Subgrouping autism and ADHD based on structural MRI population modelling centiles
Abstract Background Autism and attention deficit hyperactivity disorder (ADHD) are two highly heterogeneous neurodevelopmental conditions with variable underlying neurobiology. Imaging studies have yielded varied results, and it is now clear that there is unlikely to be one characteristic neuroanato...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-06-01
|
| Series: | Molecular Autism |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13229-025-00667-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434296999215104 |
|---|---|
| author | Clara Pecci-Terroba Meng-Chuan Lai Michael V. Lombardo Bhismadev Chakrabarti Amber N. V. Ruigrok John Suckling Evdokia Anagnostou Jason P. Lerch Margot J. Taylor Rob Nicolson Stelios Georgiades Jennifer Crosbie Russell Schachar Elizabeth Kelley Jessica Jones Paul D. Arnold Jakob Seidlitz Aaron F. Alexander-Bloch Edward T. Bullmore Simon Baron-Cohen Saashi A. Bedford Richard A. I. Bethlehem |
| author_facet | Clara Pecci-Terroba Meng-Chuan Lai Michael V. Lombardo Bhismadev Chakrabarti Amber N. V. Ruigrok John Suckling Evdokia Anagnostou Jason P. Lerch Margot J. Taylor Rob Nicolson Stelios Georgiades Jennifer Crosbie Russell Schachar Elizabeth Kelley Jessica Jones Paul D. Arnold Jakob Seidlitz Aaron F. Alexander-Bloch Edward T. Bullmore Simon Baron-Cohen Saashi A. Bedford Richard A. I. Bethlehem |
| author_sort | Clara Pecci-Terroba |
| collection | DOAJ |
| description | Abstract Background Autism and attention deficit hyperactivity disorder (ADHD) are two highly heterogeneous neurodevelopmental conditions with variable underlying neurobiology. Imaging studies have yielded varied results, and it is now clear that there is unlikely to be one characteristic neuroanatomical profile of either condition. Parsing this heterogeneity could allow us to identify more homogeneous subgroups, either within or across conditions, which may be more clinically informative. This has been a pivotal goal for neurodevelopmental research using both clinical and neuroanatomical features, though results thus far have again been inconsistent with regards to the number and characteristics of subgroups. Methods Here, we use population modelling to cluster a multi-site dataset based on global and regional centile scores of cortical thickness, surface area and grey matter volume. We use HYDRA, a novel semi-supervised machine learning algorithm which clusters based on differences to controls and compare its performance to a traditional clustering approach. Results We identified distinct subgroups within autism and ADHD, as well as across diagnosis, often with opposite neuroanatomical alterations relatively to controls. These subgroups were characterised by different combinations of increased or decreased patterns of morphometrics. We did not find significant clinical differences across subgroups. Limitations Crucially, however, the number of subgroups and their membership differed vastly depending on chosen features and the algorithm used, highlighting the impact and importance of careful method selection. Conclusions We highlight the importance of examining heterogeneity in autism and ADHD and demonstrate that population modelling is a useful tool to study subgrouping in autism and ADHD. We identified subgroups with distinct patterns of alterations relative to controls but note that these results rely heavily on the algorithm used and encourage detailed reporting of methods and features used in future studies. |
| format | Article |
| id | doaj-art-aadef3a81ed04834a7cedad1ad502e27 |
| institution | Kabale University |
| issn | 2040-2392 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | BMC |
| record_format | Article |
| series | Molecular Autism |
| spelling | doaj-art-aadef3a81ed04834a7cedad1ad502e272025-08-20T03:26:43ZengBMCMolecular Autism2040-23922025-06-0116111910.1186/s13229-025-00667-zSubgrouping autism and ADHD based on structural MRI population modelling centilesClara Pecci-Terroba0Meng-Chuan Lai1Michael V. Lombardo2Bhismadev Chakrabarti3Amber N. V. Ruigrok4John Suckling5Evdokia Anagnostou6Jason P. Lerch7Margot J. Taylor8Rob Nicolson9Stelios Georgiades10Jennifer Crosbie11Russell Schachar12Elizabeth Kelley13Jessica Jones14Paul D. Arnold15Jakob Seidlitz16Aaron F. Alexander-Bloch17Edward T. Bullmore18Simon Baron-Cohen19Saashi A. Bedford20Richard A. I. Bethlehem21Department of Psychology, University of CambridgeAutism Research Centre, Department of Psychiatry, University of CambridgeLaboratory for Autism and Neurodevelopmental Disorders, Center for Neuroscience and Cognitive Systems, Istituto Italiano Di TecnologiaCentre for Autism, School of Psychology and Clinical Language Sciences, University of ReadingAutism Research Centre, Department of Psychiatry, University of CambridgeBrain Mapping Unit, Department of Psychiatry, University of CambridgeHolland Bloorview Kids Rehabilitation Hospital, Bloorview Research Institute Toronto, University of TorontoProgram in Neurosciences and Mental Health, Research Institute, The Hospital for Sick ChildrenProgram in Neurosciences and Mental Health, Research Institute, The Hospital for Sick ChildrenDepartment of Psychiatry, University of Western OntarioMcMaster UniversityDepartment of Psychiatry, The Hospital for Sick ChildrenDepartment of Psychiatry, The Hospital for Sick ChildrenDepartment of Psychology, Queen’s UniversityCentre for Neuroscience Studies, Queen’s UniversityMathison Centre for Mental Health Research & Education, Hotchkiss