PuSH - Publication Server of Helmholtz Zentrum München

Leopold-Kerschbaumer, N.* ; Halenke, T.* ; Süzeroğlu, S.* ; Jung, M.* ; Seleznova, M.* ; Thorisch, N.* ; Lorenz, J.M.* ; Bocklitz, T.* ; Eskofier, B.M. ; Kutyniok, G.* ; Krausz, F.* ; Kepesidis, K.V.*

Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies.

NPJ Digit. Med., DOI: 10.1038/s41746-026-03226-9 (2026)
Publ. Version/Full Text Research data DOI
Open Access Gold
Creative Commons Lizenzvertrag
Infrared molecular fingerprinting of blood offers a scalable, minimally invasive window into human physiology, but limited follow-up, imbalanced cohorts, and restricted access to diverse phenotypes constrain systematic studies. Here, we introduce a conditional deep generative framework for synthesizing blood-based infrared spectra that preserves individual-level structure while allowing controlled manipulation of demographic and anthropometric covariates. Using 25,308 spectra from 5,863 ostensibly healthy participants in the longitudinal Health4Hungary - Hungary4Health cohort, we train a Conditional Variational Autoencoder, a Conditional Boundary Equilibrium GAN, and a Conditional Diffusion Model to generate blood-based infrared spectra conditioned on age, sex, and body mass index. We show that the generated spectra closely match held-out real data across multiple levels and faithfully encode demographic and anthropometric information. We further demonstrate two in-silico applications: modeling of individualized healthy aging trajectories that follow cohort-level aging manifolds while retaining individual-specific characteristics, and targeted augmentation of underrepresented body mass index categories. Together, these results demonstrate the feasibility of utilizing conditional generative modeling of blood-based infrared spectra for virtual cohort construction, cohort balancing, and controlled in-silico phenotyping, paving the way toward more comprehensive and data-efficient studies in precision health.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Pattern Recognition (psychology) ; Generative Model ; Generative Grammar ; Infrared ; Spectral Line ; Anthropometry
ISSN (print) / ISBN 2398-6352
e-ISSN 2398-6352
Journal NPJ digital medicine
Publisher Springer
Reviewing status Peer reviewed
Institute(s) Institute of AI for Health (AIH)