Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Hot Topics
  • Published:

The generative AI blueprint: modeling brain and behavior in concert

Neuropsychopharmacology volume 51, pages 345–346 (2026)Cite this article

Subjects

The quest to uncover the neurobiological underpinnings of psychiatric disorders and identify robust biomarkers faces significant challenges. While brain imaging techniques like functional magnetic resonance imaging (fMRI) have provided valuable insights into brain structure and function, their application in clinical care has been limited by a lack of reliable biomarkers with sufficient effect sizes [1].

A primary hurdle lies in the inherent complexity of the brain and the limitations of traditional research. Recent advances in fMRI analysis improved the reproducibility and reliability of fMRI data [2]. However, many conventional studies are underpowered, leading to inflated effect sizes and poor replicability [3]. Furthermore, task-specific brain imaging studies often suffer from an unfavorable ratio of “features to observations.” fMRI generates vast amounts of data, yet typical clinical studies involve far fewer participants. This disparity increases the risk of overfitting, where models capture noise rather than genuine biological signals, diminishing their generalizability and contributing to a reproducibility crisis in neuroscience [4].

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

References

  1. Akiki TJ, Abdallah CG. Mapping the depressed brain under stress using multimodal neuroimaging. Am J Psychiatry. 2024;181:578–80.

    Article  PubMed  Google Scholar 

  2. Stephan KE, Kasper L, Harrison LM, Daunizeau J, den Ouden HE, Breakspear M, et al. Nonlinear dynamic causal models for fMRI. NeuroImage. 2008;42:649–62.

    Article  PubMed  Google Scholar 

  3. Marek S, Tervo-Clemmens B, Calabro FJ, Montez DF, Kay BP, Hatoum AS, et al. Reproducible brain-wide association studies require thousands of individuals. Nature. 2022;603:654–60.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Yip SW, Kiluk B, Scheinost D. Toward addiction prediction: an overview of cross-validated predictive modeling findings and considerations for future neuroimaging research. Biol Psychiatry Cognit Neurosci Neuroimaging. 2020;5:748–58.

    Article  Google Scholar 

  5. DuPre E, Poldrack RA. The future of data analysis is now: integrating generative AI in neuroimaging methods development. Imaging Neurosci. 2024;2:1–8.

    Article  Google Scholar 

Download references

Funding

Dr. Abdallah received funding from the Beth K and Stuart Yudofsky Chair in the Neuropsychiatry of Military Post Traumatic Stress Syndrome. Dr. van Dijk received funding from NIH R351R35GM143072-01, the Wu Tsai Institute for Human Cognition at Yale, and the National Science Foundation CAREER Award (NSF 2443528).

Author information

Authors and Affiliations

  1. Department of Psychiatry, Baylor College of Medicine, Houston, TX, USA

    Chadi G. Abdallah

  2. Michael E. DeBakey VA Medical Center, Houston, TX, USA

    Chadi G. Abdallah

  3. Core for Advanced Magnetic Resonance Imaging (CAMRI), Baylor College of Medicine, Houston, TX, USA

    Chadi G. Abdallah

  4. Department of Internal Medicine, Yale University, New Haven, CT, USA

    David van Dijk

  5. Department of Computer Science, Yale University, New Haven, CT, USA

    David van Dijk

Authors
  1. Chadi G. Abdallah
    View author publications

    Search author on:PubMed Google Scholar

  2. David van Dijk
    View author publications

    Search author on:PubMed Google Scholar

Contributions

CGA and DvD wrote the paper.

Corresponding author

Correspondence to Chadi G. Abdallah.

Ethics declarations

Competing interests

Dr. Abdallah served as a consultant and/or on advisory boards for Douglas Pharmaceutical, Freedom Biosciences, Aptinyx, Genentech, Janssen, Psilocybin Labs, Lundbeck, Guidepoint, and FSV7. He also received royalties from a patent for using mTORC1 inhibitors to augment the effects of antidepressants (Aug 20, 2018). Dr. van Dijk reports no conflict of interest.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Abdallah, C.G., van Dijk, D. The generative AI blueprint: modeling brain and behavior in concert. Neuropsychopharmacol. 51, 345–346 (2026). https://doi.org/10.1038/s41386-025-02196-y

Download citation

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41386-025-02196-y

Search

Advanced search

Quick links