapsed across ages, toddlers were evaluated and referred for treatment at a median age of 19 months, and those screened at 12 months (59.4% of sample) by 15 months. Pediatricians referred one-third of screen-positive toddlers for evaluation, citing lack of confidence in the accuracy of screen-positive results as the primary reason for nonreferral. If a parent expressed concerns, referral probability doubled, and the rate of an ASD diagnosis increased by 37%. Of 897 toddlers evaluated, almost one-half were diagnosed as ASD, translating into an ASD prevalence of 1%.

CONCLUSIONS

The Get SET Early model was effective at detecting ASD and initiating very early treatment. Results also underscored the need for change in early identification approaches to formally operationalize and incorporate pediatrician judgment and level of parent concern into the process.

A Scalable Off-the-Shelf Framework for Measuring Patterns of Attention in Young Children and its Application in Autism Spectrum Disorder

Autism spectrum disorder (ASD) is associated with deficits in the processing of social information and difficulties in social interaction, and individuals with ASD exhibit atypical attention and gaze. Traditionally, gaze studies have relied upon precise and constrained means of monitoring attention using expensive equipment in laboratories. In this work we develop a low-cost off-the-shelf alternative for measuring attention that can be used in natural settings. The head and iris positions of 104 16-31 months children, an age range appropriate for ASD screening and diagnosis, 22 of them diagnosed with ASD, were recorded using the front facing camera in an iPad while they watched on the device screen a movie displaying dynamic stimuli, social stimuli on the left and nonsocial stimuli on the right. The head and iris position were then automatically analyzed via computer vision algorithms to detect the direction of attention. Children in the ASD group paid less attention to the movie, showed less attention to the social as compared to the nonsocial stimuli, and often fixated their attention to one side of the screen. The proposed method provides a low-cost means of monitoring attention to properly designed stimuli, demonstrating that the integration of stimuli design and automatic response analysis results in the opportunity to use off-the-shelf cameras to assess behavioral biomarkers.

Family navigation to increase evaluation for autism spectrum disorder in toddlers: Screening and Linkage to Services for Autism pragmatic randomized trial

LAY ABSTRACT

Young children with autism spectrum disorder can benefit from early detection and intervention to moderate autism spectrum disorder's effect on their development. Routine screening with standardized instruments facilitates early identification. However, many screen-positive children do not receive referrals for evaluation, complete diagnostic evaluations, or engage in services. This is especially true for children of color and those from less educated or low-income families. The Screening and Linkage to Services for Autism trial evaluated the effect of family navigation on referral and evaluation for autism spectrum disorder in screen-positive toddlers. The trial was conducted in an urban, low-income population. It was designed to test "real-world" implementation of family navigation. We randomly assigned 275 children aged 16-30 months with an initial positive autism spectrum disorder screen to receive navigation if indicated or usual care. Navigation increased the number of at-risk toddlers who were evaluated for autism spectrum disorder. It also improved the quality of autism spectrum disorder screening in primary care clinics. However, many children failed to receive indicated referrals for evaluation. Navigation did not improve referral rates. Furthermore, nearly half of families who were potentially eligible for navigation could not be contacted. Other ways of structuring the navigation program may be necessary to improve families' access to and acceptance of navigation, especially in the setting of financial, cultural, and linguistic barriers. Our trial nevertheless showed that family navigation may be an important tool for reducing systemic inequalities in the early identification and treatment of young children with autism spectrum disorder.

