Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability - a machine learning approach

Aug 4, 2026

Upload by Himbo

Genomic conditions are linked to developmental delay, intellectual disability, autism spectrum disorder, and physical and mental health symptoms, yet their rarity and variability restrict standard diagnostic guidelines. A screening approach for identifying young people with neurodevelopmental disorders associated with genomic conditions (ND-GCs) who may need additional support is needed. Using machine learning on 493 participants, caregivers’ assessments and exploratory graph analysis were used to build and interpret accurate ND-GC classifiers, yielding a compact set of discriminative variables.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Background

Method

Results

Limitations

Conclusions

Keywords

Background

Donnelly, N. , Cunningham, A. , Salas, S. M. , Bracher-Smith, M. , Chawner, S. , Stochl, J. , Ford, T. J. , Raymond, F. L. , Escott-Price, V. ,& van den Bree, M. B. M. (2023) . Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability: a machine learning approach. Molecular Autism, 14(1),[19] . [https://doi.org/10.1186/s13229-023-00549-2](https://doi.org/10.1186/s13229-023-00549-2) Publisher's PDF, also known as Version of record License (if available): CC BY Link to published version (if available): 10.1186/s13229-023-00549-2 Link to publication record in Explore Bristol Research PDF-document This is the final published version of the article (version of record) . It first appeared online via BMC at [https://doi.org/10.1186/s13229-023-00549-2 . Please](https://doi.org/10.1186/s13229-023-00549-2 . Please) refer to any applicable terms of use of the publisher. University of Bristol-Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: [http://www.bristol.ac.uk/red/research-policy/pure/user-guides/ebr-terms/](http://www.bristol.ac.uk/red/research-policy/pure/user-guides/ebr-terms/) Donnelly et al. Molecular Autism (2023) 14:19 [https://doi.org/10.1186/s13229-023-00549-2](https://doi.org/10.1186/s13229-023-00549-2) Molecular Autism RESEARCH Open Access Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability: a machine learning approach Nicholas Donnelly1,2 , Adam Cunningham3 , Sergio Marco Salas3 , Matthew Bracher‑Smith3 , Samuel Chawner3 , Jan Stochl4,5 , Tamsin Ford4 , F. Lucy Raymond6 , Valentina Escott‑Price3 and Marianne B. M. van den Bree3* Abstract Background Genomic conditions can be associated with developmental delay, intellectual disability, autism spec‑ trum disorder, and physical and mental health symptoms. They are individually rare and highly variable in presen‑ tation, which limits the use of standard clinical guidelines for diagnosis and treatment. A simple screening tool to identify young people with genomic conditions associated with neurodevelopmental disorders (ND‑GCs) who could benefit from further support would be of considerable value. We used machine learning approaches to address this question. Method A total of 493 individuals were included: 389 with a ND‑GC, mean age = 9. 01, 66% male) and 104 siblings without known genomic conditions (controls, mean age = 10. 23, 53% male) . Primary carers completed assessments of behavioural, neurodevelopmental and psychiatric symptoms and physical health and development. Machine learning techniques (penalised logistic regression, random forests, support vector machines and artificial neural networks) were used to develop classifiers of ND‑GC status and identified limited sets of variables that gave the best classifica‑ tion performance. Exploratory graph analysis was used to understand associations within the final variable set. Results All machine learning methods identified variable sets giving high classification accuracy (AUROC between 0.883 and 0 . 915) . We identified a subset of 30 variables best discriminating between individuals with ND‑GCs and controls which formed 5 dimensions: conduct, separation anxiety, situational anxiety, communication and motor development. Limitations This study used cross‑sectional data from a cohort study which was imbalanced with respect to ND‑GC status. Our model requires validation in independent datasets and with longitudinal follow‑up data for validation before clinical application. Conclusions In this study, we developed models that identified a compact set of psychiatric and physical health measures that differentiate individuals with a ND‑GC from controls and highlight higher‑order structure w

FAQs

What problem does the study address?

The study addresses how to identify young people with ND-GCs who could benefit from further support, despite the rarity and high variability of genomic conditions tied to neurodevelopmental disorders.

How was the machine learning approach implemented?

Care primary carers completed assessments of behavioral, neurodevelopmental, psychiatric symptoms, and physical health/development. Machine learning methods trained classifiers for ND-GC status, and exploratory graph analysis was used to interpret associations within selected variables.

What were the key results and selected variables?

All machine learning methods achieved high classification accuracy, with AUROC between 0.883 and 0.915. A subset of 30 variables best discriminated ND-GCs from controls and organized into five dimensions: conduct, separation anxiety, situational anxiety, communication, and motor development.

Aug 4, 2026

Upload by Himbo