Feasibility of Total White Blood Cells Counts by Visible-Near Infrared Spectroscopy

Total white blood cells (WBC) count is an important indication for infection diagnosis, in both human and veterinary medicine. State-of-the-art WBC counts are performed by flow cytometry combined with light scattering or impedance measurements, the clinical analysis laboratory. These technologies complex difficult to be miniaturized into a portable point-of-care (POC) system. Spectroscopy one of most powerful POC miniaturization due its capacity analyze low sample quantities, little no preparation, ‘real-time’ results. proportion 1:1000 red (RBC), latter dominate visible-near infrared (Vis-NIR) information their large quantities hemoglobin absorbance. detected traditional spectral because contained within interference bands. Herein, we perform feasibility study direct detection canine Vis-NIR spectroscopy applications, benchmarking current chemometrics techniques self-learning artificial intelligence—a new advanced method high-accuracy quantification from information. Results show that total can average limit 7.8 ×109 cells/L, R2 0.9880 between quantification. This result opens possibilities reagent-less technology diagnosis. As dogs range 5 45 obtained this research allows concluding use SL-AI algorithm step towards existence Spectral hemogram analysis.