. 2025 Jul 10;23(3):38.

doi: 10.1007/s12021-025-09729-2.

Prediction of Cerebrospinal Fluid (CSF) Pressure with Generative Adversarial Network Synthetic Plasma-CSF Biomarker Pairing

Phani Paladugu^{1

2}, Rahul Kumar³, Jahnavi Yelamanchi⁴, Ethan Waisberg⁵, Joshua Ong⁶, Mouayad Masalkhi^{7

8}, Chirag Gowda⁹, Ryung Lee¹⁰, Dylan Amiri^{11

12}, Ram Jagadeesan^{13

14}, Nasif Zaman¹⁵, Alireza Tavakkoli¹⁵, Andrew G Lee^{16

17

18

19

20

21

22

23}

Affiliations

¹ Sidney Kimmel Medical College, Philadelphia, PA, USA.
² Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
³ University of Massachusetts T.H. Chan School of Medicine, Worcester, MA, USA.
⁴ Tandon School of Engineering, New York University, New York, NY, USA.
⁵ Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK.
⁶ Department of Ophthalmology and Visual Sciences, University of Michigan Kellogg Eye Center, Ann Arbor, MI, USA.
⁷ University College Dublin School of Medicine, Belfield, Dublin, Ireland.
⁸ Department of Electronic & Computer Engineering, University of Limerick, Limerick, Ireland.
⁹ University of Miami Miller School of Medicine, 160 NW 10 Ave, Miami, FL, 33136, USA. gowdachirag24@gmail.com.
¹⁰ Touro College of Osteopathic Medicine, New York, NY, USA.
¹¹ Department of Biology, University of Miami, Coral Gables, Florida, USA.
¹² Mecklenburg Neurology Group, Charlotte, NC, USA.
¹³ Department of Computer Science, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA.
¹⁴ Artificial Intelligence Systems, Cisco Systems, Inc, San Jose, CA, USA.
¹⁵ Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, USA.
¹⁶ Center for Space Medicine, Baylor College of Medicine, Houston, TX, USA.
¹⁷ Department of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, TX, USA.
¹⁸ The Houston Methodist Research Institute, Houston Methodist Hospital, Houston, TX, USA.
¹⁹ Departments of Ophthalmology, Neurology, and Neurosurgery, Weill Cornell Medicine, New York, NY, USA.
²⁰ Department of Ophthalmology, University of Texas Medical Branch, Galveston, TX, USA.
²¹ University of Texas MD Anderson Cancer Center, Houston, TX, USA.
²² Texas A&M College of Medicine, Texas, USA.
²³ Department of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA.

PMID: 40637963
DOI: 10.1007/s12021-025-09729-2

Prediction of Cerebrospinal Fluid (CSF) Pressure with Generative Adversarial Network Synthetic Plasma-CSF Biomarker Pairing

Phani Paladugu et al. Neuroinformatics. 2025.

. 2025 Jul 10;23(3):38.

doi: 10.1007/s12021-025-09729-2.

Authors

Affiliations

¹ Sidney Kimmel Medical College, Philadelphia, PA, USA.
² Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
³ University of Massachusetts T.H. Chan School of Medicine, Worcester, MA, USA.
⁴ Tandon School of Engineering, New York University, New York, NY, USA.
⁵ Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK.
⁶ Department of Ophthalmology and Visual Sciences, University of Michigan Kellogg Eye Center, Ann Arbor, MI, USA.
⁷ University College Dublin School of Medicine, Belfield, Dublin, Ireland.
⁸ Department of Electronic & Computer Engineering, University of Limerick, Limerick, Ireland.
⁹ University of Miami Miller School of Medicine, 160 NW 10 Ave, Miami, FL, 33136, USA. gowdachirag24@gmail.com.
¹⁰ Touro College of Osteopathic Medicine, New York, NY, USA.
¹¹ Department of Biology, University of Miami, Coral Gables, Florida, USA.
¹² Mecklenburg Neurology Group, Charlotte, NC, USA.
¹³ Department of Computer Science, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA.
¹⁴ Artificial Intelligence Systems, Cisco Systems, Inc, San Jose, CA, USA.
¹⁵ Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, USA.
¹⁶ Center for Space Medicine, Baylor College of Medicine, Houston, TX, USA.
¹⁷ Department of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, TX, USA.
¹⁸ The Houston Methodist Research Institute, Houston Methodist Hospital, Houston, TX, USA.
¹⁹ Departments of Ophthalmology, Neurology, and Neurosurgery, Weill Cornell Medicine, New York, NY, USA.
²⁰ Department of Ophthalmology, University of Texas Medical Branch, Galveston, TX, USA.
²¹ University of Texas MD Anderson Cancer Center, Houston, TX, USA.
²² Texas A&M College of Medicine, Texas, USA.
²³ Department of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA.