A Systematic Literature Review on the Application of Machine-Learning Models in Behavioral Assessment of Autism Spectrum Disorder

Autism spectrum disorder (ASD) is associated with significant social, communication, and behavioral challenges. The insufficient number of trained clinicians coupled with limited accessibility to quick and accurate diagnostic tools resulted in overlooking early symptoms of ASD in children around the world. Several studies have utilized behavioral data in developing and evaluating the performance of machine learning (ML) models toward quick and intelligent ASD assessment systems. However, despite the good evaluation metrics achieved by the ML models, there is not enough evidence on the readiness of the models for clinical use. Specifically, none of the existing studies reported the real-life application of the ML-based models. This might be related to numerous challenges associated with the data-centric techniques utilized and their misalignment with the conceptual basis upon which professionals diagnose ASD. The present work systematically reviewed recent articles on the application of ML in the behavioral assessment of ASD, and highlighted common challenges in the studies, and proposed vital considerations for real-life implementation of ML-based ASD screening and diagnostic systems. This review will serve as a guide for researchers, neuropsychiatrists, psychologists, and relevant stakeholders on the advances in ASD screening and diagnosis using ML.

Improving Autism Screening and Referrals With Electronic Support and Evaluations in Primary Care

BACKGROUND

Universal screening for autism promotes early evidence-based treatment. However, many children are not screened, and screened children are often not referred for autism evaluation.

METHODS

We implemented process changes in 3 phases: phase 1, changing the screening instrument and adding decision support; phase 2, adding automatic reminders; and phase 3, adding a referral option for autism evaluations in primary care. We analyzed the proportion of visits with autism screening at 2 intervention clinics before and after implementation of process changes versus 27 community clinics (which received only automatic reminders in phase 2) with χ2 test and interrupted time series. We evaluated changes in referral for autism evaluation by calculating the rate ratio for referral.

RESULTS

In 12 233 visits over 2 years (baseline and phased improvements), autism screening increased by 52% in intervention clinics (58.6%-88.8%; P < .001) and 21% in community clinics (43.4%-52.4%; P < .001). In phase 1, interrupted time series trend for screening in intervention clinics increased by 2% per week (95% confidence interval [CI]: 1.1% to 2.9%) and did not increase in community clinics. In phase 2, screening in the community clinics increased by 0.46% per week (95% CI: 0.03% to 0.89%). In phase 3, the intervention clinic providers referred patients for diagnostic evaluation 3.4 times more frequently (95% CI: 2.0 to 5.8) than at baseline.

CONCLUSIONS

We improved autism screening and referrals by changing the screening instrument, adding decision support, using automatic reminders, and offering autism evaluation in primary care in intervention clinics. Automatic reminders alone improved screening in community clinics.

Digital Behavioral Phenotyping Detects Atypical Pattern of Facial Expression in Toddlers with Autism

Commonly used screening tools for autism spectrum disorder (ASD) generally rely on subjective caregiver questionnaires. While behavioral observation is more objective, it is also expensive, time-consuming, and requires significant expertise to perform. As such, there remains a critical need to develop feasible, scalable, and reliable tools that can characterize ASD risk behaviors. This study assessed the utility of a tablet-based behavioral assessment for eliciting and detecting one type of risk behavior, namely, patterns of facial expression, in 104 toddlers (ASD N = 22) and evaluated whether such patterns differentiated toddlers with and without ASD. The assessment consisted of the child sitting on his/her caregiver's lap and watching brief movies shown on a smart tablet while the embedded camera recorded the child's facial expressions. Computer vision analysis (CVA) automatically detected and tracked facial landmarks, which were used to estimate head position and facial expressions (Positive, Neutral, All Other). Using CVA, specific points throughout the movies were identified that reliably differentiate between children with and without ASD based on their patterns of facial movement and expressions (area under the curves for individual movies ranging from 0.62 to 0.73). During these instances, children with ASD more frequently displayed Neutral expressions compared to children without ASD, who had more All Other expressions. The frequency of All Other expressions was driven by non-ASD children more often displaying raised eyebrows and an open mouth, characteristic of engagement/interest. Preliminary results suggest computational coding of facial movements and expressions via a tablet-based assessment can detect differences in affective expression, one of the early, core features of ASD. LAY SUMMARY: This study tested the use of a tablet in the behavioral assessment of young children with autism. Children watched a series of developmentally appropriate movies and their facial expressions were recorded using the camera embedded in the tablet. Results suggest that computational assessments of facial expressions may be useful in early detection of symptoms of autism.

