Skip to main content

ORIGINAL RESEARCH article

Front. Genet.
Sec. Behavioral and Psychiatric Genetics
Volume 15 - 2024 | doi: 10.3389/fgene.2024.1375468
This article is part of the Research Topic Systems Biology Approaches to Psychiatric and Psychological Disorders: Unraveling the Complexities View all 3 articles

Applying Neural Ordinary Differential Equations for Analysis of Hormone Dynamics in Trier Social Stress Tests

Provisionally accepted
Tongli Zhang Tongli Zhang 1*Erik Nelson Erik Nelson 2
  • 1 University of Cincinnati, Cincinnati, United States
  • 2 Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, Ohio, United States

The final, formatted version of the article will be published soon.

    The application of Machine Learning (ML) and Artificial Intelligence (AI) has revolutionized data analysis and pattern recognition, leading to significant advances in various academic disciplines. In this study, we explore the use of Neural Ordinary Differential Equations (NODEs) for analyzing hormone dynamics in the hypothalamic-pituitary-adrenal (HPA) axis during Trier Social Stress Tests (TSST). This research aims to understand the HPA axis response in both healthy individuals and patients with Major Depressive Disorder (MDD). Using NODE models, we replicated hormone changes without incorporating any prior knowledge of the control system. The dynamic analysis revealed that stress effects are embedded in the nonautonomous vector fields derived from the NODE model, which were subsequently used as inputs for a Convolutional Neural Network (CNN) for patient classification. Our results demonstrate the potential of combining NODEs and CNNs to classify patients based on disease state, providing a preliminary step towards further research using the HPA axis stress response as an objective biomarker for MDD.

    Keywords: MDD (Major Depressive Disorder), machine learning (ML), Artficial Intelligence (AI), neural network, dynamical system

    Received: 23 Jan 2024; Accepted: 18 Jul 2024.

    Copyright: © 2024 Zhang and Nelson. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Tongli Zhang, University of Cincinnati, Cincinnati, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.