Brain Institute, Cumming School of Medicine, University of CalgaryDepartment of Psychiatry, University of PennsylvaniaDepartment of Psychiatry, University of PennsylvaniaBrain Mapping Unit, Department of Psychiatry, University of CambridgeAutism Research Centre, Department of Psychiatry, University of CambridgeDepartment of Psychology, University of CambridgeDepartment of Psychology, University of CambridgeAbstract Background Autism and attention deficit hyperactivity disorder (ADHD) are two highly heterogeneous neurodevelopmental conditions with variable underlying neurobiology. Imaging studies have yielded varied results, and it is now clear that there is unlikely to be one characteristic neuroanatomical profile of either condition. Parsing this heterogeneity could allow us to identify more homogeneous subgroups, either within or across conditions, which may be more clinically informative. This has been a pivotal goal for neurodevelopmental research using both clinical and neuroanatomical features, though results thus far have again been inconsistent with regards to the number and characteristics of subgroups. Methods Here, we use population modelling to cluster a multi-site dataset based on global and regional centile scores of cortical thickness, surface area and grey matter volume. We use HYDRA, a novel semi-supervised machine learning algorithm which clusters based on differences to controls and compare its performance to a traditional clustering approach. Results We identified distinct subgroups within autism and ADHD, as well as across diagnosis, often with opposite neuroanatomical alterations relatively to controls. These subgroups were characterised by different combinations of increased or decreased patterns of morphometrics. We did not find significant clinical differences across subgroups. Limitations Crucially, however, the number of subgroups and their membership differed vastly depending on chosen features and the algorithm used, highlighting the impact and importance of careful method selection. Conclusions We highlight the importance of examining heterogeneity in autism and ADHD and demonstrate that population modelling is a useful tool to study subgrouping in autism and ADHD. We identified subgroups with distinct patterns of alterations relative to controls but note that these results rely heavily on the algorithm used and encourage detailed reporting of methods and features used in future studies.https://doi.org/10.1186/s13229-025-00667-zAutismADHDPopulation modellingSubgroupingNeuroimagingStructural MRI |
| spellingShingle | Clara Pecci-Terroba Meng-Chuan Lai Michael V. Lombardo Bhismadev Chakrabarti Amber N. V. Ruigrok John Suckling Evdokia Anagnostou Jason P. Lerch Margot J. Taylor Rob Nicolson Stelios Georgiades Jennifer Crosbie Russell Schachar Elizabeth Kelley Jessica Jones Paul D. Arnold Jakob Seidlitz Aaron F. Alexander-Bloch Edward T. Bullmore Simon Baron-Cohen Saashi A. Bedford Richard A. I. Bethlehem Subgrouping autism and ADHD based on structural MRI population modelling centiles Molecular Autism Autism ADHD Population modelling Subgrouping Neuroimaging Structural MRI |
| title | Subgrouping autism and ADHD based on structural MRI population modelling centiles |
| title_full | Subgrouping autism and ADHD based on structural MRI population modelling centiles |
| title_fullStr | Subgrouping autism and ADHD based on structural MRI population modelling centiles |
| title_full_unstemmed | Subgrouping autism and ADHD based on structural MRI population modelling centiles |
| title_short | Subgrouping autism and ADHD based on structural MRI population modelling centiles |
| title_sort | subgrouping autism and adhd based on structural mri population modelling centiles |
| topic | Autism ADHD Population modelling Subgrouping Neuroimaging Structural MRI |
| url | https://doi.org/10.1186/s13229-025-00667-z |
| work_keys_str_mv | AT clarapecciterroba subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT mengchuanlai subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT michaelvlombardo subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT bhismadevchakrabarti subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT ambernvruigrok subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT johnsuckling subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT evdokiaanagnostou subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT jasonplerch subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT margotjtaylor subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT robnicolson subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT steliosgeorgiades subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT jennifercrosbie subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT russellschachar subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT elizabethkelley subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT jessicajones subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT pauldarnold subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT jakobseidlitz subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT aaronfalexanderbloch subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT edwardtbullmore subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT simonbaroncohen subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT saashiabedford subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles AT richardaibethlehem subgroupingautismandadhdbasedonstructuralmripopulationmodellingcentiles |