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

&nbsp;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.

Primary Care Autism Screening and Later Autism Diagnosis

OBJECTIVES

To describe the proportion of children screened by the Modified Checklist for Autism in Toddlers (M-CHAT), identify characteristics associated with screen completion, and examine associations between autism spectrum disorder (ASD) screening and later ASD diagnosis.

METHODS

We examined data from children attending 18- and 24-month visits between 2013 and 2016 from 20 clinics within a health care system for evidence of screening with the M-CHAT and subsequent coding of ASD diagnosis at age >4.75 years. We interviewed providers for information about usual methods of M-CHAT scoring and ASD referral.

RESULTS

Of 36 233 toddlers, 73% were screened and 1.4% were later diagnosed with ASD. Hispanic children were less likely to be screened (adjusted prevalence ratio [APR]: 0.95, 95% confidence interval [CI]: 0.92-0.98), and family physicians were less likely to screen (APR: 0.12, 95% CI: 0.09-0.15). Compared with unscreened children, screen-positive children were more likely to be diagnosed with ASD (APR: 10.3, 95% CI: 7.6-14.1) and were diagnosed younger (38.5 vs 48.5 months, P < .001). The M-CHAT's sensitivity for ASD diagnosis was 33.1%, and the positive predictive value was 17.8%. Providers routinely omitted the M-CHAT follow-up interview and had uneven referral patterns.

CONCLUSIONS

A majority of children were screened for ASD, but disparities exist among those screened. Benefits for screen-positive children are improved detection and younger age of diagnosis. Performance of the M-CHAT can be improved in real-world health care settings by administering screens with fidelity and facilitating timely ASD evaluations for screen-positive children. Providers should continue to monitor for signs of ASD in screen-negative children.

Impact of a digital Modified Checklist for Autism in Toddlers-Revised on likelihood and age of autism diagnosis and referral for developmental evaluation

LAY ABSTRACT

This was a project in primary care for young children (1-2 years old). We tested a parent questionnaire on a tablet. This tablet questionnaire asked questions to see whether the child may have autism. We compared the paper and pencil version of the questionnaire to the tablet questionnaire. We read the medical charts for the children until they were 4 years old to see whether they ended up having autism. We found that doctors were more likely to recommend an autism evaluation when a parent used the tablet questionnaire. We think that the tablet's automatic scoring feature helped the doctors. We also think that the doctors benefited from the advice the tablet gave them.

The Acceptability and Effectiveness of Web-Based Developmental Surveillance Programs: Rapid Review

Background

Web-based developmental surveillance programs may be an innovative solution to improving the early detection of childhood developmental difficulties, especially within disadvantaged populations.

Objective

This review aimed to identify the acceptability and effectiveness of web-based developmental surveillance programs for children aged 0 to 6 years.

Methods

A total of 6 databases and gray literature were searched using a Preferred Reporting Items for Systematic Reviews and Meta-Analyses–informed protocol. Data extraction included variables related to health equity.

Results

In total, 20 studies were identified. Most papers implemented web-based versions of the Modified Checklist for Autism in Toddlers, Revised with Follow-Up screener for autism spectrum disorder or Parent Evaluation of Developmental Status screeners for broad developmental delay. Caregivers and practitioners indicated a preference for web-based screeners, primarily for user-friendliness, improved follow-up accuracy, time, and training efficiencies.

Conclusions

Although evidence is limited as to the necessity of web- versus face-to-face–based developmental screening, there are clear efficiencies in its use.

