Work

AI-based autism identification from hyperspectral imaging detection of oxidative stress in pediatric red blood cells

Year: 2026

Type: article

Abstract: Oxidative stress (OS) plays a key role in many pathologies, yet the non-invasive, label-free, and cost-effective detection remains a challenge. This study evaluates Hyperspectral Imaging (HSI) combined with AI to detect OS by identifying changes in red blood cell (RBC) membranes. An OS model for the HSI procedure is established by treating EDTA-anticoagulated whole blood with 1.5% hydrogen peroxide (H2O2) to induce stress without cell lysis. Membrane fatty acid composition (lipidome) is analysed via gas chromatography, while HSI in dark-field microscopy captures spectral signatures and their distributions in healthy and insulted RBC. The HSI methodology is then applied to RBC samples from 31 neurotypical (NT) children and 27 children with Autism Spectrum Disorder (ASD), a condition linked to OS. A deep learning algorithm is used to classify the clinical samples based on the identified OS signatures. Here, we show that significant spectral distribution differences are present in OS-exposed RBCs, which correlate with membrane lipidome remodelling. Notably, the OS-induced spectral differences in the H2O2 model mirror those observed between the ASD and NT groups. The AI-assisted analysis successfully classifies the pediatric cohort, achieving 93.2% accuracy in identifying ASD subjects. HSI, guided by OS-specific modeling and integrated with AI, provides a robust, scalable method for membrane diagnostics. This approach offers a promising pathway for personalized medicine and the non-invasive monitoring of oxidative stress-related conditions. Oxidative stress (OS) is an imbalance that occurs in some cells within the body. It is linked to various diseases, yet it remains challenging to detect early. Methods based on hyperspectral imaging (HSI), a technique that captures imaging data beyond the human visual spectrum, offers a cost-effective, non-invasive, and precise measurement of damage to cells occurring as a result of oxidative stress. We used HSI on a single drop of blood to examine red blood cell membranes. We found that cells exposed to OS could be distinguished from healthy cells using HSI. We used this method on blood samples from children with and without Autism Spectrum Disorder (ASD). Children with ASD could be identified with over 93% accuracy through AI analysis. This AI-aided HSI approach represents a promising clinical tool that could enable earlier intervention before cellular damage leads to severe health conditions. Vartian, Sansone et al. integrate hyperspectral imaging with AI to detect oxidative stress by analyzing red blood cell membrane changes in a hydrogen peroxide model and a cohort of autistic children. Spectral signatures correlate with membrane lipidome remodeling and allow the algorithm to identify autistic people with 93.2% accuracy.

Source: Communications Medicine

DOI: 10.1038/s43856-026-01581-y