Profiles of autism characteristics in thirteen genetic syndromes: a machine learning approach

Abstract

Background Phenotypic studies have identified distinct patterns of autistic characteristics in genetic syndromes associated with intellectual disability (ID), leading to diagnostic uncertainty and compromised access to autism-related support. Previous research has tended to include small samples and diverse measures, which limits the generalisability of findings. In this study, we generated detailed profiles of autistic characteristics in a large sample of > 1500 individuals with rare genetic syndromes. Methods Profiles of autistic characteristics based on the Social Communication Questionnaire (SCQ) scores were generated for thirteen genetic syndrome groups (Angelman n = 154, Cri du Chat n = 75, Cornelia de Lange n = 199, fragile X n = 297, Prader–Willi n = 278, Lowe n = 89, Smith–Magenis n = 54, Down n = 135, Sotos n = 40, Rubinstein–Taybi n = 102, 1p36 deletion n = 41, tuberous sclerosis complex n = 83 and Phelan–McDermid n = 35 syndromes). It was hypothesised that each syndrome group would evidence a degree of specificity in autistic characteristics. To test this hypothesis, a classification algorithm via support vector machine (SVM) learning was applied to scores from over 1500 individuals diagnosed with one of the thirteen genetic syndromes and autistic individuals who did not have a known genetic syndrome (ASD; n = 254). Self-help skills were included as an additional predictor. Results Genetic syndromes were associated with different but overlapping autism-related profiles, indicated by the substantial accuracy of the entire, multiclass SVM model (55% correctly classified individuals). Syndrome groups such as Angelman, fragile X, Prader–Willi, Rubinstein–Taybi and Cornelia de Lange showed greater phenotypic specificity than groups such as Cri du Chat, Lowe, Smith–Magenis, tuberous sclerosis complex, Sotos and Phelan-McDermid. The inclusion of the ASD reference group and self-help skills did not change the model accuracy. Limitations The key limitations of our study include a cross-sectional design, reliance on a screening tool which focuses primarily on social communication skills and imbalanced sample size across syndrome groups. Conclusions These findings replicate and extend previous work, demonstrating syndrome-specific profiles of autistic characteristics in people with genetic syndromes compared to autistic individuals without a genetic syndrome. This work calls for greater precision of assessment of autistic characteristics in individuals with genetic syndromes associated with ID.

Heterogeneity of Autism Characteristics in Genetic Syndromes: Key Considerations for Assessment and Support

“…Autism is widely understood as a complex condition, with variation in terms of sex-specific factors, intellectual ability, and co-occurring conditions [ 13 ]. Detailed analyses that have considered the specific patterns of autism characteristics within individual syndrome groups show that the profiles of autism characteristics are highly heterogeneous between different syndrome groups [ 14 ••], even when individuals score above clinical cut-off scores on autism assessment tools. In many cases, the profile of autism characteristics is reported to be subtly different, both qualitatively and quantitatively from non-syndromic autism.…”

“…For example, some syndrome groups evidence a profile of characteristics which includes significant repetitive behaviours and/or interests (RRBIs) alongside differences in social communication that are similar to that of autistic people who do not have a genetic syndrome, combined with comparatively heightened social motivation (e.g. Rubinstein-Taybi syndrome [ 14 ••], Sturge-Weber syndrome [ 7 ••]). For other syndromes, both social interaction and communication differences evidence similarities with non-syndromic autism, while RRBIs may be less apparent in the syndrome or may present differently to those described in autistic people without a syndrome (e.g., Phelan-McDermid syndrome [ 15 ], Sotos [ 16 ]).…”

A dimensional approach to neurodevelopmental differences in genetically well‐defined populations: What's next?

“…In genetic syndromes, a complicating factor for accurate assessment is that behavioral features of autism and other neurodevelopmental disorders may depart from the typical presentation in non-syndromic populations. 3 On top of this, there is need to consider the impact of relevant medical (e.g. feeding problems, orthopedic issues, pain, medical trauma) and neurological (e.g.…”

“…Despite this critical insight, within the current medical system a discrete diagnosis is often necessary to obtain access to relevant services and treatments. In genetic syndromes, a complicating factor for accurate assessment is that behavioral features of autism and other neurodevelopmental disorders may depart from the typical presentation in non‐syndromic populations 3 . On top of this, there is need to consider the impact of relevant medical (e.g.…”

The use of eye-tracking technology as a tool to evaluate social cognition in people with an intellectual disability: a systematic review and meta-analysis

“…For instance, people with Down syndrome and Rubinstein-Taybi syndrome present with high levels of social motivation [ 32 , 33 ], whereas Cornelia de Lange syndrome and fragile X syndrome are characterised by social anxiety and extreme shyness [ 34 ]. Notably, profiles of autism characteristics are highly heterogeneous and appear qualitatively different, often in very subtle ways, across genetic syndromes and when compared to non-syndromic 2 autism [ 35 ]. This heterogeneity cannot be accounted for by degree of ID severity [ 22 ] and appears to reflect the broader behavioural phenotypes presented in specific genetic syndromes [ 36 ].…”