Dataset Information

A Machine Learning Strategy for Autism Screening in Toddlers.

ABSTRACT: OBJECTIVE:Autism spectrum disorder (ASD) screening can improve prognosis via early diagnosis and intervention, but lack of time and training can deter pediatric screening. The Modified Checklist for Autism in Toddlers, Revised (M-CHAT-R) is a widely used screener but requires follow-up questions and error-prone human scoring and interpretation. We consider an automated machine learning (ML) method for overcoming barriers to ASD screening, specifically using the feedforward neural network (fNN). METHODS:The fNN technique was applied using archival M-CHAT-R data of 14,995 toddlers (age 16-30 months, 46.51% male). The 20 M-CHAT-R items were inputs, and ASD diagnosis after follow-up and diagnostic evaluation (i.e., ASD or not ASD) was the output. The sample was divided into subgroups by race (i.e., white and black), sex (i.e., boys and girls), and maternal education (i.e., below and above 15 years of education completed) to examine subgroup differences. Each subgroup was evaluated for best-performing fNN models. RESULTS:For the total sample, best results yielded 99.72% correct classification using 18 items. Best results yielded 99.92% correct classification using 14 items for white toddlers and 99.79% correct classification using 18 items for black toddlers. In boys, best results yielded 99.64% correct classification using 18 items, whereas best results yielded 99.95% correct classification using 18 items in girls. For the case when maternal education is 15 years or less (i.e., associate degree and below), best results were 99.75% correct classification when using 16 items. Results were essentially the same when maternal education was 16 years or more (i.e., above associate degree); that is, 99.70% correct classification was obtained using 16 items. CONCLUSION:The ML method was comparable to the M-CHAT-R with follow-up items in accuracy of ASD diagnosis while using fewer items. Therefore, ML may be a beneficial tool in implementing automatic, efficient scoring that negates the need for labor-intensive follow-up and circumvents human error, providing an advantage over previous screening methods.

SUBMITTER: Achenie LEK

PROVIDER: S-EPMC6579619 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Strategy for Autism Screening in Toddlers.

Achenie Luke E K LEK Scarpa Angela A Factor Reina S RS Wang Tao T Robins Diana L DL McCrickard D Scott DS

Journal of developmental and behavioral pediatrics : JDBP 20190601 5

<h4>Objective</h4>Autism spectrum disorder (ASD) screening can improve prognosis via early diagnosis and intervention, but lack of time and training can deter pediatric screening. The Modified Checklist for Autism in Toddlers, Revised (M-CHAT-R) is a widely used screener but requires follow-up questions and error-prone human scoring and interpretation. We consider an automated machine learning (ML) method for overcoming barriers to ASD screening, specifically using the feedforward neural network ...[more]

PMID: 30985384

Similar Datasets

Project description:ObjectiveThis is a prospective population screening study for autism in toddlers aged 18-30 months old using the Quantitative Checklist for Autism in Toddlers (Q-CHAT), with follow-up at age 4.DesignObservational study.SettingLuton, Bedfordshire and Cambridgeshire in the UK.Participants13 070 toddlers registered on the Child Health Surveillance Database between March 2008 and April 2009, with follow-up at age 4; 3770 (29%) were screened for autism at 18-30 months using the Q-CHAT and the Childhood Autism Spectrum Test (CAST) at follow-up at age 4.InterventionsA stratified sample across the Q-CHAT score distribution was invited for diagnostic assessment (phase 1). The 4-year follow-up included the CAST and the Checklist for Referral (CFR). All with CAST ≥15, phase 1 diagnostic assessment or with developmental concerns on the CFR were invited for diagnostic assessment (phase 2). Standardised diagnostic assessment at both time-points was conducted to establish the test accuracy of the Q-CHAT.Main outcome measuresConsensus diagnostic outcome at phase 1 and phase 2.ResultsAt phase 1, 3770 Q-CHATs were returned (29% response) and 121 undertook diagnostic assessment, of whom 11 met the criteria for autism. All 11 screened positive on the Q-CHAT. The positive predictive value (PPV) at a cut-point of 39 was 17% (95% CI 8% to 31%). At phase 2, 2005 of 3472 CASTs and CFRs were returned (58% response). 159 underwent diagnostic assessment, including 82 assessed in phase 1. All children meeting the criteria for autism identified via the Q-CHAT at phase 1 also met the criteria at phase 2. The PPV was 28% (95% CI 15% to 46%) after phase 1 and phase 2.ConclusionsThe Q-CHAT can be used at 18-30 months to identify autism and enable accelerated referral for diagnostic assessment. The low PPV suggests that for every true positive there would, however, be ~4-5 false positives. At follow-up, new cases were identified, illustrating the need for continued surveillance and rescreening at multiple time-points using developmentally sensitive instruments. Not all children who later receive a diagnosis of autism are detectable during the toddler period.