Trial Registration

PROSPERO CRD42019127894; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=127894

Screening for autism spectrum disorder in a naturalistic home setting using the systematic observation of red flags (SORF) at 18-24 months

The purpose of this study was to examine the utility of the Systematic Observation of Red Flags (SORF; Dow et al., 2016) as a level 2 screener for autism spectrum disorder (ASD) in toddlers during a naturalistic video-recorded home observation. Psychometric properties of the SORF were examined in a sample of 228 toddlers-84 with ASD, 82 with developmental delay (DD), and 62 with typical development (TD). Trained undergraduate research assistants blind to diagnosis rated 22 red flags (RF) of ASD associated with DSM-5 diagnostic criteria using a 4-point scale. The following scores were computed: a total score summing all items, domain scores summing social communication and restricted, repetitive behavior items, and number of RF counting items with scores of 2 or 3 indicating clear symptom presence. The performance of the total, domain, and RF scores and individual items were examined. A composite score was formed with six items with the best psychometric performance: poor eye gaze directed to faces, limited showing and pointing, limited coordination of nonverbal communication, less interest in people than objects, repetitive use of objects, and excessive interest in particular objects, actions, or activities. The 6-item composite provides a brief measure with optimal performance, while the RF may be instrumental for clinicians who are interested in characterizing the range of observed symptoms. The SORF shows promise as a practical alternative to currently available screening methods for implementation by nonexperts with the potential to increase feasibility and reduce common obstacles to access to care. Autism Res 2020, 13: 122-133. © The Authors. Autism Research published by International Society for Autism Research published by Wiley Periodicals, Inc. LAY SUMMARY: Research suggests that current autism spectrum disorder (ASD) screening tools are not accurate enough to use in routine screening. The Systematic Observation of Red Flags was developed as a practical option for children at high risk for ASD. It can be used with video-recorded samples of parent-child interactions in the home and by raters who are not experts in ASD. It shows promise in predicting ASD risk in toddlers to determine if a full diagnostic evaluation is necessary.

General paediatric practice in autism spectrum disorder screening in Ontario, Canada: Opportunities for improvement

Background

Screening is important for early identification of children with autism spectrum disorder (ASD), potentially leading to earlier intervention. Research has identified some barriers to early identification of ASD, however, information about ASD screening in Canadian general paediatric practice is lacking.

Objectives

The aim of the study is to better understand ASD screening practice patterns by examining the use of ASD and general developmental screening tools by general paediatricians.

Methods

The research team conducted a cross-sectional survey of general paediatricians.

Results

Two-hundred and sixty-seven paediatricians responded and 132 were eligible for the study. Ninety-three per cent of the responders used a developmental screening tool. Eighty-five per cent of the responders used an ASD screening tool when there were concerns for ASD, and 15% never used one. The most commonly used ASD screening tool was the M-CHAT. Children suspected of having ASD were referred to specialists not only to confirm the diagnosis but also to facilitate access to resources. General paediatricians were keen to incorporate formal ASD screening tools in their practice but identified the need for clearer guidelines.

Conclusion

Previous studies have shown that children at risk of ASD continue to be missed through developmental surveillance and targeted screening. Paediatricians are interested in implementing an ASD screening tool and cite brevity and forms that can be completed by parents as factors that would support the use of a screening tool. Clearer guidelines and tools to support ASD screening and access to resources are needed.

Improving Developmental Screening, Discussion, and Referral in Pediatric Practice

Objective. Although pediatricians' use of standardized screening tools for identifying developmental delays has increased, only 63% of pediatricians report performing standardized screening as recommended. The purpose of the current quality improvement project was to improve developmental monitoring, screening, and referral for developmental concerns by pediatricians. Method. Twenty-eight pediatricians completed an in-person meeting, monthly webinars, and individualized feedback from an Expert Work Group on progress across a 3-month action period. Results. Statistically significant increases were observed in rates of autism screening, discussions of screening results with families, and referral following abnormal results. There was no statistically significant change in rates of general developmental screening. Comparing self-report with record review, pediatricians overestimated the extent to which they conducted discussion and referral. Conclusions. Universal screening for all children has yet to be achieved. The current project supports that practice-based improvements can be made and delineates some of the routes to success.

