Introduction to the Study
A groundbreaking study led by Associate Professor Thomas Yeo from the National University of Singapore has revealed that longer functional MRI (fMRI) scans can significantly reduce research costs while enhancing the accuracy of predictions in brain-based AI models. Published in the journal Nature, this research challenges the traditional approach of scanning large numbers of individuals for short durations, suggesting that fewer, longer scans may be more effective.
The Dilemma in Neuroscience Research
In the realm of neuroscience, the conventional wisdom has been to collect extensive datasets by scanning thousands of participants for brief periods, typically around 10 minutes. This data is then used to train AI models to predict individual traits and outcomes, such as cognitive abilities and mental health indicators. However, as the number of participants increases, so do the associated costs, including recruitment, scheduling, and administrative tracking. Moreover, short scans may not capture sufficient high-quality data to make reliable personalized predictions.
The Innovative Approach
The research team, including collaborators from the University of Oxford and Washington University in St. Louis, proposed an alternative strategy: scanning fewer individuals for longer periods. They developed a mathematical model to predict how variations in scan time and participant numbers affect the performance of AI models. This model was validated using nine international imaging datasets, encompassing diverse individuals in terms of age, ethnicity, and health status.
Key Findings
The study found that 30-minute scans strike an optimal balance, maximizing prediction accuracy while minimizing research costs. This approach can lead to cost savings of up to 22% without compromising the reliability of predictions. “For years, the mantra has been ‘bigger is better.’ We’ve chased ever-larger cohorts without asking how long each person should be scanned,” said Associate Professor Yeo. “We show that in brain imaging, ‘bigger’ doesn’t have to mean larger cohorts. It can also mean more data per person.”
Implications for Future Research
This finding has the potential to reshape the design of neuroscience and mental health studies, particularly for populations that are difficult to recruit, such as patients with rare neurological conditions. The team is now refining their model using real-world clinical data and emerging brain imaging technology, aiming to make it easier for researchers and health systems worldwide to design smarter, more cost-effective studies.
Impact on Neurology and Psychiatry
By enabling studies to collect better data for less money, this research could influence future investigations in neurology and psychiatry. It also has the potential to guide national and global efforts to deliver more personalized, affordable healthcare. Professor Nico Dosenbach, a neurologist from Washington University in St. Louis and co-author of the study, emphasized the significance of this work: “This is a game-changer for the field. It gives research teams a rigorous, quantitative way to design smarter studies, especially critical as we move toward precision neuroscience.”
Conclusion
The study, jointly authored by Dr. Leon Ooi, Dr. Csaba Orban, and Dr. Shaoshi Zhang, highlights the benefits of longer individual fMRI scans. This approach not only optimizes cost and prediction accuracy but also offers a more efficient strategy for neuroscience and mental health research. As the team continues to refine their model, the potential for more effective and economical brain studies becomes increasingly attainable.
🔗 **Fuente:** https://medicalxpress.com/news/2025-07-global-longer-brain-scans-accurate.html