Jul 2026· Frontiers in Digital Health· Vol 8· 0 citations· 22 references
Medicine
TL;DR
It is demonstrated that lay behavioral descriptions can provide diagnostically valuable information comparable to clinical observations, although they are not readily summarized by AI.
Abstract
Introduction Early autism diagnosis remains challenging due to reliance on clinical observation and limited specialist availability. Addressing these barriers through automated diagnostic labeling and the integration of parental input may help mitigate the problem. Methods We trained a BioBERT machine learning model to label individual autism behavioral descriptions using the seven DSM-5 diagnostic criteria (A1-A3, B1-B4). This approach offers transparent clinical decision-making by providing detailed diagnostic information for individual behaviors and avoiding final case-level black-box decisions. We evaluated the model's performance on labeling lay (N = 35,971) and clinical (N = 145,603) behavior descriptions, as well as its transferability between the two. In addition, we compared the data sources by evaluating the diagnostic utility of lay and clinical examples across four dimensions, and of AI-generated summaries across two dimensions. Results We found that BioBERT can label both types of input, although it achieved higher precision (69%) on clinical descriptions and higher recall (83%) on lay descriptions. Sample size did not explain differences in performance. Transferring models from one data type to another results in a performance drop. Overall, training first on clinical data yielded the best-performing diagnostic models. When evaluating the examples from both data sources, the results show similar scores for the Utility, Specificity, Clinical Relevance, and Impact on Daily Life dimensions, and the cosine similarity analysis revealed substantial overlap (0.42) in vocabulary between the two. The utility of examples for A diagnostic behaviors was generally scored higher than that for B diagnostic behaviors. AI-generated summary scores showed a similar pattern between A and B examples but they were only moderately representative of these examples. Discussion These results demonstrate that lay behavioral descriptions can provide diagnostically valuable information comparable to clinical observations, although they are not readily summarized by AI. The integration of lay information into the diagnostic workflows could accelerate autism diagnosis without compromising clinical utility.
Machine learning can support diagnosticians in this effort, as demonstrated here utilizing multiple rating scales, the TASI, and the TAP, but there is a risk for bias when using machine learning and as such, no algorithm should replace expert clinical judgment.
Aaron J. Kaat, Ashlynn Campagna, Hannah Feiner et al.· JCPP Advances· 0 citations
Evidence is provided that mobile video-based ASD diagnosis can achieve comparable performance to models trained on clinical instrument data, and contributes to the development of broader adaptable autism detection tools, bypassing the dependence on traditional clinical instrument data.
Saimourya Surabhi, K. Dunlap, Parnian Azizian et al.· BioMedInformatics· 0 citations
Autism Spectrum Disorder (ASD) is a neurological and developmental condition characterized by challenges in social interaction, communication (both verbal and non-verbal), and repetitive behaviours. While genetics play a key role in its onset, early diagnosis remains essential for effective intervention. Machine learning (ML) offers a promising approach to streamline and accelerate ASD detection, making it faster and more cost-effective than traditional methods. This paper evaluates eight classification models to identify key ASD features and automate diagnosis. We compare their performance on large datasets to enhance predictive accuracy. ML has transformed healthcare by leveraging vast data volumes for analysis, with technological advances over the past decade improving diagnostic tools now standard in medical settings. ASD affects individuals variably, with symptoms typically appearing between 18 months and 3 years. Although genetic and environmental factors contribute, no single cause is confirmed. Traditional screenings rely heavily on clinician expertise, involving manual assessments and scoring, which can be subjective and time-consuming—even experts face uncertainties in predicting onset or severity. Parents seek rapid, reliable results. ML and deep learning (DL) address these gaps by analyzing complex patterns in data, enabling early prediction of ASD and its severity. This study implements diverse algorithms to support precise, automated screening, reducing diagnostic delays and improving outcomes.
Devireddy Mamatha, K. Maheswari· 2026 6th International Confe...· 0 citations
It is argued that meaningful clinical impact will require the integration of multimodal learning, semantic knowledge representation, explainable reasoning, and human-in-the-loop decision processes to support safe, interpretable, and clinically deployable AI systems in pediatric healthcare environments.
R. Zgheib, A. Naggar, Arash Kermani Kolankeh et al.· Information· 0 citations
The Autism Diagnostic Observation Schedule (ADOS) and its second edition (ADOS-2) have acquired a de facto “gold standard” status for reliably diagnosing autism in the United States, even though the developers themselves emphasize that the instrument should be used as part of a holistic, clinically driven developmental assessment. This narrative review is informed by diagnostic accuracy studies and the global mental health relevance of ADOS/ADOS-2 to lowand middle-income countries (LMICs) using Türkiye and the United States as point of contrast. We consider the benefits of ADOS/ADOS-2 —its contribution to standardized observation, cross-site comparability, and detailed phenotyping in research and complex clinical cases—as well as its limitations, including extensive training requirements, time-intensive administration, high kit costs, proprietary licensing, and tightly regulated translation policies. These factors substantially limit the practicality of routine ADOS/ADOS-2 use in LMICs and other resource-constrained settings, where most autistic children live. In the United States, ADOS/ ADOS-2 based assessments have become deeply integrated into specialty services and, in some regions, even informally mandated by insurers or school systems, with consequences for wait times, access, and equity. In Türkiye, autism is primarily diagnosed through clinical assessment by child and adolescent psychiatrists without formal requirements for ADOS/ADOS-2, which expands clinical autonomy but results in less standardization and weaker cross-site consistency. We argue that treating the ADOS/ ADOS-2 as a universal diagnostic “gold standard” is unachievable given the global public health resource constraints in LMICs. Autism diagnosis, service eligibility, and research, especially in such a poor resource setting will require scalable, open-access, and cost-effective tools for both routine care and population-level studies.
Setenay Adıgüzel, Kerim M. Munir· Psychiatry and Clinical Psyc...· 0 citations
A toddler‑centered Case‑Based Reasoning (CBR) framework that emulates clinicians’ decision‑making by retrieving and adapting similar historical cases and delivers transparent, interpretable recommendations via comparable cases, supporting clinician trust is introduced.
Hachemi Yamina· ITEGAM- Journal of Engineeri...· 0 citations
