⚡ Quick Summary
This study utilized population modelling to identify distinct subgroups within autism and ADHD based on structural MRI data. The findings reveal that these subgroups exhibit opposite neuroanatomical alterations compared to controls, emphasizing the complexity of these neurodevelopmental conditions.
🔍 Key Details
- 📊 Dataset: Multi-site dataset focusing on cortical thickness, surface area, and grey matter volume.
- 🧩 Features used: Global and regional centile scores of neuroanatomical measures.
- ⚙️ Technology: HYDRA, a novel semi-supervised machine learning algorithm.
- 🏆 Comparison: Performance compared to traditional clustering approaches.
🔑 Key Takeaways
- 🔍 Distinct subgroups were identified within autism and ADHD, as well as across diagnoses.
- ⚖️ Neuroanatomical alterations were often opposite relative to controls.
- 📉 No significant clinical differences were found across the identified subgroups.
- 🔄 Method selection greatly influences subgroup identification and characteristics.
- 💡 Population modelling is a promising tool for studying heterogeneity in neurodevelopmental disorders.
- 📈 Results highlight the need for careful reporting of methods in future studies.
📚 Background
Autism and ADHD are recognized as highly heterogeneous neurodevelopmental conditions, characterized by a wide range of symptoms and underlying neurobiological variations. Previous imaging studies have produced inconsistent results, indicating that a singular neuroanatomical profile for either condition is unlikely. Understanding this heterogeneity is crucial for developing more effective clinical interventions and improving patient outcomes.
🗒️ Study
The study employed a novel approach using population modelling to cluster a multi-site dataset based on neuroanatomical features. The researchers utilized the HYDRA algorithm, which is designed to cluster data based on differences from control groups, and compared its effectiveness to traditional clustering methods. This innovative approach aims to parse the complexities of autism and ADHD to identify more homogeneous subgroups.
📈 Results
The analysis revealed distinct subgroups within both autism and ADHD, characterized by varying patterns of neuroanatomical alterations. Interestingly, these subgroups often displayed opposite alterations compared to control groups. However, the study did not find significant clinical differences among the subgroups, suggesting that while neuroanatomical features may vary, they do not necessarily correlate with clinical outcomes.
🌍 Impact and Implications
The findings from this study underscore the importance of examining the heterogeneity present in autism and ADHD. By utilizing advanced population modelling techniques, researchers can gain deeper insights into the neurobiological underpinnings of these conditions. This approach not only enhances our understanding but also paves the way for more tailored and effective interventions in clinical settings. The implications of this research could significantly influence future studies and treatment strategies for neurodevelopmental disorders.
🔮 Conclusion
This study highlights the critical role of population modelling in understanding the complexities of autism and ADHD. By identifying distinct neuroanatomical subgroups, researchers can better appreciate the variability within these conditions. As we move forward, it is essential to continue refining our methods and reporting practices to enhance the reliability and applicability of findings in neurodevelopmental research. The future of understanding autism and ADHD looks promising with these innovative approaches!
💬 Your comments
What are your thoughts on the implications of this research for understanding autism and ADHD? We invite you to share your insights and engage in a discussion! 💬 Leave your comments below or connect with us on social media:
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 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.
Author: [‘Pecci-Terroba C’, ‘Lai MC’, ‘Lombardo MV’, ‘Chakrabarti B’, ‘Ruigrok ANV’, ‘Suckling J’, ‘Anagnostou E’, ‘Lerch JP’, ‘Taylor MJ’, ‘Nicolson R’, ‘Georgiades S’, ‘Crosbie J’, ‘Schachar R’, ‘Kelley E’, ‘Jones J’, ‘Arnold PD’, ‘Seidlitz J’, ‘Alexander-Bloch AF’, ‘Bullmore ET’, ‘Baron-Cohen S’, ‘Bedford SA’, ‘Bethlehem RAI’]
Journal: Mol Autism
Citation: Pecci-Terroba C, et al. Subgrouping autism and ADHD based on structural MRI population modelling centiles. Subgrouping autism and ADHD based on structural MRI population modelling centiles. 2025; 16:33. doi: 10.1186/s13229-025-00667-z