Computer vision analysis captures atypical attention in toddlers with autism

To demonstrate the capability of computer vision analysis to detect atypical orienting and attention behaviors in toddlers with autism spectrum disorder. One hundered and four toddlers of 16-31 months old (mean = 22) participated in this study. Twenty-two of the toddlers had autism spectrum disorder and 82 had typical development or developmental delay. Toddlers watched video stimuli on a tablet while the built-in camera recorded their head movement. Computer vision analysis measured participants' attention and orienting in response to name calls. Reliability of the computer vision analysis algorithm was tested against a human rater. Differences in behavior were analyzed between the autism spectrum disorder group and the comparison group. Reliability between computer vision analysis and human coding for orienting to name was excellent (intra-class coefficient 0.84, 95% confidence interval 0.67-0.91). Only 8% of toddlers with autism spectrum disorder oriented to name calling on >1 trial, compared to 63% of toddlers in the comparison group (p = 0.002). Mean latency to orient was significantly longer for toddlers with autism spectrum disorder (2.02 vs 1.06 s, p = 0.04). Sensitivity for autism spectrum disorder of atypical orienting was 96% and specificity was 38%. Older toddlers with autism spectrum disorder showed less attention to the videos overall (p = 0.03). Automated coding offers a reliable, quantitative method for detecting atypical social orienting and reduced sustained attention in toddlers with autism spectrum disorder.

Providing early detection and early intervention for autism spectrum disorder in South Africa: stakeholder perspectives from the Western Cape province

We set out to examine key stakeholder perspectives on early detection and intervention for autism spectrum disorder (ASD) in South Africa. Early detection and intervention improves child and family outcomes and lessens long-term costs. We focused on stakeholders in the Western Cape province, one of the better-resourced in terms of healthcare. Eight senior management level stakeholders, two each from government's Health, Education, and Social Development, and the non-profit sector were identified using purposive sampling. In-depth interviews focused on key implementation- related themes. The National Integrated Early Childhood Development Policy was the most relevant to early detection and intervention. This policy, however, is not ASD specific. This lack of specificity is in keeping with an emerging theme: ASD was only seen within the context of other developmental disabilities, particularly by Health and Social Development. Specific ASD early detection and intervention may not currently align with Health and Social Development departmental goals. These departments are primarily responsible for identifying and providing services and financial support to young children with ASD. Increased ASD knowledge and local South African statistics on prevalence, burden and associated costs may alter this approach. At this time, ASD early intervention may be more closely aligned with Education department goals.

Automatic emotion and attention analysis of young children at home: a ResearchKit autism feasibility study

Current tools for objectively measuring young children's observed behaviors are expensive, time-consuming, and require extensive training and professional administration. The lack of scalable, reliable, and validated tools impacts access to evidence-based knowledge and limits our capacity to collect population-level data in non-clinical settings. To address this gap, we developed mobile technology to collect videos of young children while they watched movies designed to elicit autism-related behaviors and then used automatic behavioral coding of these videos to quantify children's emotions and behaviors. We present results from our iPhone study Autism & Beyond, built on ResearchKit's open-source platform. The entire study-from an e-Consent process to stimuli presentation and data collection-was conducted within an iPhone-based app available in the Apple Store. Over 1 year, 1756 families with children aged 12-72 months old participated in the study, completing 5618 caregiver-reported surveys and uploading 4441 videos recorded in the child's natural settings. Usable data were collected on 87.6% of the uploaded videos. Automatic coding identified significant differences in emotion and attention by age, sex, and autism risk status. This study demonstrates the acceptability of an app-based tool to caregivers, their willingness to upload videos of their children, the feasibility of caregiver-collected data in the home, and the application of automatic behavioral encoding to quantify emotions and attention variables that are clinically meaningful and may be refined to screen children for autism and developmental disorders outside of clinical settings. This technology has the potential to transform how we screen and monitor children's development.