Project description:The differentiation of induced pluripotent stem cells (iPSCs) into diverse functional cell types provides a promising solution to support drug discovery, disease modeling, and regenerative medicine. However, functional cell differentiation is currently limited by the substantial line-to-line and batch-to-batch variability, which severely impede the progress of scientific research and the manufacturing of cell products. For instance, iPSC-to-cardiomyocyte (CM) differentiation is vulnerable with great sensitivity to inappropriate doses of CHIR99021 (CHIR) that are applied in the initial stage of mesoderm differentiation. Here, by harnessing live-cell bright-field imaging and machine learning (ML), we realize real-time cell recognition in the entire differentiation process, e.g., CMs, cardiac progenitor cells (CPCs), iPSC clones, and even misdifferentiated cells. This enables non-invasive prediction of differentiation efficiency, purification of ML-recognized CMs and CPCs for reducing cell contamination, early assessment of the CHIR dose for correcting the misdifferentiation trajectory, and evaluation of initial iPSC colonies for controlling the start point of differentiation, all of which provide a more invulnerable differentiation method with resistance to variability. Moreover, with the established ML models as a readout for the chemical screen, we identify a CDK8 inhibitor to further improve the cell resistance to the overdose of CHIR. Together, this study indicates that artificial intelligence is able to guide and iteratively optimize iPSC differentiation to achieve consistently high efficiency across cell lines and batches, providing a better understanding and rational modulation of the differentiation process for functional cell manufacturing in biomedical applications. With the assistance of RNA sequencing, we transcriptomically characterize the image-recognized CPCs (IR-CPCs), the cells treated with different CHIR doses at stage I, iPSC-CM treated with or without BI-1347, and cells treated with or without BI-1347 at stage I.

Project description:BackgroundAutism spectrum disorder (ASD) is characterised by many of features including problem in social interactions, different ways of learning, some children showing a keen interest in specific subjects, inclination to routines, challenges in typical communication, and particular ways of processing sensory information. Early intervention and suitable supports for these children may make a significant contribution to their development. However, considerable difficulties have been encountered in the screening and diagnosis of ASD. The literature has indicated that certain retinal features are significantly associated with ASD. In this study, we investigated the use of machine learning approaches on retinal images to further enhance the classification accuracy.MethodsForty-six ASD participants were recruited from three special needs schools and 24 normal control were recruited from the community. Among them, 23 age-gender matched ASD and normal control participant-pairs were constructed for the primary analysis. All retinal images were captured using a nonmydriatic fundus camera. Automatic retinal image analysis (ARIA) methodology applying machine-learning technology was used to optimise the information of the retina to develop a classification model for ASD. The model's validity was then assessed using a 10-fold cross-validation approach to assess its validity.FindingsThe sensitivity and specificity were 95.7% (95% CI 76.0%, 99.8%) and 91.3% (95% CI 70.5%, 98.5%) respectively. The area under the ROC curve was 0.974 (95% CI 0.934, 1.000); however, it was noted that the specificity for female participants might not be as high as that for male participants.InterpretationBecause ARIA is a fully automatic cloud-based algorithm and relies only on retinal images, it can be used as a risk assessment tool for ASD screening. Further diagnosis and confirmation can then be made by professionals, and potential treatment may be provided at a relatively early stage.

Project description:OBJECTIVES:Although the American Academy of Pediatrics recommends screening for autism spectrum disorder (ASD) for all young children, disparities in ASD diagnosis and intervention in minority children persist. One potential contributor to disparities could be whether physicians take different actions after an initial positive screen based on patient demographics. This study estimated factors associated with physicians completing the follow-up interview for the Modified Checklist for Autism in Toddlers with Follow-up (M-CHAT-F), and referring children to diagnostic services, audiology, and Early Intervention (EI) immediately after a positive screen. METHODS:Children seen in a large primary care network that has implemented universal ASD screening were included if they screened positive on the M-CHAT parent questionnaire during a 16-30 month well child visit (N = 2882). Demographics, screening results, and referrals were extracted from the electronic health record. RESULTS:Children from lower-income families or on public insurance were more likely to have been administered the follow-up interview. Among children who screened positive, 26% were already in EI, 31% were newly referred to EI, 11% were referred each to audiology and for comprehensive ASD evaluation. 40.2% received at least one recommended referral; 3.7% received all recommended referrals. In adjusted multivariable models, male sex, white versus black race, living in an English-speaking household, and having public insurance were associated with new EI referral. Male sex, black versus white race, and lower household income were associated with referral to audiology. Being from an English-speaking family, white versus Asian race, and lower household income were associated with referral for ASD evaluation. A concurrent positive screen for general developmental concerns was associated with each referral. CONCLUSIONS:We found low rates of follow-up interview completion and referral after positive ASD screen, with variations in referral by sex, language, socio-economic status, and race. Understanding pediatrician decision-making about ASD screening is critical to improving care and reducing disparities.

Dataset Information

A Machine Learning Strategy for Autism Screening in Toddlers.

Publications

A Machine Learning Strategy for Autism Screening in Toddlers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets