Developing a predictive model for rapid stroke diagnosis via blood using mid-infrared spectroscopy.
Saiko Kino1, Tomohisa Ishida2, Kuniyasu Niizuma3
1Graduate School of Biomedical Engineering, Tohoku University, 6-6-05, Aza-Aoba, Aramaki, Aoba-ku, Sendai, Miyagi 980-8579, Japan.
Spectrochimica Acta. Part A, Molecular and Biomolecular Spectroscopy
|September 2, 2025
Summary
Mid-infrared (MIR) spectroscopy offers a rapid and cost-effective method for diagnosing stroke. This blood analysis technique accurately identifies stroke patients and can help differentiate stroke types, aiding timely treatment.
Area of Science:
- Biomedical Spectroscopy
- Clinical Diagnostics
- Medical Technology
Background:
- Stroke diagnosis requires rapid, objective methods for timely intervention.
- Limited healthcare resources necessitate faster, more accessible diagnostic tools.
- Mid-infrared (MIR) spectroscopy presents a simple, quick, and cost-effective blood analysis approach.
Purpose of the Study:
- Evaluate MIR spectroscopy for stroke diagnosis.
- Differentiate stroke patients from non-stroke individuals.
- Identify stroke subtypes and predict lesion volume.
Main Methods:
- Analyzed plasma from 324 individuals (160 stroke, 153 controls) using attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy.
- Employed partial least squares analysis of absorbance data.
- Assessed diagnostic accuracy via cross-validation.
Main Results:
- Achieved 87.9% accuracy in distinguishing stroke patients from controls (AUC 0.97).
- Identified ischemic stroke with 73% accuracy, outperforming hemorrhagic stroke detection.
- Observed plasma protein structural changes and increased lipid concentrations; correlated lesion volume prediction (ICH: 0.61, IS: 0.34).
Conclusions:
- ATR-FTIR spectroscopy shows promise as a rapid stroke detection tool.
- The method is minimally invasive and suitable for clinical application.
- This technique supports faster diagnosis and potentially improved patient outcomes.
