Back
Science

Study combines hyperspectral imaging and AI to detect oxidative stress in red blood cells

Generated on: Last updated: 1 sources
View source

AI and Hyperspectral Imaging Detect Oxidative Stress in Blood Cells

A new study published in Nature Communications Medicine details a diagnostic method that combines hyperspectral imaging (HSI) with artificial intelligence (AI) to detect oxidative stress in red blood cells. The researchers state that oxidative stress alters the optical scattering properties of red blood cell membranes, which can be detected using HSI.

The AI analysis achieved over 93% accuracy, sensitivity, and specificity in distinguishing between children with Autism Spectrum Disorder and neurotypical subjects in this initial study.

Methodology

The research employed a multi-step framework combining optical imaging, biochemical analysis, and machine learning.

  • Sample Collection & Imaging: Blood samples were collected and analyzed within five hours. A small droplet was imaged using hyperspectral dark-field microscopy, capturing spectral data across the 400–1000 nm range.
  • Spectral Analysis: The Spectral Angle Mapper (SAM) algorithm was used to identify and map eight distinct spectral signatures (endmembers) across cell membranes.
  • Modeling Oxidative Stress: To create a model, samples were treated with controlled concentrations of hydrogen peroxide.
  • Biochemical Validation: Lipidomic analysis using gas chromatography quantified changes in fatty acid composition.
  • Clinical Validation: Red blood cell samples from 31 neurotypical children and 27 children with Autism Spectrum Disorder (ASD) were analyzed.
  • AI Classification: Artificial neural networks (ANNs), combined with the TWIST optimization system, were used to classify subjects based on their spectral patterns.

Key Findings

The study reports that hyperspectral imaging can detect structural and biochemical changes in red blood cell membranes caused by oxidative stress.

  • In healthy samples, eight consistent spectral signatures were identified.
  • Oxidative treatment caused significant shifts in these spectral distributions, with specific endmembers increasing or decreasing.
  • Lipidomic analysis confirmed a decrease in polyunsaturated fatty acids and an increase in saturated fatty acids after oxidative treatment.
  • When applied to clinical samples, the method revealed similar spectral pattern changes in children with ASD as those seen in the laboratory oxidative stress model.
  • One spectral component is identified as a key indicator of oxidative damage, showing correlation with lipid composition.
  • Measurement of Na+/K+-ATPase activity showed a significant reduction in ASD samples, which correlated with specific spectral signatures.

Context and Future Potential

The researchers highlight that the method is non-invasive and requires only a small blood sample. They suggest the approach has potential for early detection of conditions related to oxidative stress, including some neurodevelopmental disorders.

The researchers propose the framework could be extended to other diseases linked to oxidative stress.

The study notes that future research with larger and more diverse populations is needed to validate and refine the approach.

Reference:
Vartian, R., Sansone, A., et al. (2026). AI-based autism identification from hyperspectral imaging detection of oxidative stress in pediatric red blood cells. Communications Medicine 2026. DOI: 10.1038/s43856-026-01581-y