PMID: 40637963
DOI: 10.1007/s12021-025-09729-2

Abstract

Non-invasive intracranial pressure (ICP) monitoring can help clinicians safely and efficiently monitor spaceflight-associated neuro-ocular syndrome (SANS), idiopathic intracranial hypertension, and traumatic brain injury in astronauts. Current invasive ICP measurement techniques are unsuitable for austere environments like spaceflight. In this study, we explore the potential of plasma-derived cell-free RNA (cfRNA) biomarkers as non-invasive alternatives to cerebrospinal fluid (CSF) markers for ICP assessment. We conducted a secondary analysis of NASA's Open Science Data Repository datasets 363-364, focusing on plasma and CSF biomarkers related to ICP and neurovascular health. An ensemble model combining Support Vector Machine, Gradient Boosting Regressor, and Ridge Regression was developed to capture plasma-CSF biomarker relationships. To address limited sample size, we employed a Generative Adversarial Network (GAN) to generate synthetic plasma-CSF biomarker pairs, expanding the dataset from 29 to 279 samples. The model's performance was evaluated using Mean Squared Error (MSE) and validated against real biomarker data. The GAN-augmented ensemble model achieved high predictive accuracy with an MSE of 0.0044. Synthetic plasma-CSF pairs closely aligned with actual biomarker distributions, demonstrating their effectiveness in reducing overfitting and enhancing model robustness. Strong correlations between plasma-derived RNA biomarkers and corresponding CSF indicators support their potential as non-invasive proxies for ICP assessment. This study establishes a novel framework for non-invasive ICP monitoring using plasma cfRNA profiles enriched with GAN-generated synthetic data. The approach shows promise for both spaceflight and clinical applications, potentially broadening diagnostic capabilities for ICP-related conditions. However, further validation across diverse populations is necessary, along with careful consideration of bioethical and data security issues associated with synthetic data use in clinical diagnostics.

Keywords: Biomarker Prediction; Generative Adversarial Networks; Intracranial Pressure; Machine Learning in Medicine; Non-invasive Diagnostics.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethical Approval: Not applicable. This study was a secondary analysis of publicly available NASA datasets (Open Science Data Repository 363–364) and did not involve direct experimentation on human or animal subjects. No IRB approval or consent to participate/publish was required. Conflicts of interest: Andrew G. Lee has received compensation as a speaker for Amgen and Alexion and has served as a consultant for Viridian, Erythreal, Catalyst, AstraZeneca, Bristol Myers Squibb, Stoke, and the U.S. Department of Justice. He is also a consultant for NASA; however, the views expressed in this study are his own and do not necessarily reflect those of NASA or the U.S. government. Ram Jagadeesan is an employee of Cisco and holds stock in the company.

References

1. Abbasi, M., Santos, B. P., Pereira, T. C., Sofia, R., Monteiro, N. R. C., Simões, C. J. V., Brito, R. M. M., Ribeiro, B., Oliveira, J. L., & Arrais, J. P. (2022). Designing optimized drug candidates with Generative Adversarial Network. Journal of Cheminformatics, 14(1), 40. https://doi.org/10.1186/s13321-022-00623-6 . Erratum.In:JCheminform.2022Aug11;14(1):53.10.1186/s13321-022-00631-6. - DOI - PubMed - PMC
1. Albrecht LJ, Höwner A, Griewank K, et al (2022) Circulating cell-free messenger RNA enables non-invasive pan-tumour monitoring of melanoma therapy independent of the mutational genotype. Clinical and Translational Medicine 12. https://doi.org/10.1002/ctm2.1090
1. Alhoraibi, L., Alghazzawi, D., & Alhebshi, R. (2024). Generative Adversarial Network-Based Data Augmentation for Enhancing Wireless Physical Layer Authentication. Sensors (Basel), 24(2), 641. https://doi.org/10.3390/s24020641 - DOI - PubMed
1. Amal, S., Safarnejad, L., Omiye, J. A., Ghanzouri, I., Cabot, J. H., & Ross, E. G. (2022). Use of multi-modal data and machine learning to improve cardiovascular disease care. Frontiers in Cardiovascular Medicine, 27(9), 840262. https://doi.org/10.3389/fcvm.2022.840262 - DOI
1. Arora, A. (2022). Generative adversarial networks and synthetic patient data: Current challenges and future perspectives. Future Healthcare Journal, 9(2), 190–193. https://doi.org/10.7861/fhj.2022-0013 - DOI - PubMed - PMC

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Substances

Actions
Actions

LinkOut - more resources

Full Text Sources
- Springer

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Prediction of Cerebrospinal Fluid (CSF) Pressure with Generative Adversarial Network Synthetic Plasma-CSF Biomarker Pairing

Affiliations

Prediction of Cerebrospinal Fluid (CSF) Pressure with Generative Adversarial Network Synthetic Plasma-CSF Biomarker Pairing

Authors

Affiliations

Abstract

Conflict of interest statement

Similar articles

References

MeSH terms

Substances

LinkOut - more resources

Full Text Sources

Abstract

Conflict of interest statement

Similar articles

References

MeSH terms

Substances

Related information

LinkOut - more resources

Full Text Sources