In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM–recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.
In the field of autism intervention, a large amount of evidence has demonstrated that parent-mediated interventions are effective in promoting a child’s learning and parent caring skills. Furthermore, remote delivery treatments are feasible and can represent a promising opportunity to reach families at distance with positive results. Recently, the sudden outbreak of COVID-19 dramatically disrupted intervention services for autism and forced an immediate reorganization of the territory services toward tele-assisted intervention programs, according to professional and local resources. Our study aimed to conduct a retrospective pilot exploratory investigation on parental compliance, participation, and satisfaction in relation to three different telehealth intervention modalities, such as video feedback, live streaming, and psychoeducation, implemented in the context of a public community setting delivering early autism intervention during the COVID-19 emergency. We found that parents who attended video feedback expressed the highest rate of compliance and participation, while parental psychoeducation showed significantly lower compliance and the highest drop-out rate. Regardless of the tele-assistance modality, all the participants expressed satisfaction with the telehealth experience, finding it useful and effective. Potential benefits and advantages of different remote modalities with reference to parent involvement and effectiveness are important aspects to be taken into account and should be further investigated in future studies.
22 January 2026 in International Journal of Clinical and Health Psychology
Early signs of autism often emerge through distinct developmental pathways, particularly in communication, social interaction, and play. While naturalistic parent-child interactions during free play are ideal for observing spontaneous social behaviors, few autism studies have adopted this ecological and developmental approach. To address this gap, we used a fine-grained microanalytic method to examine motor, gestural, and vocal behaviors in young children, integrating machine learning to explore how combinations of these traits distinguish early autistic neurodivergence.